master
85
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Niklas Wenzel
|
79bce0c881 |
tests : enable Gemma 4 in test-llama-archs (#31401)
* tests : enable Gemma 4 in `test-llama-archs` * tests : use GQA for Gemma 4 in `test-llama-archs` |
||
  Oliver SimonsandSigbjørn Skjæret
|
68d20b884c |
Quant: OCP FP8 E4M3 support (#27512)
* WIP OCP FP8 E4M3 support * Fix python type-checker * Materialize input_scales also for FP8 when converting * Fix conversion of https://huggingface.co/RedHatAI/Qwen3.8-27B-NVFP4 1. Per row FP8 wrongly fell to NVFP4 conversion, as NVFP4 checked on dims alone. Also check on dtype for FP8 2. Need to reshape FP8 QKV projections scales in the same way that weights are reshaped * Allow remaining FP8 tensors to be dequantized during conversion * Allow tensor-strategy for FP8-only compressed-tensor ckpts * Fix and test gguf-py behavior for FP8_E4M3 * Disallow QKV-fusion for FP8 temporarily * Fix conversion of fused qkvz & FP8 for Qwen3-Next * Avoid fusing FP8 for --fuse-gate-up-exps as we may have different ws * Emit warnings when not fusing FP8 during conversion * More FP8 conversion fixes * Add supported for strided copies to/from FP8 in CPU * remove unneeded scratch buffer from FP8 cpu cpy/dup path * add explanatory comments and TODOs * Add dedicated encoder and decoder tests for FP8 * Whitelist ggml_op_get_rows in metal instead of blacklisting required to fix failing CI, and white-listing should be more future-proof than adding FP8 to the black-list https://github.com/ggml-org/llama.cpp/actions/runs/38433916498/job/115422880633?pr=27512 * Fix more conversion bugs * Defer weight materialization during conversion * Blacklist fp8 in metal backend instead of white-list * Adjust indents * Fix lint + execute tests * Add fast CPU kernel for F8_E4M3 * Conversion fixes * Fix remaining gaps * Enable tied weights with shared scales * Make mandatory-F32 rules apply to FP8 during conversion * Fix python type checks https://github.com/ggml-org/llama.cpp/actions/runs/39765670052/job/119780379595?pr=27512 * Fix kaleidai unit-test failures https://github.com/ggml-org/llama.cpp/actions/runs/39765670125/job/119780383150 * Relax numeric precision constraints for pre-check * Leave fast-FP8 CPU on RISC-V for follow-up We already exclude arm from the fast-path * Allow output scale tensors to be located in any gguf shard * Move test_conversion_fp8.py test execution to behavior-check.yaml * Apply batched suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Move mixed compressed-tensor logic into dequant_fp8 + add unit-tests for it * Install all requirements also on Windows for behavior-check Fixes https://github.com/ggml-org/llama.cpp/actions/runs/40535852590/job/122300758223?pr=27512 * Unmap lazy tensors before clean-up in Windows Should fix https://github.com/ggml-org/llama.cpp/actions/runs/40539797824/job/122314782459?pr=27512 * LF line endings https://github.com/ggml-org/llama.cpp/actions/runs/40539798168/job/122314791118?pr=27512 * Extract FP8 tests from llama-arch to its own test-fixture See https://github.com/ggml-org/llama.cpp/pull/27512#discussion_r4400628221 * Update gguf-py/gguf/scripts/gguf_convert_endian.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> |
||
 Xuan-Son Nguyen
|
78feec062d |
model: mistral le chonk (#31376)
* llama: extend DSA and sdpark to new model * fix ci |
||
 Giuseppe Scrivano
|
abb76ab380 |
model : Support Limite 1B - Violetto (#29433)
* gguf-py : add Limite arch Assisted-by: Claude Opus 5.5 Signed-off-by: Giuseppe Scrivano <giuseppe@scrivano.org> * convert : add Limite support Assisted-by: Claude Opus 5.5 Signed-off-by: Giuseppe Scrivano <giuseppe@scrivano.org> * llama : add Limite support Assisted-by: Claude Opus 5.5 Signed-off-by: Giuseppe Scrivano <giuseppe@scrivano.org> --------- Signed-off-by: Giuseppe Scrivano <giuseppe@scrivano.org> |
||
 
|
19cce69199 |
model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B (#31252)
* model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> Co-authored-by: Xuan-Son Nguyen <son@huggingface.co> Assisted-by: Claude Opus 5.5 * tests : set the SWA rope base of the LFM3 test model Assisted-by: Claude Opus 5.5 * llama : enable recurrent state rollback for LFM3 Assisted-by: Claude Opus 5.5 * Apply batched suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> Co-authored-by: Tarek Dakhran <github@dakhran.com> * gguf-py : align the lfm3vl mapping comments Assisted-by: Claude Opus 5.5 * llama : fix CRLF line endings from the review suggestions Assisted-by: Claude Opus 5.5 * tests : add the LFM3 Metal fusion baseline Assisted-by: Claude Opus 5.5 * llama : keep the LFM3-VL depthwise conv kernels in F32 when quantizing Assisted-by: Claude Opus 5.5 --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> Co-authored-by: Xuan-Son Nguyen <son@huggingface.co> |
||
 Georgi Gerganov
|
8542e94350 |
tests : speed up tensor data generation and model saving (#31145)
* tests : speed up tensor data generation and model saving Refactor save_models to create only the model, not a llama_context, which is not needed for saving. Replace the slow std::normal_distribution draw with a splitmix64 + box-muller normal generator. Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB) * tests : use a shared pool of normal draws for tensor data Generate a pool of normal draws once with std::mt19937 and std::normal_distribution, then have every tensor copy a cyclic slice of it instead of running a per-tensor box-muller. The name-keyed slice selection keeps the draw deterministic. Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB) * tests : log the size of saved models Report the produced file size in bytes and MB after each save. Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB) * tests : simplify the model save log Put the model name, target and size on one line per saved model. Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB) |
||
|
Georgi Gerganov
|
fd8f8451a2 |
tests : refactor test-llama-archs to not link internal libllama symbols (#30880)
test-llama-archs included src/llama-arch.h and src/llama-model-saver.h, which prevented building on Windows with shared libraries since the used symbols are not exported from the DLL. - declare llama_arch_* wrappers around the internal llm_ arch query functions in the llama-ext.h staging header, together with llama_arch_kv_name() and llama_arch_supports_save() - slim llama_model_saver down to the private implementation of llama_model_save_to_file(): the fixture-writer half used by the test moves into tests/test-llama-archs.cpp as a local kv_writer - replace the roundtrip saver usage with the public llama_model_save_to_file() writing to a temp path (also removes the tmpfile() fd leak and its Windows workaround) - move test-llama-archs, test-generate-models, test-llama-context and test-fusion out of the NOT WIN32 OR NOT BUILD_SHARED_LIBS guard Assisted-by: pi:llama.cpp/ggml-org/GLM-5.3-Flash-GGUF (2x DGX Spark (RDMA, TP=2)) |
||
  Aman GuptaandDaniel Han
|
74bca39500 |
model: DSV4.1 flash (#31086)
* model : add DeepSeek-V4.1-Flash (deepseek41) * deepseek41 : remove MXFP8, convert the Engram table to BF16 * deepseek41 : compute the compressed-KV read layers once in the cache * deepseek41 : use get_cells() for the shared-history check, drop llama_kv_cache::seq_pos_tok_le * deepseek41 : gather the Engram rows in-graph like qwen4exp, drop the host gather * deepseek41 : keep the Engram hash constants in hparams.ple_*, one module per Engram layer * deepseek41 : drop the LLAMA_DSV41_KV_MIRROR toggle * deepseek41 : keep il last in build_hc_mixes * deepseek41 : sort the top-k rows before the sparse gather * tests : add deepseek41 to the Metal fusion baseline --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> |
||
 alexey-rsiandSigbjørn Skjæret
|
a37cc46104 |
models : add Flint model (FlintForCausalLM) (#30928)
* Add Flint model (FlintForCausalLM). Assisted by Codex * cleanup * one more --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> |
||
 Maphist0andSigbjørn Skjæret
|
7775ffb7e4 |
model: Add support for SenseNova U1 model (#28919)
* model : add SenseNova U1 understanding support Add support for the dense SenseNova U1 understanding branch, including the U1.5-8B-MoT model. - Add HF-to-GGUF conversion for NEOChatModel, excluding MoT generation tensors and concatenating temporal and spatial Q/K normalization weights. - Register the sensenova_u1 GGUF architecture and custom spatial RoPE metadata. - Implement temporal/spatial Q/K normalization with 4-axis RoPE. - Keep U1-specific text position handling in the model implementation. - Add synthetic architecture coverage for sensenova_u1. Only the dense understanding branch is supported; generation branches are intentionally rejected during conversion. * conversion : treat one-expert SenseNova U1 configs as dense * mtmd : add SenseNova U1 vision support Add conversion support for the SenseNova U1 vision encoder and implement its CPU mtmd projector graph. The graph applies patch embedding, GELU, adjacent-pair 2D RoPE, spatial downsampling, and dense projection for dynamic-resolution image inputs. * mtmd : fix SenseNova U1 vision token layout * model : clean up SenseNova U1 RoPE metadata Replace the hard-coded spatial RoPE key with shared GGUF and LLM_KV definitions used by conversion, model loading, and architecture tests. Clarify why SenseNova U1 retains its custom text-position input: U1 uses [t, 0, 0, 0], while the generic M-RoPE input uses [t, t, t, 0]. * mtmd : simplify SenseNova U1 projector integration Map the SenseNova U1 dense projection to the standard mm.0 weight and bias tensors and reuse the shared projector fields in the loader and graph. Read vision parameters from the checkpoint configuration and remove the U1-specific tensor names and model fields while preserving its strided projection, bias, and row-major token layout. * mtmd : fix SenseNova U1 image positions and attention * fix spacing * mtmd : restore generic test input chunks * mtmd : restore SenseNova U1 integration after upstream merge * Update conversion/sensenova_u1.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update src/models/sensenova-u1.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * model : remove SenseNova U1 BF16 activation casts Use standard backend precision handling for QKV, FFN, and output projections instead of casting inputs based on the output tensor type. Assisted-by: Codex * Update src/models/sensenova-u1.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> |
||
|
Georgi Gerganov
|
7879491cf4 |
tests : make MoE router selection independent of the backend noise (#30818)
* tests : make MoE router selection independent of the backend noise
The router scores are in the range [0, 1), so a random draw can leave the
last expert (or expert group) still selected and the first one dropped tied
within the noise between the backends. They then route a token to different
experts and the logits differ by 4e-3 instead of the usual 5e-7.
Beam is the only arch here with a real top-k (8 experts, 2 used) and a group
top-k (4 groups, 2 used), so it is the only one that hits this: 2 of 20 seeds
failed on an M2 Ultra, the other MoE archs select 2 of 2 and cannot tie.
Fill the selection bias with a ramp of step 2 to give every expert a score
range of its own, which turns the top-k into a function of the expert index
alone. The bias affects only the selection, the weights still come from the
unbiased probs, so the MoE output keeps its magnitude. Beam now matches the
CPU reference within 4e-7 for all of 160 seeds.
Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB)
* tests : tell the CPU and the GPU of an Apple SoC apart in the device table
Both devices report the same description ("Apple M2 Ultra" here), so the
device column of the test table had two indistinguishable rows and a failing
row did not say whether the Metal device or the host CPU produced it.
Add the device name, which is also what -b takes, unless the description
already is the name.
Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB)
|
||
 Pascal
|
10b8b75534 |
tests: give the random model generator a per-tensor filler table (#30674)
* tests: give the random model generator a per-tensor filler table Muse Spark makes test-llama-context fail on state_load, cp_h and cp_d on about six percent of the random seeds, with an NMSE of 1.0e-05 to 1.4e-05 against a threshold of 1.0e-05. The sliding window is what exposes it: a restored state keeps the window alone, so the attention of an SWA layer reduces over a different cell layout and the continuation is not bit exact. Every SWA model carries that, at 1e-08. Muse Spark carried it at 1e-05. The generator is what turns 1e-08 into 1e-05. A norm preserving residual gate holds alpha^2 + beta^2 == 1 and the conversion resolves both weights from one raw weight, while the generator draws every tensor on its own. The pair then scaled the stream and the branch independently, the stream lost an arbitrary factor at each layer, and the model became an amplifier. The weights the test ran on were not a Muse Spark. Per-tensor rules lived inside the write path, where a flag picked the values of a tensor inside each of the two branches that store them, so a new rule meant a new flag threaded through both. The file asks to be rid of that in a TODO of its own. Give each rule a filler, pick one from a table keyed on a substring of the tensor name, and keep a single write path behind it. Mamba moves into the table and Muse Spark joins it: the gate filler draws the raw weight once per block and resolves alpha and beta the way the conversion does. Over a thousand seeds on a CPU build the worst case drops from 1.36e-05 to 2.48e-06 and the median from 4.10e-06 to 5.48e-07, with no seed above the threshold. The other 131 models come out identical to the bit, since no other architecture carries these tensors. ctest is green on a CPU build and on a CUDA build. * tests: draw every tensor filler from fill_normal The fillers repeated the generator and the distribution each time. The normal draw now takes its key and the other fillers transform its values, so the generator lives in one place. The generated models are identical to the bit. |
||
 Xue ZhenliangandSigbjørn Skjæret
|
62318cd57d |
model : add Kolibri-1 (Aleph-Alpha) support (#30673)
* model : add Kolibri-1 (Aleph-Alpha) support Kolibri-1 is a bilingual German/English MoE reasoning model with 78B parameters and 3.46B active per token: 50 layers, 384 routed experts plus one shared expert. Attention interleaves four sliding layers at a 513 window with one full layer. The sliding layers rotate with NeoX RoPE, the full layers are NoPE. GQA runs 48 query heads against 4 KV heads at head_dim 128 with a QK-RMSNorm, and every block carries four RMSNorms, so the attention and the MLP output are normalized before they rejoin the residual stream. Routing picks the experts from logits + expert_bias and weights them with the sigmoid of the unbiased logits, without renorm. The converter reuses AfmoeModel for the per-expert checkpoint layout and the expert selection bias, and writes the shared expert and the per layer sliding window pattern. The released FP8 checkpoint needs no special code, it goes through the generic weight_scale_inv path. Three tensor names are added to the mapping (post_attn_norm, post_ffn_norm, moe.router.expert_bias) and the 128k vocabulary registers the qwen2 pre-tokenizer by hash. The arch is registered in test-llama-archs, with GQA and the sliding window pattern. Assisted-by: DeepSeek Harness (DeepSeek V4.1 Flash) * Update src/models/kolibri1.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Add fusion records for kolibri1 * Update src/models/kolibri1.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> |
||
|
Daniel Han
|
01fc3aae84 | model: add Beam (Reflection) (#30670) | ||
|
Georgi Gerganov
|
88aaf325a7 |
tests : catch vanished rows in the fusion baseline (#30618)
* tests : update the Metal fusion baseline Re-record the MTL fusion baseline with the current build: 276 rows over 131 dummy models. Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * tests : fail test-fusion when a baseline row stops matching The report was built from the counters the run produced, and the baseline was only ever used as a lookup table, so a fusion that stopped matching produced no row and was never compared. qwen4exp and mellum lost their fusions this way while the Fusion / metal job stayed green. Report a baseline row that the run does not reproduce as a regression. Scope the pass to the arches that were actually run so --model keeps working. Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * pi : never write inline comments unless the user asks Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * tests : keep the mellum dummy model softmax-gated mellum reads expert_gating_func from the GGUF since #30578, while the fixture writes sigmoid for every MoE arch, so the Mellum dummy model stopped building the softmax MoE routing fusion. Write softmax for mellum, matching the arch default and the GGUFs that conversion/mellum.py produces. Re-record the MTL baseline: the routing row is back, 277 ok / 0 failed. Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * pi : use emoji in the AI stats disclosure Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * pi : list the disclosure model after the hardware Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * pi : use monochrome symbols in the AI stats disclosure Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * tests : add muse-spark to the Metal fusion baseline Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) |
||
  Karthik VijayanandKarthik Vijayan
|
f12aaa344c |
Fix failing RocM tests (#30611)
Co-authored-by: Karthik Vijayan <kavijay@microsoft.com> |
||
|
ba3c05f71d |
model: add Muse Spark Open (text, vision and audio) (#30616)
* model: add Muse Spark Open (text, vision and audio) Muse Spark Open is a latent space MoE: the residual stream stays at 8192 while the 256 experts live in 4096, with a projection down and up around them, top-8 sigmoid routing with a correction bias. Attention interleaves three sliding layers at a 2048 window with rope for one global layer without rope, with a sigmoid output gate and a weightless QK-norm. Residuals are norm preserving, their gate is folded at conversion time. Vision reuses the Muse Glimmer tower. Audio is a causal convolutional pyramid with no attention and no spectrogram, four stages folding 16, 6, 5 and 4 samples into the channel dim, one embedding per 80 ms of 24 kHz. The quantizer keeps the latent projections and the attention gate at Q8_0, a little over 1% of the weights, since the whole residual stream passes through them and the low-bit types turned the output into a repeating loop. The model saver writes the post norm epsilon, and the arch is registered in test-llama-archs. Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Muse Spark: drop the redundant forward expand * Muse Spark: drop the redundant forward expand and tighten the comments * Update src/llama-quant.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update src/llama-graph.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: Pedro Cuenca <pedro@huggingface.co> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> |
||
|
Karthik VijayanandKarthik Vijayan
|
3e4dfa8f39 |
models : add maion-coder (#29778)
* Add Support to maion-coder arch * iAdd Support to support Draft models * Address comments * Remove maion context shift function --------- Co-authored-by: Karthik Vijayan <kavijay@microsoft.com> |
||
|
Xuan-Son Nguyen
|
097cf33d94 |
model: support vllm decision 2 model (#30378)
* models: support pplx-decider * vllm d2 * update * clarify naming rule * stricter validation * fix ci * rm redundant filter_tensors |
||
|
Aman Gupta
|
c811cb8f0a | llama: support MoE cache over multiple GPUs (#30112) | ||
|
Aman Gupta
|
d6cf9acb25 |
llama : add a GPU cache for MoE experts kept in host memory (#29887)
* llama : add a GPU cache for MoE experts kept in host memory Assisted-by: Claude * use llama_moe_cache_ptr |
||
      
|
4625240437 |
model : add K2 Horizon dense and MoVA support (#29535)
* model: K2 Horizon gguf conversion code
* model: loading hparams and tensors in k2-horizon.cpp
* model: K2 Horizon compute graph
* model: K2 Horizon compute graph adjustment and registering tokenizers
* model: K2 Horizon chat template and accomodate safetensors naming
* unicode : add the K2-Horizon pre-tokenizer splitter
The K2-Horizon regex had no arm in unicode_regex_split_custom and fell through to the
general std::regex fallback, which fails two ways.
On MSVC std::regex rejects \p{...}, so no K2-Horizon GGUF loads on Windows at all:
llama-quantize, llama-imatrix and llama-perplexity all abort with
regex_error(error_escape) before a token is produced.
Where the fallback does compile it is still wrong. unicode_regex_split collapses each
codepoint to a single byte naming its Unicode category before matching, and U+200C/U+200D
are category Control, which has no entry in k_ucat_cpt, so both become the 0xD0 fallback
byte. The literal and alternatives in K2's regex can then never match and
every ZWNJ or ZWJ ends a letter run.
The splitter is the existing llama3 one with a single rule widened, since K2's regex
differs from llama3's only in that a letter run also takes marks, ZWNJ and ZWJ.
tests/test-unicode.cpp gains a case for this: it fails before the change with
[Amy] [ZWNJ khaham] and passes after with the run intact.
* tests: expand K2 Horizon unicode splitter coverage
* unicode: handle K2 Horizon case folding and empty input
Assisted-by: Codex
* jinja : support sequence indices in selectattr and rejectattr
Assisted-by: Codex
* model : add K2 Horizon dense and MoVA support
Includes the K2 Horizon implementation from ifm-ai/llama.cpp with converter, tensor-parallel and model save/reload fixes.
Assisted-by: Codex
* chat : support K2 Horizon reasoning and tool calls
Assisted-by: Codex
* conversion: remove obsolete K2 Aurora alias
Assisted-by: Codex
* k2-horizon: enforce response schemas and load YaRN betas
Constrain final JSON after reasoning, accept flexible JSON tool envelopes,
enforce XML dialects, and handle repeated or alternate thinking markers.
Load YaRN beta metadata instead of retaining the default values.
Add schema, streaming, continuation, and model reload regressions. Validate
CUDA and CPU builds and 0.9B, 4B, and MoVA conversation/tool round trips.
Assisted-by: Codex
* renaming template fixture
* adressing cisc follows ups
* desloppify the parser / adress aldehir comments
* clean test-chat
* remove fallback : model trained mostly on high anyway
* fix k2 attn_v_exp tn splitting and metal fusion baseline
* k2-horizon : forward expand views before sums
* k2-horizon: copy embds before group norm to fix TP
* disable tesnor parallelism
---------
Co-authored-by: Ryandito Diandaru <ryandito.diandaru@mbzuai.ac.ae>
Co-authored-by: WestWaters <mario.papaleo2013@gmail.com>
Co-authored-by: Natani L. Mayday <71436458+TaskPuppyNatani@users.noreply.github.com>
Co-authored-by: West <100190545+WestWaters@users.noreply.github.com>
Co-authored-by: aaryamonvikram <aaryamonvikram@gmail.com>
Co-authored-by: aaryamonvikram <96529820+aaryamonvikram@users.noreply.github.com>
|
||
|
Xuan-Son Nguyen
|
4fbc76dec5 | model: support embeddinggemma2 (text+vision+audio) (#30054) | ||
|
Aman GuptaandGeorgi Gerganov
|
6753a033f0 |
ggml: refactor selective expert copying to user code (#29943)
* ggml: refactor selective expert copying to user code * tests: enroll two models into selective expert copy test * tests: use deepseek2 as test model * improve comment in ggml-backend.h Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * cont: fix whitespace * cont : better comments Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> |
||
 Ihar Hrachyshka
|
cbb7d52ecb |
test-llama-archs : initialize backends before generating models (#30034)
With GGML_BACKEND_DL=ON, backends must be loaded explicitly before creating models. Assisted-by: Codex |
||
|
Xuan-Son Nguyen
|
0bb496dbd3 |
llama: support both embd + raw tokens in batch (#29622)
* llama: support both embd + raw tokens in batch * add to test-llama-archs * also check case llm_arch_supports_mixed_batch = false * constant graph topology * have dedicated input for mixed case * rm set_tensor_backend * is_embd --> type * consolidate m-rope pos handling into one place * nits |
||
|
Xuan-Son NguyenandSigbjørn Skjæret
|
99b95488ca |
model: add support for clef decision model (text-only) (#29831)
* init support for clef (text only) * more static graph * clean up * nits * nits 2 * Update gguf-py/gguf/constants.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> |
||
 Sihan Yu
|
4f31296a90 |
test-llama-archs : toggle causal_attn to catch graph shape changes (#29724)
After the device decode, flip causal_attn off, decode n_ubatch/2 then n_ubatch tokens. Both have the same node count, so a shape that depends on the flag makes the second reallocate at an unchanged graph size, which aborts under GGML_SCHED_NO_REALLOC. Skipped for the encode archs. |
||
|
Xuan-Son Nguyen
|
60e9cf7a7b |
batch: migrate the rest of examples to llama_batch_ext (#29601)
* migrate the rest * test-thread-safety * rm common_batch_staged |
||
|
Pascal
|
3b3d022b82 |
ci : fix Models Backend Check by shortening the hrm_text fixture (#29744)
The fixture recycles its two blocks over 8 cache slots, so the fp16 error builds up past the 1e-4 NMSE bound on the Vulkan T4 and WebGPU jobs of Models Backend. Two l-cycles keep every branch of the cycle loop and halve the error. |
||
  
|
649dcb1036 |
add GLM-5.3-Flash (GLM5-Next) support (#27773)
* Rebase GLM-Next support onto master, and migrate to llama-memory-hybrid-idx * Add initial MTP support * Merge branch optimizations. Reduce allocated compute buffer size, speed up long context decode, fla, and slight MTP improvements. * Review driven changes, remove env vars, protect tensors * Strip MTP for initial PR * Clean up after mtp strip * Clean up after mtp strip * Update speculative.cpp * Update llama-context.h * Clean up after mtp strip * Fix tokenizer ignore merges * Improve quantization protection selection * Refactor mhc helpers, graph base * Lint Fixes * Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Skip glm5-next in model saver, fix CRLF * Skip glm5-next in sweep * Remove T4 fallback * Review cleanup * Review suggestions * Defer separate MTP gguf handling to MTP PR, drop filter * Repad n_head_kv * kpool init apply * Order by descending score * Drop guard * read kpool from hparams, clarify kpool cache flags, remove kpool_build_state(nullptr) * Add glm5-next support to model saver and add arch test fixture * Review cleanup * Kpool pooled caching clarify * Add multi stream support * Finish Rebase * Sparse FA fir DSA prefill * Const * Update llama-model.cpp to fix rebase error * gguf-py : merge tensor map entries for HC tensors * model : use build_gdn_l2_norm in GLM5_NEXT implementation * chore : remove trailing whitespace * model : use new OP precision setting API in GLM5_NEXT implementation * mtmd : use ggml_swiglu_clamp in GLM5V and apply the image token limit The two clamps around swiglu_split are what ggml_swiglu_clamp already does, so the clamp bounds collapse back to one value. GLM5V also never called set_limit_image_tokens(), so --image-max-tokens had no effect. Assisted-by: Claude Opus 5 (cherry picked from commit 46d18e12d422be4cc04a70e4a9a9e0168bb3d5b7) * llama : keep the GLM5-Next k-pool layout across ubatches The layout was rebuilt from a full cell scan on every ubatch. Pools are fixed by the positions relative to the sequence's first one, so the layout now lives on the memory and a ubatch only appends to it. A sequence edit no longer stales every pooled key either, only the ones at or after the edited position, which makes a tail seq_rm free. The pooling subgraph is built unconditionally so the graph shape no longer changes every kpool tokens, and the pool axis is folded into rows before soft_max, which otherwise exceeds the CUDA gridDim.y limit past n_kv 262144. Assisted-by: Claude Opus 5 (cherry picked from commit 5d1c40b93e17fddbf73b785efe43e0d02ccb3977) * model : write the GLM5-Next recurrent rollback checkpoints The conv state and the delta net state were only written to the live row, so a rollback restored whatever the checkpoint rows happened to hold. Take the same route as kimi-k3: build_recurrent_attn for the state, and write all K_rs conv groups. That also drops a state view that assumed contiguous rows. Enroll the arch in test-recurrent-state-rollback, which catches this under its garbage-filled cache pass. Assisted-by: Claude Opus 5 (cherry picked from commit 5ace37e86d5d448e83ef5dde5632c748185b18cd) * llama: fix PR #27773 test-save-load-state restore failure Clear the attention and indexer cache data after a failed hybrid state restore so restored NaNs cannot affect a later sequence. Assisted-by: Codex * llama: fix PR #27773 gpu-rocm graph reallocation Reserve the full GLM5-Next pool capacity and dirty pool count. The gpu-rocm Test step aborts when n_new grows while the graph node count stays fixed; CUDA, Vulkan, Metal, and WebGPU checks report the same error. Assisted-by: Codex * llama : fix GLM5-Next k-pool layout staleness after edits and shared teardown Two defects in the cross-ubatch k-pool layout added by the k-pool commit: 1. Wrong results. An edited sequence only rebuilt its pool layout when its cell count changed, so if the first ubatch after an edit added back exactly as many cells as were removed, the stale position-to-cell list survived. With a unified cache and more than one sequence, where another sequence takes the freed cells, the reused layout points at the wrong cells (CPU: large logit drift, CUDA: NaN). Rebuild whenever the sequence is stale, not only on a size mismatch. 2. Slowdown. "shared" mode was assumed to end only with an edit that forces a rebuild, but sharing also ends when the other sequence is removed. The survivor kept shared = true, pinning cache_safe off and re-pooling every pool on every ubatch (server trigger: n>1 completions with -kvu, via the seq_cp in copy_state_to). In seq_rm, if the layout has shared cells, stale every sequence so one rebuild re-derives sharing and cache_safe returns to 1. Assisted-by: Claude Opus 5 * llama : fix build_attn_mha stream stride for non-contiguous q build_attn_mha split the batch into streams with a stream stride of q->nb[3]/n_stream. That only equals one stream's span, (ne[2]/n_stream)*nb[2], when q is contiguous. GLM5-Next is nope-only, so it does not concat a rope part and passes the permuted q_absorbed straight in, where nb[3] != ne[2]*nb[2]; the stride was then n_head times too large and every stream s >= 1 read another head's queries. Split-KV (-np N without --kv-unified) multi-stream prefill was wrong for every stream past the first. Unified KV and decode were unaffected (n_stream == 1, and decode takes the gather path). Other MLA models concat rope so q is contiguous and the computed value is unchanged for them. Compute the stride from the token dimension, which is identical for a contiguous q. Assisted-by: Claude Opus 5 * llama : re-derive GLM5-Next k-pool sharing on state_read/state_drop The shared-cell teardown added to seq_rm (stale every sequence when the layout has shared cells, so a survivor does not keep shared = true and pin cache_safe off) was missing from the other paths that can free shared cells: state_read and state_drop staled only the one sequence. Apply the same re-derivation there and correct the comment that claimed sharing ends only via an edit or seq_rm. Assisted-by: Claude Opus 5 * quant : drop duplicate GLM5-Next hc_ filter The hc_ name filter was listed twice in the GLM5_NEXT protection block. Assisted-by: Claude Opus 5 * glm5-next: scope K-pool cache access to indexed operations * glm5-next: keep K-pool access in hybrid index memory * glm5-next: keep mHC graph builders model-local * glm5-next: mark only touched pools per ubatch --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> Co-authored-by: Piotr Wilkin <ilintar@gmail.com> |
||
  Tobyandaetherbird
|
f830688e91 |
model : add Ling 3.0 VL support (#29151)
* model : fold Ling 3.0 VL into the BailingMoeV3 architecture Assisted-by: Scout * model : keep shared NORM rope list intact when gating bailingmoe3 on mrope sections --------- Co-authored-by: aetherbird <aetherbird@users.noreply.github.com> |
||
  Masashi YoshimuraandJohannes Gäßler
|
d2e54583c7 |
tests: add -b/--backend option to test-llama-archs for testing a specific backend (#27372)
* tests: add backend option to test-llama-archs * Update tests/test-llama-archs.cpp Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * remove extra space --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de> |
||
|
Georgi Gerganov
|
161755f29e |
test-llama-archs : make tensor data stdev configurable and improve help (#29133)
* test-llama-archs : make tensor data stdev configurable Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * test-llama-archs : expand usage and add examples Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * test-llama-archs : fail on unknown args and log usage Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * test-llama-archs : add test run summary Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * test-llama-archs : initialize Mamba ssm_a negative Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * test-recurrent-state-rollback : report NMSE for logits mismatches Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * test-recurrent-state-rollback : use NMSE for rollback logits checks Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * tests : disable invalid test * cont : adjust nmse_eps * tests : zero DSA indexer score projection in synthetic fixtures Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * cont : add support for `--arch` regex * cont : alternative top-k stability * cont : indentation * cont : fix top-k value * cont : consistent logs |
||
|
Georgi Gerganov
|
5b59b83f4e |
metal : add MoE and SSM_CONV fusion optimizations (#28948)
* metal : add top-k MoE fusion Adds a Metal fusion for SOFT_MAX + ARGSORT + GET_ROWS with optional routing-weight normalization and scale, matching the top-k MoE fusion available in the CUDA and Vulkan backends. The fused kernel writes the selected expert ids and routing weights directly, eliding the separate softmax, argsort, get-rows, sum-rows, clamp, div and scale kernels. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : add MoE weighted reduction fusion Fuses MUL(experts, weights) plus the expert VIEW/ADD chain into one kernel that computes the weighted sum directly. The graph_optimize hook keeps the expert and weight buffers alive until the fused output so the allocator cannot reuse them while the kernel is still reading them. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * tests : expose MoE weighted reduction in fusion baseline Use 2 experts per token in the generated MoE test models so the Metal MoE weighted reduction fusion (MUL + ADD) is exercised by test-fusion. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : fuse RMS_NORM + SCALE Adds NORM/RMS_NORM + SCALE fusion to the Metal backend by reusing the norm+mul kernel with a scalar scale flag. Adds test coverage for both NORM+SCALE and RMS_NORM+SCALE and regenerates the fusion baseline. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : use function constant for RMS_NORM + SCALE Replaces the runtime use_scale karg with a Metal function constant. The norm+mul kernel is compiled with FC_norm_use_scale=false for MUL fusion and FC_norm_use_scale=true for SCALE fusion, so the fused kernel has no runtime branch. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : use function constant for top-k MoE with_norm Replaces the runtime with_norm karg with a Metal function constant. The top-k MoE kernel is compiled separately for the normalized and non-normalized routing variants, removing the runtime branch. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : rename moe_weighted_reduction suffix to moe_reduce Shortens the MoE weighted-reduction fusion identifiers, kernel, pipeline, matcher, args struct, and test op name from moe_weighted_reduction to moe_reduce. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : add MUL_MAT + UNARY and MUL_MAT + ADD + UNARY fusion Adds dense mat-vec activation fusion for sigmoid/silu and bias+softplus. The mat-vec kernels apply the activation/bias epilogue via function constants, avoiding the separate unary/add passes. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : revert MUL_MAT + UNARY and MUL_MAT + ADD + UNARY fusion The mat-vec activation fusion regressed decode throughput on Qwen3.6-35B-A3B by ~8% (tg32 81.5 vs 88.5 t/s). The regression is caused by loss of concurrency: the standalone unary kernels previously overlapped with other mat-vec work, while fusing the activation into the mat-vec kernel serializes it on the critical path. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : add SSM_CONV + UNARY (silu) fusion The SSM_CONV kernels apply silu directly via a function constant, eliding the separate unary pass. Regenerates the fusion baseline. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : address fusion review comments - Fix declaration/table alignment - Rename top-k MoE kargs fields to val_clamp / val_scale - Move moe-reduce alloc-deps handling into a general fusion helper - Remove the public moe-reduce matcher API Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : fix unused parameter in top-k MoE fusion check Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : guard SSM_CONV fusion lookup behind use_fusion Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : track all fused outputs in graph reorder Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : keep top-k MoE logits alive until fused output Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : refactor alloc deps to pattern-driven approach Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : check fused kernel destination in concurrency tracking Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * meta : forward graph_optimize to underlying backends Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : use vector for fusion table Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * meta : keep graph_optimize unimplemented Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * parallel : fix non-deterministic prompt selection Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * parallel : support dummy models and add global logits run hash Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : sync cross-device copies with destination completion event Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : avoid const_cast in fusion alloc deps Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : skip fusions with aliased sources Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : hide fusion pattern definition Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : use vector fusion op sequences Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : drop redundant struct keywords Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : add alloc deps comment separator Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : generalize fusion output memory ranges Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : rename fusion out_offsets to outs Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : avoid dst vector in memory range check Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : optimize fusion matching and multi-output handling - use pointer arithmetic for fusion info count lookup - avoid heap allocations in top-k MoE and MoE reduce pattern matchers - use fusion outs for multi-output subgraph checks Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * Revert "parallel : support dummy models and add global logits run hash" This reverts commit 57c7caf941c1b43c270fd5009c9f175063522e96. * fusion : update MTL.csv * metal : unroll constant loops in top-k MoE kernel Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : use function constants for top-k MoE n_expert and top_k Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : rename fusion kargs to scale and clamp Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : use function constants for moe_reduce and ssm_conv Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * fusion : update MTL.csv |
||
|
Georgi Gerganov
|
efa28e950e |
test-llama-archs : generate dummy test vocab (#29084)
Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp |
||
 GeorgeandSigbjørn Skjæret
|
7d6f5d02bb |
model : add support for HrmTextForCausalLM (DFM Mimir 1B) (#27625)
* model : add support for HrmTextForCausalLM (DFM Mimir 1B) HRM-Text runs two transformer stacks (low, high) in an alternating cycle over the same token stream. The low-cycle state z_l starts from a learned [n_embd] tensor and is broadcast over positions. - conversion: new writer for the fused gqkv projection (order gate,q,k,v) remapped to llama.cpp q/k/v plus a separate sigmoid gate tensor - loader: block_count = lps * h_cycles * (l_cycles + 1) cache slots aliasing 2*lps physical blocks via struct copies - graph: looped build with sigmoid-gated attention, SwiGLU FFN and parameterless RMS norms; learned embedding_scale applied in build_inp_embd - saver: pointer-deduplicated layer loop (looped archs alias tensors) - tests: hrm_text fixture (lps 1, h 2, l 3) in test-llama-archs Limitations: causal attention only - the upstream prefix-LM mode is not implemented (the prefix_lm GGUF key round-trips unused). The KV cache holds one entry per pass: 128 layers for Mimir 1B, i.e. 4x a same-width 32-layer model - about 3072 MiB at ctx 4096 in F16 (halves with q8_0 KV + FA). Every token runs all 128 block passes, so decode cost is roughly 4x a dense model of equal width (2.65 t/s BF16, 8-thread desktop CPU). Verified against the HF reference: identical argmax at 334/334 positions across 20 prompts (BF16 GGUF vs FP32 golden). q8_0 requant: 95.8% top-1, all remaining misses inside the HF top-5 (accumulated error over 128 sequential blocks). AI usage disclosure: YES Used GLM-5.3 for the majority of code AI-generated under my direction, all gates verified locally. All in all I could say that I have written less than 20% of the code and most of the heavy lifting has been done by the model. As such, this should be considered experimental. * Update conversion/hrm_text.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update src/llama-arch.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * convert : add gguf_writer methods for hrm_text metadata replace raw add_uint32/add_bool calls with dedicated GGUFWriter methods, following the add_embedding_scale pattern Assisted-by: GLM-5.3 * convert : map regular hrm_text tensors via tensor_mapping delegate unfused checkpoints to the base tensor mapping; training-style attn. names are renamed to self_attn. so the patterns match Assisted-by: GLM-5.3 * model : format hrm-text build_* calls as in other models one argument group per line, matching sibling model files Assisted-by: GLM-5.3 * llama : move hrm z_l_init table entries out of the nemotron group place the name and tensor-info entries with the other global input tensors Assisted-by: GLM-5.3 * convert : slim down hrm_text comments Assisted-by: GLM-5.3 * convert : build hrm_text block tensor names from the {bid} template The tensor map holds concrete per-block names, so format the template with the computed layer index before handing it to super(). * llama : name hrm metadata keys in their own hrm. namespace The four keys are arch-independent, unlike the arch-substituted Keys.LLM entries, so group them under Keys.HRM (like Keys.Split) and rename the llm_kv entries to LLM_KV_HRM_*. Only our own GGUFs carry the old hrm_text.* keys; they are regenerated. * Update src/llama-model-saver.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * llama : keep hrm metadata keys arch-substituted Per review: the GGUF keys stay "{arch}.h_cycles" style, so the Python members drop the LLM_KV_HRM_ prefix and keep arch templates; C++ keeps the LLM_KV_HRM_* enums. GGUF output is unchanged - existing files and HF uploads stay valid. * Update gguf-py/gguf/constants.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update src/llama-arch.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update src/llama-arch.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * convert : rename hrm writer methods to add_hrm_* Generic names like add_h_cycles/add_prefix_lm are too broad on the shared GGUFWriter; prefix them with hrm_ like the metadata keys. * model : fix meta-split lookup for archs with aliased cache slots Cache tensors of archs that alias physical blocks across looped slots (hrm_text, nanbeige with num_loops > 1) can reference block indices without weight tensor names. Take the output projection from the layer array instead of asserting; all other lookups are unchanged. * model : replicate hrm_text tensors on meta devices instead of splitting The aliased cache slots rotate split states differently from their physical weights, so the meta-split execution invariants (set_rows requires the cache state to match the token indices) cannot hold for any device count. Replicate all hrm_text tensors on every meta device instead; single-device and non-meta paths are unchanged. Assisted-by: Claude Sonnet --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> |
||
 Alex
|
3d10bcd197 |
llama: add Maple 20B-A1B ternary MoE architecture (CPU) (#27000)
* gguf-py: add Maple tensor constants
Add MODEL_ARCH.MAPLE, its "maple" name, and the tensor list for the
Maple 20B-A1B ternary MoE architecture: token embeddings, output,
attention with Q/K RMS norms, and per-expert FFN tensors.
* convert: add Maple HF->GGUF converter
Register MapleForCausalLM in the HF architecture map and add the
converter for the Maple 20B-A1B ternary MoE model: 24 layers, 256
experts with 8 active, sliding-window attention (SWA-512) interleaved
with global attention at a 3:1 ratio, partial rotary factor 0.5, and
per-expert weight stacking into merged 3D tensors.
* llama: add Maple architecture (20B-A1B ternary MoE)
Add the Maple 20B-A1B ternary MoE architecture: 24 layers, 256
experts with 8 active, sliding-window attention (SWA-512) interleaved
with global attention at a 3:1 ratio, and ternary TQ1_0/TQ2_0
quantization support.
- register LLM_ARCH_MAPLE between MAMBA2 and JAMBA
- implement llama_model_maple: Q/K RMS norms after projection (GEMMA4
style), rope applied only on SWA layers (nope_on_global_attention),
ISWA KV cache, and MoE FFN with swiglu gate clamp at +7 (DEEPSEEK4
style)
- mark MAPLE as unsupported by the model saver (roundtrip skipped)
* tests: mark Maple as MoE-mandatory
Maple is always-MoE: the model throws when n_expert == 0, so the
test harness must only run the MoE config for LLM_ARCH_MAPLE.
* maple: apply review feedback (n_ff_exp_arr, get_arr, rope params)
- load_arch_hparams: use n_ff_exp_arr + n_ff_exp() accessor (upstream
changed these from a scalar member during the rebase)
- sliding_window_pattern: get_arr, the pattern is mandatory for this arch
- partial_rotary_factor: read only from rope_parameters (base.py mirrors
the top-level key automatically)
- document why TOKEN_EMBD/OUTPUT are forced to F16 (they are the two
dense tensors in Maple, and the reference GGUFs ship them as F16)
- add @ModelBase.example("deepgrove/maple-preview")
* tests: add Maple to the SWA pattern array list
get_arr for maple.attention.sliding_window_pattern requires an array, but
the harness only emitted a per-layer array for the arches in its list, so
test-llama-archs -a maple failed to load the model.
Assisted-by: DeepSeek Harness
* maple: move swiglu_clamp_exp to the converter
The loader prefilled 7.0 and read the key optionally. The converter now
writes it and the loader reads it as required, because llama-graph.cpp
skips the clamp when the limit is 0 and an optional read would silently
run unclamped. The test harness provides the key for the same reason.
Also drops tensor_force_quant: base.py already forces FFN_GATE_INP to F32
and TOKEN_EMBD/OUTPUT to F16 for ternary file types.
Assisted-by: DeepSeek Harness
* convert: fix the LazyBase func signature in the Maple converter
ty flagged the stack() closure: it takes no argument, while LazyBase is
annotated with func: Callable[[Any], Any]. Pass the tensor list through
args instead of closing over it, the same way kimi_k3 does, so the
callable shape matches.
Assisted-by: DeepSeek Harness
|
||
 fairydreamingandStanisław Szymczyk
|
5f436dddb4 |
tests : exclude HY_V4 from WebGPU test-llama-archs tests (#28855)
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> |
||
|
Georgi Gerganov
|
a2878d30df |
metal : single-source fusion table + fusion debug rework (#28164)
* metal : rework fusion patterns into a single table All fusable op patterns for the Metal backend are now declared once in a fusion table (ggml-metal-fuse.cpp) and consumed by both the graph optimizer (ggml_metal_fuse_max, packing) and the op encoders (ggml_metal_fuse_next, compute). The two phases share the same pattern table plus ggml_can_fuse_subgraph_ext for the structural checks, and differ only in the mode used for the pattern check (STRUCTURAL at optimize time, since tensors are not allocated yet, and FULL at compute time, including Metal buffer placement). This also protects the snake activation (MUL + SIN + SQR + MUL + ADD) from being reordered during graph optimization, which was previously unprotected. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * metal : fix absolute output indices in fusion patterns ggml_can_fuse_subgraph_ext expects the outputs array to contain absolute graph node indices (it indexes cgraph->nodes[outputs[i]]), but the fusion table query was passing a relative index (n_ops - 1). As a result the last node of every pattern was not recognized as an output and was subjected to the elidable use-count check, which failed for essentially all fusions. This silently disabled the norm/MUL fusion and caused a ~5% token-generation regression. Pass the absolute graph index of the last node instead. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * metal : fuse gated_delta_net with cache cpy Add GGML_METAL_FUSE_GDN_CACHE to the fusion table: when the gated_delta_net kernel is followed by a cpy that scatters its recurrent state snapshots into the KV cache, the kernel writes the snapshots straight into the cache buffer and the trailing cpy is elided. The gdn output has other consumers (the attn scores view), so unlike the elision-chain patterns this is not a simple chain: a 'raw' flag on the fusion pattern skips the generic chain/shape and ggml_can_fuse_subgraph_ext checks, making the pattern-specific check callback the sole validator. Packing (ggml_metal_fuse_max) now matches on the same view-transparent node sequence that the compute phase uses, so the gdn + cache cpy group is packed along with any intermediate views and stays adjacent through the reorder. The fused cpy is a view consumer of the gdn (it writes the cache directly), so its mem-range is skipped in the encoder; the skip is restricted to CPY nodes consuming the previous fused node through a view so other fusions are unaffected. Add test_gated_delta_net_cache_fusion and register 5 cases. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * metal : drop is_view_consumer mem-range skip The is_view_consumer skip was carried over from the upstream gated_delta_net cache-fusion draft, but it is not needed: keeping the elided cpy's mem-range in the concurrency tracker only ever adds a (conservative) memory barrier at the fusion point. It can never remove a barrier, so it cannot introduce a race. The worst case is one spurious barrier per gdn+cache-cpy fusion, which is within run-to-run noise on Qwen3.5-0.8B Q8_0. Dropping the check keeps the mem-range loop uniform for all fused groups. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * metal : rename gated_delta_net fused state output args Rename the fused cache-write kernel argument to match the rest of the kargs: state_out_stride -> nb_out (and widen it to uint64_t), and the local buffer id bid_state_out -> bid_out. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * metal : rename raw fusion flag to unsafe raw did not convey that the flag opts a fusion pattern out of the generic elision-chain safety net (ggml_can_fuse_subgraph_ext + chain/shape checks). rename it to 'unsafe' to make explicit that the pattern's check callback is the sole validator and must re-establish the safety guarantees itself. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * metal : tidy fusion pattern checks and table - const-correct ggml_metal_fuse_outputs buffer - annotate unused check-callback parameters - drop a redundant size_t cast - align the ops/table initializers and add blank-line separation Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * metal : add generic fusion stats via ad-hoc proc-address API Add a device-owned fusion context that lets a test tool count how many times each fusion pattern fires and toggle fusion. It is exposed through the ad-hoc ggml_backend_reg_get_proc_address mechanism with generic names so the testing tool is backend-agnostic: - ggml_backend_fusion_stats_init: start collecting fusion stats; when a context is created afterwards it registers the labels/counters and encodes single-threaded (n_cb == 0) so the counters are race-free - ggml_backend_fusion_stats_reset / _get_stats / _set_enabled The context lives on the metal device (not on the last backend context), so counters accumulate across contexts and reads are always consistent. The enable/disable toggle is initialized from GGML_METAL_FUSION_DISABLE and can be overridden by the test through set_enabled. Labels are synthesized from the fuse table via ggml_metal_fuse_label (e.g. "GATED_DELTA_NET+CPY"). Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : add fusion count regression test with per-backend baseline test-fusion runs every dummy model generated by test-llama-archs on a single backend (single-threaded encoding, n_cb == 0) with fusion enabled and disabled, and for each mode (prefill / decode) reports the per-fusion counters and the NMSE between the fused and unfused logits, plus the NMSE against a CPU reference. A fusion pattern that silently stops matching (or fires when it should not) is caught as a regression by comparing the counters against a committed per-backend TSV baseline: - --record writes the golden baseline, --check (default) validates it - the unfused run doubles as a control: its counters must be all-zero - NMSE is skipped when it is NaN or the arch is already broken on the device (e.g. plamo2 on Metal), so the count check is the hard gate - baseline counts depend only on graph structure, not weights (verified stable across weight seeds) - the fusion stats API is resolved through the ad-hoc get_proc_address mechanism with generic names; a backend that does not export it makes the test fail with an error The committed MTL0.tsv baseline covers 110 dummy archs (298 rows). Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : rename fusion api helpers to match stats_init signature Align the test with the ad-hoc fusion stats API: fusion_stats_init no longer takes an enable bool (stats are turned on by calling it), so the proc-address wrappers and typedefs are renamed to the api_* convention. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : rename backend to device in fusion test CLI The fusion test operates on a compute device (e.g. MTL0), not a backend, so rename the --backend argument to --device and the backend_name variable to device_name. Keep "backend" where it refers to the ggml backend interface (the ad-hoc proc-address mechanism). Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : add --model and --help to fusion test --model FILE runs the fusion regression test over a single model file instead of enumerating a --models DIR. --models and --model are mutually exclusive. Also add a --help/-h option that prints the usage. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : use backend base name for fusion baseline output The fusion test is invoked with a specific device name (e.g. MTL0), but its output - the recorded baseline and the header it writes - should be named after the backend base name (e.g. MTL, via ggml_backend_reg_name), since the counters depend on the backend, not on the specific device index. Rename the committed baseline to MTL.tsv. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : run fusion test from ci instead of ctest The fusion test needs Metal and generates a lot of dummy models, so it does not belong in the generic ctest suite. Move it to ci/run.sh as gg_run_test_fusion, gated on GG_BUILD_METAL like gg_run_test_llama_archs_tensor_split: it generates the dummy models with test-llama-archs -o and then validates the fusion counts against the committed baseline. test-fusion.cpp is still built (llama_build) but no longer registered as a ctest. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : align fusion baseline TSV columns Pad the TSV fields to fixed widths so the columns line up regardless of the variable arch and fusion-label lengths, and trim each field on parse so the padded file is still accepted. Regenerate the committed MTL.tsv baseline in the padded format (data unchanged, verified identical modulo padding). Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : widen label column and align fusion TSV header Give the label column more room (28 chars) and fix the column header widths so they match the data rows (moe/mode/label), keeping the header aligned with the values. Regenerate the MTL.tsv baseline in the new format (data unchanged). Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : switch fusion baseline from TSV to CSV Use comma-separated values like the rest of the project, keeping the padded, aligned columns. Split on ',' and trim on parse. Rename the committed baseline to MTL.csv (data unchanged, verified identical modulo padding/separator). Update the ci/run.sh check path accordingly. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * cont : rebase + update MTL stats * tests : avoid graph reallocations for some archs * metal : tidy fusion debugging context and op init - simplify the shared fusion debugging context comments - shorten the ggml_metal_fusion struct comment - align the ggml_metal_fuse struct fields and comments - move the fusion parameter of ggml_metal_op_init right after dev Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : dedup fusion baseline into any mode prefill and decode always produce the same per-graph fusion count, so store a single row per label with mode = "any" and the per-graph count instead of two rows. this halves the baseline size and keeps the check stable. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * ci : move fusion model generation to a separate step the dummy models generated by test-llama-archs are reused by other tests, so generate them once in their own step instead of inside test_fusion. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : bump nmse thold * models : fix plamo2 graph * tests : remove "skip" logic from test-fusion * tests : set qwen3tts dummy vocab to codec head size the dummy qwen3tts model used a vocab of 4096 while the codec head is 3072, so the graph padded the output with -inf which made the NMSE in test-fusion produce NaN. use the exact codec head size instead so the padding is not generated at all. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * tests : regen fusion baseline reflect the plamo2 graph fix, which changed its fusion pattern split (RMS_NORM+MUL 11->10, RMS_NORM+MUL+ADD 3->4; same total). Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * ci : skip dummy model generation on OpenVINO test-llama-archs does not build on the OpenVINO platform, so do not try to generate the dummy models there. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * cont : minor * tests : enable test-llama-archs on windows * cont : disable on windows + workaround * metal : naming nits * test-fusion : add instructions to update baseline * context : fix Kimi-K3 graph reserve * fusion : update MTL * cont : fix naming * metal : rework fusion info storage Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : align fusion info API Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * metal : use opaque fusion handle in ad-hoc API Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * ci : move fusion test to dedicated workflow Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp * cont : run only on ggml changes * cont : simplify * fusion : remove multi-output stuff for now * ci : fix typo |
||
 
|
3ad1ba7336 |
[Model] Support for Spark2_5ForCausalLM implementation (#27868)
* Add Spark3 Model * rename spark3 -> spark2_5 Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> Co-authored-by: dongjiang <dongjiang2010@gmail.com> |
||
|
49c0dc82b8 |
model : add Tencent Hy 4 (hy_v4) preview architecture support (#28127)
* model: add Tencent Hy 4 (hy_v4) preview architecture support Adds support for the Tencent Hy 4 model (Hugging Face architecture HYV4ForCausalLM, GGUF arch hy_v4): Add HF -> GGUF conversion script (conversion/hy_v4.py) and wire it into the conversion registry Register hy_v4 GGUF constants, arch enum, and writer support Implement the hy-v4 model graph, hparams, vocab and context changes Register the new arch in llama-arch and models registry Extend arch tests to cover hy_v4 Assisted by Claude Opus 5 * Update convert_hf_to_gguf_update.py Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com> * Update conversion/base.py Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com> * convert : move hy_v4 entry to the same place as in convert_hf_to_gguf_update.py * model : apply changes related to n_ff_exp becoming per-layer in Hy4-preview * n_layer_all --------- Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com> Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> |
||
|
Daniel Han
|
36b1015438 |
qwen4exp: fix seq_cp, block position keying, mtmd input, cuda abort, add tests (#27941)
* qwen4exp: follow up fixes * -kvu NaN collapse fix Assisted-by: Claude * indexer cache ext.x/ext.y restore fix Assisted-by: Claude * kv-cells: rename seq_set to seq_get_all seq_get is already taken by the single-id getter, so the suggested name cannot be overloaded on return type alone. Assisted-by: Claude * memory-hybrid-idx: implement set_input_qsa on the memory class The context held the whole implementation, where the pattern elsewhere is a thin context forwarding to the memory class, as llama_kv_cache_context does for set_input_kq_mask. The body reads no context state, so it moves unchanged and the context keeps a forwarder. Also shortens the seq_get_all comment as suggested. * tests: check that a sequence state survives a save/restore round-trip Saves seq 0, erases it, restores the blob and saves again, requiring the two blobs to match. Compares blobs rather than generated text, which cannot see a field dropped on the way back in. Note this passes on master for qwen4exp, so it does not demonstrate the ext.x/ext.y drop this PR fixes; reaching that needs 2D mrope content. * tests: give the synthetic qwen4exp a PLE so the state test bites has_cell_ext() is n_pos_per_embd() > 1 || ple_n_heads > 0, and the indexer cache sets rope_type = NONE, so without a PLE it serializes no cell ext at all and the round-trip test cannot see a dropped ext.x/ext.y. With one, removing the ext_set restore in state_read_meta fails the test: 198 of 335692 bytes differ, first at offset 282092. Loading such a model needed two fixes: - the row count of per_layer_token_embd came from require_weight(), which a model synthesised from metadata alone has no file to answer. Derive it from the head ranges and prefer the file's padded count where there is one. - the PLE conv history is a row of the recurrent cache, so a PLE on a full attention layer dereferenced a null p_l. Reject it at load time instead. The meta mirror is skipped for qwen4exp. It returned NaN logits before this fixture carried a PLE, which the nmse check passes since a NaN comparison is false, and aborts with one. -sm tensor on real devices works. Assisted-by: Claude * llama: disable -sm tensor for qwen4exp test-llama-archs skipped the tensor split for this arch from inside the test, so the arch still advertised support it does not have. Declare it in llm_arch_supports_sm_tensor instead and drop the test-side exception; the existing llm_arch_supports_sm_tensor branch then does the skipping. Assisted-by: Claude |
||
|
Georgi Gerganov
|
d086dbb348 |
tests : fix log verbosity for test-llama-archs (#28147)
* tests : fix log verbosity for test-llama-archs * cont : naming * cont : add note |
||
|
Georgi Gerganov
|
4e97ac86eb |
tests : run test-save-load-state across all architectures (#27755)
* tests : run test-save-load-state across all architectures test-save-load-state previously only ran in ctest against a single downloaded model (tinyllamas/stories15M), i.e. only the llama arch. Add a --models DIR mode to test-save-load-state that runs the full save/load suite over every *.gguf in a directory, reporting a per-model PASS/FAIL and exiting non-zero if any model fails, and wire a ctest to run it over all architectures using the existing generate-models fixture (test-llama-archs). The single-model -m mode is preserved (still used by ci/run.sh). Also bump the dummy-model training context in test-llama-archs from 128 to 256 so that the per-sequence context (which is padded up to a multiple of 256) no longer exceeds n_ctx_train and emits the "possible training context overflow" warning. The test is expected to fail until the affected arches are fixed: deepseek4 (host seq-copy), gemma2/gpt-oss/lfm2 (device seq-copy), minimax-01 (state load). It aborts at the first arch that crashes. Assisted-by: pi:llama.cpp/Qwen3.8-27B * tests : match dummy DSA indexer to fused Lightning Indexer kernel The dummy DSA indexer (deepseek32, glm-dsa, ...) used key_length=64 and head_count=1, so the fused Lightning Indexer op's q tensor was shaped [64, 1, ...]. The Metal fused kernel is fixed to DK=128, NH=64, so it rejected the op and the scheduler fell back to CPU, emitting a 'layer assigned to MTL but Lightning Indexer on CPU' warning. Bump key_length to 128 and the DSA head_count to 64 so the fused op runs on the GPU. Assisted-by: pi:llama.cpp/Qwen3.8-27B * tests : add --help and document -o in test-llama-archs Add a --help/-h flag to test-llama-archs and list the existing -o/--out option in the usage text, which was previously missing. Assisted-by: pi:llama.cpp/Qwen3.8-27B * tests : use 64 indexer heads for deepseek4 deepseek4's indexer head count was set to n_head (8), which does not match the fused Lightning Indexer kernel's fixed NH=64, so the fused op fell back to the CPU backend and emitted a device-mismatch warning. Give it the same fixed 64 as the other indexer archs by dropping it from the n_head ternary (only minimax-m3 keeps n_head, since it does not use the fused Lightning Indexer op). Assisted-by: pi:llama.cpp/Qwen3.8-27B * tests : fix dsv4 save-load n_stream mismatch The dsv4 KV cache keeps per-sequence KV/state streams even in unified mode, so its n_stream equals n_seq_max. The test saved the state in the baseline with n_seq_max=1 but loaded it in the seq-copy tests with n_seq_max=2, so state_read threw an n_stream mismatch. Use n_seq_max=2 in the baseline and state-load tests so the save and load agree. Assisted-by: pi:llama.cpp/Qwen3.8-27B * context : relax on-device seq-copy chunk alignment The on-device state seq copy (llama_state_seq_set_data with LLAMA_STATE_SEQ_FLAGS_ON_DEVICE) copied the write-side cpy tensors to the read-side targets 1:1 by index, requiring the writer and reader to emit the same number of chunks in the same order with the same per-chunk sizes. state_write_data chunks per cell-range while state_read_data chunks contiguous-or-per-cell, so the counts diverged for non-contiguous sources (dsv4, SWA) and the copy aborted with "memory buffer mismatch". All state writers and readers enumerate the same logical data in the same order, differing only in chunking. Copy the flat write-side data into the read-side targets with a byte cursor that walks both tensor lists across their boundaries, so the chunking no longer needs to match. Keep the total-size guard; drop the n_tensors equality check. Assisted-by: pi:llama.cpp/Qwen3.8-27B * model : fix dangling hparams ref in minimax-01 LA graph input llm_graph_input_la stored const llama_hparams & hparams, bound to the llm_graph_params temporary in llama_context::process_ubatch. The input object outlives that temporary (it is kept in llm_graph_result::inputs for graph reuse), so set_input() read destroyed stack memory on every graph reuse - test-save-load-state crashed for minimax-01 when the stack region was overwritten (n_layer_all read as 0, abort in llama_hparams::n_head). Store a copy like every other graph input class. Assisted-by: pi:llama.cpp/Qwen3.8-27B * context : handle "worst case" graph and add TODO |
||
 
|
6c84c7d5d8 |
model: add Qwen3.8-Flash-Next (qwen4exp) (#27742)
* gguf: add qwen4exp (Qwen3.8-Flash-Next) arch and converter
Adds the GGUF-side plumbing for HF model_type qwen4_exp:
- MODEL_ARCH.QWEN4EXP plus tensors for the low-rank hyper-connection
variant (hc_*_norm/down/up/inject) and the PLE n-gram hash embeddings.
The DeepSeek-V4 hc_*_fn/base/scale tensors are a different
parameterisation, so these are separate entries rather than reuse.
- Reuses the existing indexer, per_layer_token_embd, SSM and
compress_ratios keys unchanged.
- conversion/qwen4exp.py inherits the Qwen3.5 linear-attention V-head
reorder and interleaved mrope, concatenates the 128 PLE embedding
shards, and splits index_qk_proj into separate indexer q/k tensors.
The PLE hash multipliers reach ~2.4e13. prepare_tensors() casts every
non-float dtype to float32 before modify_tensors() runs, and GGUF array
writes infer INT32 from Python ints, so both paths are bypassed: the
constants are read from the pre-cast lazy tensors and written as
explicit UINT64 arrays.
Additive only; no existing arch changes behaviour.
* llama: load qwen4exp (Qwen3.8-Flash-Next) hparams and tensors
Adds LLM_ARCH_QWEN4EXP with its hparams and tensor loading. The graph
comes in the next commit; this makes the model load and report correct
metadata.
- hyper-connections set n_embd_out_impl = hc_count * n_embd, so the
residual stream is 4x wide and there is no output_norm: the final
mixer's hc_norm is the last norm in the model.
- registered as hybrid and given the same recurrent/attention memory
filters as Qwen3-Next and Qwen3.5.
- reuses the existing indexer, per_layer_token_embd, SSM and
compress_ratios keys as-is.
- the PLE table row count is read back from the file rather than
recomputing the vocab padding rule.
llama-model-loader gains UINT64 array support. That branch previously
threw, so no existing caller changes behaviour; it is needed because the
PLE hash multipliers do not fit in int32.
* qwen4exp: shorten comments
* llama: qwen4exp text graph with hyper-connections, GDN and MoE
Implements the decode graph for Qwen3.8-Flash-Next: the hyper-connection
residual stream, gated delta net layers, the MoE block with its gated shared
expert, and dense full attention. The QSA indexer and the PLE n-gram embedding
are not wired up yet and land in later commits.
Hyper-connections are implemented here rather than shared with deepseek4.cpp.
The two formulations agree on the [n_embd, hc, n_tokens] layout and little
else: DeepSeek-V4 mixes with a full-rank projection and Sinkhorn-normalises
it, whereas this model uses a low-rank down/silu/up sigmoid gate and collapses
by a plain mean. Only the ~10 line stream mean is genuinely common, so sharing
would mean touching DSV4's hot path and its three fused CUDA ops to reuse very
little. What is reused is the substantive part: the LLM_KV_HYPER_CONNECTION_*
keys, the n_embd_out_impl wide-residual support already in the loader, and the
layout convention.
Also allows a checkpoint to carry no PLE layers at all, which makes it
possible to bring the graph up and validate it in stages.
Validated against vLLM, the only working reference implementation. On a
scaled-down model with an init scale large enough to give non-uniform logits,
agreement with vLLM sits at the numerical noise floor: llama.cpp f32 against
its own bf16 gives 84.3% top-1 agreement over 255 positions, and this graph
against vLLM gives 85.1%. The comparison was calibrated by seeding three
deliberate bugs (silu instead of sigmoid on the delta net gate, dropping the
1/hc scale in the mix, dropping the 2x in the combine); each drops top-1 to
between 0% and 11%, an order of magnitude below the floor.
* llama: qwen4exp PLE n-gram hash embedding
Adds the per-layer embedding: a custom I32 graph input hashes each token with
its ngram_size-1 predecessors host-side and the result is a plain row gather
over the shared table, the same shape gemma3n's per-layer embedding uses. The
hash has to run on the host because the splitmix64-derived multipliers reach
2^45, so the products need 64-bit integers and an xor, neither of which ggml
has.
Predecessors that fall outside the ubatch come from a small per-sequence
history on the model, mirroring the per-request ngram_context the reference
carries. It is only trusted when contiguous with the incoming position, so a
fresh prompt or a rewound cache falls back to EOS padding rather than hashing
against stale tokens.
The depthwise conv is written out as a sum of shifted, per-channel-scaled
copies rather than through ggml_conv_1d_dw, which carries a correctness
warning upstream.
Verified two ways. The row indices match a transcription of the reference's
tensor formulation exactly, 1024 of 1024 rows, including sequences with EOS
tokens sprinkled through them to exercise the segment reset. Separately, with
PLE placed on layer 0 so its input is just the token embedding, ple_embd and
ple_gated_value match a PyTorch computation from the same checkpoint to every
printed digit.
End to end over 1023 scored positions the port sits the same distance from
vLLM with PLE as without it, 6.3 points of top-1 against 6.0, so PLE costs no
accuracy relative to the rest of the model. That common offset is vLLM's bf16
activations, which cannot be removed: its QSA kernel refuses float32.
Two bugs found along the way, both caught by the row-index check. The history
was read and updated in the same pass, so a token early in a ubatch could pick
up an earlier token of that same ubatch as prior context; it is now snapshotted
first. And an EOS token was cutting its own context, where the reference takes
the last EOS strictly before the position, so a boundary only hides tokens from
the positions after it.
Known gap: the conv carries no state across ubatches, so it is exact only for a
prefill that starts at position 0. Chunked prefill and decode need the conv
state wired into the recurrent memory, and the conv branch itself is still
numerically unverified because the fixture zeroes its weights.
* llama: carry the qwen4exp PLE conv state across ubatches
The PLE depthwise conv was zero-padding on the left, which is only right for a
prefill that starts at position 0. Decode and chunked prefill saw a truncated
history for the first (kernel-1)*ngram_size positions of every ubatch.
The PLE module sits on a layer that is also a delta-net layer, so both need a
conv history in the same recurrent row. Rather than plumb a per-layer state
size through build_rs and build_conv_state, the row is widened once and each
convolution addresses its own slice through a local helper. n_embd_r() gains
the extra span, which is zero for every other architecture because it is
derived from ple_n_heads.
Verified by feeding the same 1024 token sequence in chunks instead of one
shot: at 64 tokens per decode the logits are bit-identical to the single-shot
run, 1023 of 1023 top-1 and a maximum logprob deviation of exactly zero. At
one token per decode they differ slightly, but the no-PLE model differs more
under the same test (94.6% against 97.1%), so that is the usual gemv-versus-
gemm accumulation difference and not the state.
The conv branch is also no longer unverified. With non-zero conv weights the
port sits 6.3 points of top-1 below the numerical floor, the same distance as
with the weights zeroed and as the model with no PLE at all, so the branch
adds no error of its own.
test-llama-archs passes every existing architecture at 0.00e+00, including the
delta-net models that share this code path.
* llama: fix the qwen4exp PLE conv state and unblock test-llama-archs
build_rs writes into the state tensor in place, zeroing one row and copying the
carried-over states, so calling it twice for the same layer let the second call
clobber the first write-back. The PLE layer is also a delta-net layer, so that
is exactly what happened: both convolutions gathered the same row. They now
share a single gather per layer.
The earlier claim that the conv state was carried correctly was tested on a
fixture whose conv weights are zero, where the branch contributes nothing and
chunking matches trivially. Re-running with non-zero conv weights showed the
divergence, growing with the number of ubatch boundaries: 97.1% top-1 at one
boundary down to 90.2% at seven. With the shared gather it is bit-identical to
the single-shot run at every chunk size tried, 512, 128 and 64, with a maximum
logprob deviation of exactly zero over 1023 positions. The delta-net-only model
stays bit-identical too, so nothing regressed there.
Also derive the delta-net conv channel count the way load_arch_tensors sizes
wqkv instead of from ssm_d_inner. The two agree for this model, but n_embd_r()
only bounds the row and the convolution has to match the tensor feeding it.
test-llama-archs previously aborted on this architecture and took every later
architecture with it. qwen4exp is marked MoE-only, given the hyper-connection
keys and an ssm_d_inner consistent with its tensor derivation, and skipped for
now: the hyper-connection keys written by get_gguf_ctx are not reaching the
synthesised file, which needs a separate look. The suite completes again, 124
architectures at 0.00e+00.
* llama: optional indexer key cache in llama_memory_hybrid
Groundwork for qwen4exp's QSA sparse attention. Its indexer needs a per-token
key history for the full-attention layers, but a hybrid model cannot use
llama_kv_cache_dsa: that class derives from llama_memory_i rather than
llama_kv_cache, and llama_memory_hybrid constructs its attention cache
directly. No existing architecture pairs recurrent state with a sparse
indexer, so there was nothing to reuse wholesale.
llama_memory_hybrid therefore gains a third, optional cache, shaped the same
way llama_kv_cache_dsa shapes its lightning-indexer cache: a copy of hparams
with n_head_kv forced to 1 and n_embd_head_k_full set to indexer_head_size.
It is built only when a filter_idx callback is passed, which defaults to
nullptr, so every existing architecture gets exactly what it got before. The
per-sequence operations and the batch preparation forward to it under a null
check, matching how the DSA cache prepares its two caches over the same
ubatches.
test-llama-archs passes all 124 architectures at 0.00e+00, including the 12 in
the hybrid family that share this code. The qwen4exp fixtures are unchanged:
same logits against vLLM, and chunked evaluation still bit-identical to
single-shot.
* llama: QSA sparse attention for qwen4exp
The full-attention layers of this model do not attend to everything. An
indexer scores one mean-pooled key per block of compress_ratio tokens and
keeps a budget of the best blocks, plus the tail of tokens that do not yet
form a complete block. Below indexer_top_k + compress_ratio - 1 cached
tokens every block fits in the budget, so the result is exactly dense.
What is reused rather than rebuilt:
- the mask machinery. build_attn's DSA overload already turns a list of
token indices into a KQ mask via ggml_set_rows, so that block is lifted
out verbatim into build_attn_mask_top_k and shared with a new overload
on llm_graph_input_attn_kv. DSA's node sequence is unchanged; the new
overload exists because llama_kv_cache_dsa assumes MLA and cannot be
dropped into a hybrid model.
- the indexer key cache, which is the optional third cache added to
llama_memory_hybrid in the previous commit. It holds raw keys, because
pooling happens before the norm and the rotation.
The graph expands block scores rather than block indices: giving every
token of a block its block's score needs only a gather, where expanding
indices would need an integer multiply-add that ggml has no op for. Since
the budget is a whole number of blocks and a block's members tie exactly,
the cut still lands on a block boundary.
Everything that depends on cache layout is computed host-side in
set_input_qsa. Blocks are cuts of the position line rather than of the cell
array, so nothing assumes the cache is contiguous.
Measured on the tiny fixture against vLLM, comparing the selected token
indices directly rather than the logits:
below the budget selection identical, and 1024-token logits are
bit-identical to the pre-QSA dense path
above the budget mean jaccard 0.975
The direct index comparison is what made this correct. The reference
rectifies each head's dot product before summing over heads, which an
earlier reading of it had missed; on logits alone the resulting port looked
fine, because on a randomly initialised fixture the known-correct dense
path already disagrees with vLLM by more than the bug did. Comparing the
indices showed 0.794, and fixing the ReLU moved it to 0.975.
* llama: give the qwen4exp indexer cache the attention cache's slots
The indexer cache found its own slots, independently of the attention
cache. Both are the same size and see the same ubatches, so in a
straight-through prefill they agree, which is why every fixture and every
single-shot parity run passed. They drift once the context is being
rewritten between turns, and then the QSA top-k indices, which are applied
against the attention mask, point at the wrong cells.
The seven-turn chat test caught it on the third turn: llama-server aborted
on the assertion that the two caches report the same n_kv.
The cache is a side buffer addressed by the attention cache's cells, so it
now takes that cache's slot layout instead of computing one. Applying that
layout also marks its cells identically, so the two agree cell for cell by
construction rather than by coincidence, and the assertion can no longer
fire.
Inert where the caches already agreed: test-llama-archs green at 126 archs
and 0.00e+00, and the 4096-token tiny fixture is unchanged at max logit
delta 0.0.
* tests: record what the qwen4exp arch-test skip actually observes
The old note guessed that the hyper-connection keys never reach the file.
They do: dumping the gguf_context handed to llama_model_init_from_user
shows both among its 67 KVs, and the loader still reports one missing.
* tests: cover qwen4exp in test-llama-archs
The arch was skipped with a note guessing that the hyper-connection keys
never reached the synthesised file. They did. The suite builds a model, then
saves and reloads it, and llama_model_saver did not re-emit those keys, so
the failure was in the roundtrip leg rather than the first load. Three gaps,
all in shared code and all additive:
- add_kv_from_model wrote no hyper-connection, compress-ratio or PLE keys.
The PLE group only means anything whole, so it is written or omitted
together; the rest follow the file's existing style of writing every key
unconditionally, since an architecture that does not read one is
unaffected by a zero.
- the saver had no uint64 path at all, which the PLE hash constants need.
- add_tensors_from_model enumerates model-level tensors by hand and was
missing per_layer_tok_embd and the three final-mixer tensors.
Two smaller fixes on the qwen4exp side, both found by running the test:
- build_qsa_top_k divided by the compression ratio before asserting it was
non-zero, so a file without the key crashed instead of reporting.
- a layer with no compression ratio now falls back to dense attention,
which is what the model computes below the budget anyway. The test then
has to write a ratio to reach QSA at all, and an indexer key length no
narrower than n_rot, since the indexer ropes with the main attention's
rotary width.
Full suite: 126 archs, qwen4exp at 0.00e+00 with roundtrip OK. The tiny
fixture is unchanged, max logit delta 0.0 against the pre-QSA dense run.
* convert: stream the qwen4exp PLE table instead of concatenating it
The n-gram table arrives as 128 shards that were held in a dict and then
torch.cat-ed, so the peak was the shards plus the concatenation: around
300 GB of RSS on the real checkpoint, which rules out machines that could
otherwise convert this model.
Each shard is now written straight into a memory-mapped file at its final
row offset and dropped, so the resident set is one shard and the rest is
the page cache's problem. The temporary file sits beside the output and is
removed once the write finishes, including on failure.
Shards other than the last must be uniform for direct placement, which is
asserted rather than assumed, and a shard arriving before the stride is
known is held instead of misplaced.
Verified on the tiny fixture: the resulting GGUF is byte-identical to the
one the concatenating path produced (md5 2d274efac91ad1e9a6007efb0687e597).
* quantize: fall back to F16 for 32-block types with an odd ncols
tensor_type_fallback demotes a tensor whose ncols is not a multiple of the
target's block size, but its switch only enumerates the 256-block types. A
target that is already a 32-block type (iq4_nl, q4_0, q5_0, q8_0, ...) falls
into default: and throws, even though the function already knows how to answer
that case: the ncols check right below the switch resolves an unrepresentable
shape to F16.
Route those types into that check instead of throwing. Only paths that abort
today change, so no quantization that currently succeeds is affected.
Found on a 4-wide depthwise conv kernel. llama-quantize reported nothing but
"failed to quantize model from ...", with no tensor name and no exception text,
which made a quant recipe that had simply not pinned the tensor look like a
corrupt model. It now names the tensor and continues.
* quantize: let --tensor-type name per_layer_token_embd
per_layer_token_embd shares the TOKEN_EMBD category with token_embd.weight, so
--token-embedding-type is returned for it before any --tensor-type pattern is
consulted, and there is no way to give it a tier of its own.
That grouping is fine as a default and stays the default. It is a poor fit for
the size, though: on qwen4exp the table is 97.7 GiB of a 337.6 GiB BF16 file and
about 46% of a 4-bit one, roughly eighty times token_embd.weight, and it is
read by ggml_get_rows rather than a matmul so no imatrix ever covers it.
Allow an explicit --tensor-type pattern to name it, and only it. Nothing
changes unless such a pattern is passed, and token_embd.weight keeps the old
precedence in either case.
Measured on Qwen3.8-Flash-Next, Q4_K_M with an imatrix: the table lands at q8_0
(51.9 GiB, 113.5 GiB total) by following --token-embedding-type, and pinning it
q4_1 gives 30.5 GiB for 92.1 GiB total, 19% off the file.
* quantize: size the output buffer exactly instead of nelements * 4
The per-tensor output buffer was sized `nelements * 4`, described as an upper
bound. It is a very loose one: the output is at most 2 bytes per element
(f16/bf16) and usually well under 1.1 (q8_0 and below), so between 2x and 4x of
it is never touched. The exact size is already known here, since it is what the
quantization loop writes, what new_size sums to, and what the GGUF metadata is
asserted against a few lines later.
On a model whose largest tensor is a few GB none of this matters. On
Qwen3.8-Flash-Next it does: per_layer_token_embd is 51.2 G elements, so the
buffer was 205 GB where 54 GB is needed at q8_0 and 32 GB at q4_1.
Measured on that model, VmHWM of a live llama-quantize was 485 GB per process.
Three of them fit in 2 TB and five did not, which is what an OOM-killed quant
ladder looks like. This removes about 150 GB of that.
Byte-identical output, verified against the same binary built at the parent
commit: q4_K, q8_0, q5_K, q6_K and IQ4_XS, over BF16 and F32 sources, with and
without a PLE table present. Six cases, six matching md5s.
* qwen4exp: hash the image placeholder for multimodal batches
The PLE row indices are computed host-side from ubatch->token, and set_input
returned early when that was null. A multimodal ubatch is exactly that case:
the mtmd layer consumes the image placeholder ids and hands llama_decode
embeddings instead. The early return left the I32 index tensor uninitialised,
so ggml_get_rows indexed a 320 M row table with whatever the buffer happened to
contain, and aborted:
GGML_ASSERT(i01 >= 0 && i01 < ne01) failed
ggml_compute_forward_get_rows
mtmd_helper_decode_image_chunk -> llama_decode
Every image request crashed. Nothing caught it because the vision work had only
ever been verified by converting an mmproj, never by running one.
The reference computes the hash over input_ids, where those positions still
hold the image placeholder, so carry that id through as qwen4exp.ple.image_token_id
and hash it. The key is optional: a file converted before it existed falls back
to the PLE EOS token, which is defined and treats the image as a segment
boundary rather than crashing.
Verified end to end with llama-mtmd-cli, a Q4_K_M base and the F16 mmproj, on a
generated image with known content. The model names the red circle, the blue
square, the inverted green triangle and reads "UNSLOTH 42", each with the right
position.
* qwen4exp: support a non-unified KV cache in QSA
set_input_qsa asserted n_stream == 1, so llama-server could not serve this
model with more than one slot unless -kvu was passed. With a non-unified
cache each sequence owns its own cells, and a cell index means a different
token in each stream, so a single shared mapping is wrong.
- cell_blk, blk_cells and bias gain a stream dimension. At n_stream == 1
these collapse to the shapes they had, so the unified path is unchanged.
- Scoring is now batched over streams. ggml_mul_mat matches ne[2] on both
operands, so stream s's queries only ever meet stream s's blocks; without
this sequences would score against each other's context.
- set_input_qsa loops per stream and resolves cells through
v_cells[seq_to_stream[seq_id]], following set_input_kq_mask_impl, instead
of hardcoding v_cells[0].
- llama_kv_cache_context::get_n_stream() is added, mirroring the ns that
get_k and get_v already derive from the slot info.
build_attn_mask_top_k needed no change: it already expects
[n_top_k, n_batch, 1, n_stream], so the top-k result is reshaped to meet it.
set_input_qsa has exactly one caller, so the blast radius is qwen4exp only.
Validation, UD-Q4_K_XL on one B200:
- unified cache unchanged within noise: 1802.9/68.85 -> 1807.2/69.11 t/s at
batch 1, 2262.5/192.43 -> 2270.1/193.75 at batch 4.
- non-unified now runs at npl 1, 4, 16 where it previously aborted, and is
22% faster than the -kvu workaround at batch 16 (1205 vs 984 t/s total),
since per-stream cells avoid the cross-sequence masking a unified cache
pays for.
- no cross-stream contamination: four concurrent sequences each carrying a
distinct secret all recall their own and no other, on both cache modes.
- test-llama-archs green on qwen4exp, deepseek2, gemma3n, qwen3next, llama.
Note on testing: comparing concurrent output against solo output exactly is
not a valid check. It failed 0/4 with no bug present, and the unified-cache
control failed the same way, because batch composition changes the
floating-point reduction order and near-tied tokens flip. The contamination
test above is what the exit code gates on.
* llama: keep the qwen4exp top-k attention mask arch-local
The QSA graph needed a build_attn that attends only to the cells named by a
top_k tensor, and the first version got it by adding a llm_graph_input_attn_kv
overload to llm_graph_context and factoring the mask construction out of the
existing MLA sparse path into a shared build_attn_mask_top_k.
That put a new arch on the shared attention path and made the deepseek32 and
glm-dsa attention build depend on a helper introduced for qwen4exp. Build the
mask in src/models/qwen4exp.cpp instead and leave llama-graph.{h,cpp} exactly as
they were: the MLA path keeps its own copy of the same node sequence.
The nodes emitted are unchanged, so this is bit-identical.
* llama: hold the qwen4exp indexer cache in a new llama_memory_hybrid_idx
The indexer key cache was added by extending llama_memory_hybrid with an
optional third cache, and the host-side cell/block mapping that drives QSA was
added as set_input_qsa on llama_kv_cache. Both are shared classes that every
hybrid and every attention model goes through.
Move both into a new memory type, llama_memory_hybrid_idx, following
llama_kv_cache_msa: the indexer cache and the pos<->cell translation live with
the sparse-attention memory rather than in the classes that serve every other
architecture. llama-kv-cache.{h,cpp} and llama-memory-hybrid.{h,cpp} are
restored to their unmodified state.
init_batch is repeated from llama_memory_hybrid because the indexer cache has to
be handed the attention cache's slot infos, and those are not reachable through
the context the base returns. Allocating them separately lets the two caches
drift, which is what pointed QSA's top-k at the wrong cells before.
The context derives from llama_memory_hybrid_context so build_inp_mem_hybrid
keeps working unchanged, and get_n_stream is computed from the slot infos
exactly as llama_kv_cache_context did.
Behaviour is unchanged: logits over an 8192-token sequence are bit-identical to
the previous implementation, sparse and dense alike.
* llama: save and restore the qwen4exp indexer KV cache
llama_memory_hybrid_idx forwarded clear, seq_rm, seq_cp, seq_keep, seq_add and
seq_div to the indexer cache but not state_write / state_read, so a saved
session dropped the indexer keys and a restored one selected QSA top-k against
an empty cache. The effect is invisible until the context passes
indexer_top_k + compress_ratio - 1 cells, because QSA is exactly dense below
that and the indexer contents cannot change the result.
The indexer section is written last rather than next to the attention cache it
mirrors. As a suffix, a reader that does not expect it stops early and the
trailing bytes are caught by the size check in state_load_file; placed between
the attention and recurrent sections it would instead be parsed as recurrent
state, which can succeed and restore silent garbage. It follows the same
LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY gate as the attention cache, since a partial
checkpoint deliberately skips the token-level attention caches.
The indexer restores its own cells instead of taking the attention cache's
restored slots. The two caches share size, padding and every sequence
operation, and init_batch hands the indexer the attention cache's slot infos,
so both state_read_meta calls run find_slot over identical occupancy and land
on identical cells.
The overrides live on llama_memory_hybrid_idx, the only memory type that owns
an indexer cache, so llama_memory_hybrid and every architecture that uses it
write and read exactly the bytes they did before.
The session and sequence state versions are bumped because the qwen4exp state
layout changed. The session path already rejects a short read via its size
check, but llama_state_seq_load_file accepts one silently, so only the version
check stops a pre-fix blob from being half-restored by a fixed build.
(cherry picked from commit 2721542354f8e158c3217625f4e2e7b83e51e3fe)
* llama: make the qwen4exp PLE n-gram history per context and serialise it
The PLE hash of a token mixes in the ple_ngram_size - 1 tokens before it, which
a decode ubatch does not carry, so they were remembered in a map on
llama_model_qwen4exp. That is the wrong owner twice over.
A llama_model is shared by every context that loads it, and the map was keyed
only by llama_seq_id, so two contexts running the same sequence id - two server
instances on one model, or a draft/target pair - overwrote each other's window.
The next_pos guard turned that into EOS padding instead of a crash, so it
degraded quality silently.
The map was also in no state blob: grep found ple_hist in neither
llama-kv-cache.cpp nor llama-memory-*.cpp nor llama-context.cpp. A restored
context therefore failed the next_pos check on its first ubatch and hashed the
first tokens after the restore against EOS padding. This is why a session blob
round-tripped byte for byte while the restored context computed different
logits: the state was never in the bytes.
It moves to llama_memory_hybrid_idx, which is per context, is the memory type
qwen4exp always builds, and already does the per-sequence bookkeeping this
needs. Every sequence operation now carries the window with it:
seq_rm a rewind (p1 < 0) truncates the window to the surviving prefix and
moves next_pos to p0, so a rollback keeps exact context; a hole
punched in the middle leaves the window non-contiguous, so it is
dropped
seq_cp the destination inherits the source's window, truncated to the
copied position range - a copied sequence continues with the same
n-grams the source would have used
seq_keep every other sequence's window is dropped, like its cells
seq_add a shift that moves the whole window keeps it and moves next_pos with
it, which is the context-shift case; one that cuts through it drops
it
seq_div positions stop being consecutive, so an overlapping window is
dropped
clear everything is dropped
Dropping means next_pos = -1, which set_input turns into full EOS padding: the
same thing a fresh sequence gets, and the same thing this code did before it
followed the sequence operations at all, so no case is worse than before.
The state payload is a self-delimiting list, u32 count then per entry
{ i32 seq_id, i32 next_pos, u32 n_toks, i32 toks[n_toks] }, so a whole-context
save and a single-sequence save share one format and a single-sequence restore
can retarget the window at its destination seq_id. It is written after the
indexer section, last, for the same reason that one is: as a pure suffix an
older reader stops early instead of parsing these bytes as something else.
Unlike the indexer section it is not under LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY.
The window is recurrent state - it is the input the PLE convolution's own
recurrent state is derived from - and the recurrent cache beside it is written
for partial checkpoints too. Gating it would leave the server's speculative
decoding checkpoints restoring the conv state without the window that produced
it.
No further version bump: LLAMA_SESSION_VERSION 10 and LLAMA_STATE_SEQ_VERSION 3
were introduced for the indexer section in the same unreleased series, and both
changes are qwen4exp-only additions to the same blob layout.
Also fixes the padding of a short window. set_input pads a window shorter than
ngram_size - 1 up to that length, but prev() indexes the snapshot with the most
recent token last, and resize() pads at the back, so the filler EOS landed where
the immediately preceding token belongs. It now pads at the front. A window is
short at a sequence start after a one-token prefill, and after a seq_rm rewind,
which the new bookkeeping makes common.
Every architecture other than qwen4exp builds llama_memory_hybrid rather than
llama_memory_hybrid_idx, has no PLE table and never asks for a history, so
nothing about its graph, its sequence operations or its state bytes changes.
(cherry picked from commit de170364c052c68fcf63285cc0028095edb9f23c)
* qwen4exp: tidy comments and simplify image token read
Rewrite the comments this series adds to the AGENTS.md rules: one or two lines,
no prose hard-wrapped mid-sentence, no narrative or history, and no comment that
only restates the code. Net 146 fewer comment lines, no code change.
Correct the PLE image comment: mtmd does not consume the placeholder ids. An
image is decoded as an embeddings-only batch, so ubatch->token is null and the
per-position ids never exist here. gemma3n and gemma4 hit the same case and
stand in row 0 of per_layer_token_embd; qwen4exp stands in the configured image
token id instead.
Read image_token_id straight from self.hparams in the converter. base.py merges
text_config into the root of hparams, and the key sits at the root of
config.json, so the config.json re-read was redundant.
(cherry picked from commit 205840c12169057da3e8d2f65ec4ceec3e18b980)
* qwen4exp: support a quantized KV cache in the QSA attention path
(cherry picked from commit 4c30574f81dc1115d08078c47b6cf8c789c0a842)
* llama: give qwen4exp a large-graph node budget
(cherry picked from commit 37c8c194e6a30e4c46ac29bee3fb264f091596ef)
* qwen4exp: drop an unused variable that breaks -Werror builds
(cherry picked from commit 528d032b51fa3cf935ed3ef6e0fb1c7401df53b5)
* quantize: dequantize and quantize large tensors in row bands
f32_conv_buf held the whole dequantized tensor, which is 204.8 GB for
per_layer_token_embd alone and dies with std::bad_alloc long before the
work buffer is reached. Dequantize and quantize in bands of whole rows
instead, capping the f32 staging at 1 GiB per band.
Rows are independent and the imatrix is indexed by column, so band
boundaries cannot change any output byte. Bands nest inside the existing
per-expert loop so each expert slice keeps its own imatrix, and a band is
kept to at least one quantization chunk per worker thread so the existing
multithreading still has work. F32 sources still stage nothing and are
banded by pointer arithmetic into the tensor.
llama_tensor_dequantize_impl now takes a first element offset; the single
caller is updated.
(cherry picked from commit 658c22549613555dbce57a772be4de8509eba3ee)
* llama: segment the qwen4exp fused QKV for tensor split
qwen4exp was missing from the gated delta net branch of get_split_segments,
so its attn_qkv.weight, shaped {n_embd, 2*key_dim + value_dim}, fell through
to the generic fused QKV rule and tripped
GGML_ASSERT(tensor->ne[axis] == n_embd + 2*n_embd_gqa) while loading with
--split-mode tensor. --split-mode layer was unaffected.
qwen4exp broadcasts K to the V heads by tiling, k_conv is grown with a plain
ggml_repeat_4d over the head axis so that v head j pairs with k head
j % n_k_heads. That is the Qwen 3.5 pattern, not the repeat interleave that
Qwen 3 Next builds explicitly, so qwen4exp takes the else branch and its V is
segmented on the scale of K.
Reported by benklop.
(cherry picked from commit 353d753f595dc81634ae6130188b31f06018f5ae)
* llama: fix the qwen4exp PLE history seq_rm(-1) iterator invalidation and the fatal-warning build
ple_hist_rm recursed over ple_hist with a range-based for and the recursive call
erases the entry it is iterating when the whole sequence is removed (p0 <= 0,
p1 < 0), so the loop then increments an invalidated iterator. It is unreachable
today only because llama_memory_recurrent::seq_rm rejects seq_id < 0 before
llama_memory_hybrid_idx::seq_rm reaches the history, which is a guard in another
class. Advance past the entry before recursing.
Two smaller things in the same area:
- the n_toks sanity bound in ple_hist_state_read was the literal 64, which is
the value of LLAMA_MAX_PLE_HEADS, not of the quantity being checked. The
window is at most ple_ngram_size - 1 tokens, so the bound is
LLAMA_MAX_PLE_NGRAM - 1, eight times tighter.
- build_conv_state_at left mem_size unused, so -DLLAMA_FATAL_WARNINGS=ON does
not compile. Predates this series; drop the line.
(cherry picked from commit 6eba44a89d5f328eb4859b844e1d28fb564cbe3e)
* qwen4exp: include llama-impl.h explicitly for llama_mul_mat_hadamard
(cherry picked from commit b634fd4d250d181ef82bf78bd00c1ae3b96a7af6)
* convert: fix the qwen4exp lint and type-check failures
flake8 flagged an unused MmprojModel import, and ty flagged seven errors in
the PLE streaming path: eos_token_id can be absent, and _ple_map, _ple_path,
_ple_row_dim and _ple_rows_per_shard are all Optional at the declaration but
were dereferenced without narrowing.
The map is opened and the stride fixed before the first shard is written, and
_finish_ple_table only runs once every shard has landed, so the invariants
hold. Assert them so the checker can see it. A missing eos_token_id now raises
with the reason instead of a TypeError from int(None).
* llama: give the qwen4exp indexer cache its own tensor names
The indexer KV cache and the attention KV cache both named their tensors
cache_k_l%d, so the Meta backend matched the indexer cache against the
attention split pattern and aborted in handle_set_rows. Tag the names
instead, and mirror the indexer cache: it has one key head and its
projections are mirrored.
(cherry picked from commit a1cdc8181134659766763a17762545a1f0e5db7b)
* qwen4exp: double the Q split granularity for tensor parallelism
qwen4exp fuses the attention gate into attn_q.weight the same way qwen3next
and qwen 3.5 do, so a device boundary must fall on a whole q+gate pair or the
Q heads stop lining up with the K/V heads and attn_output rows.
(cherry picked from commit 6c9a592f0a425a459ab6efae3b897cf68460e244)
* qwen4exp: keep the indexer cache in step across server slots
The QSA indexer keeps a side cache addressed by the cells of the attention
cache, so cell j has to hold the same token in both: the top-k indices it
produces are applied to the attention KQ mask. init_batch already hands the
indexer the attention cache's slot layout rather than letting it look for its
own, but the restore path did not. state_read called llama_kv_cache::state_read
on the two caches in turn and each ran its own find_slot over its own occupancy.
That agrees only for as long as nothing has already pushed the two caches apart,
which is the property a restore is supposed to re-establish rather than one it
can lean on.
The failure path was the worse half, and it is reachable from the public API
with nothing more than a short buffer. Truncating a good blob at 35 offsets and
feeding it to llama_state_seq_set_data left the two caches disagreeing at 5 of
them, and every one of 23 truncations of a whole-context blob did. Four of those
five land inside the attention section, so the attention cache drops the
sequence and the indexer keeps it; only the cut that lands in the indexer
section gives the opposite direction. llama_kv_cache::state_read cleans up its
own cache and rethrows, so whichever way it falls, nothing is left to bring the
two back together. The server papers over this by clearing the slot when a
prompt cache load fails; a caller of llama_state_seq_set_data that does not is
left with an indexer addressing cells that no longer mean what it thinks.
llama_kv_cache::state_read_sinfo reports the cells a restore landed in, or takes
a copy of them, and state_read_meta uses a supplied layout in place of find_slot
once it has checked that those cells are free here too. The indexer now adopts
the attention cache's restored layout by construction instead of reproducing it
by coincidence, and a layout that does not fit fails the read rather than being
applied over cells that already drifted. The hybrid restore is wrapped so that
any failure drops the sequence, or for a whole-context restore the context, from
all three caches at once, which is a state they do agree on.
* kv-cache: clear the cache once when restoring a whole context
state_read walks the streams of the cache in turn, and for a whole-context restore
each stream went through state_read_meta, which starts by calling clear(). clear()
resets every stream at once, so each stream after the first threw away the streams
already restored, and the K/V buffers with them. A non-unified cache holds one
stream per sequence, so a context saved with N sequences in it came back with only
the sequence in the last stream that carried any cells - the highest sequence id.
A unified cache has one stream and never showed it.
The cache is now emptied once, before the loop, which is what a whole-context
restore means. A blob whose streams are all empty now empties the cache as well,
where before it left the old contents in place.
* kv-cache: check the mirrored slot layout on a whole-context restore too
state_read_meta only looked at the layout it was given on the single-sequence path.
A whole-context restore lays the cells out from 0 in both caches, so they agree as
long as they restore the same number of cells, but nothing checked that they did: an
indexer section belonging to some other context was read over cells the attention
cache had filled from a different one, which is the state the indexer must never be
left in.
* qwen4exp: give the PLE conv history its own mirrored recurrent row
n_embd_r() reserved n_conv + ple_conv_state() so that one cache_r_l row could
carry both the delta-net conv state and the PLE dilated conv history, but the
QWEN4EXP arm of get_split_segments only described n_conv. Under -sm tensor the
segment sum came up short by ple_conv_state() and llama_memory_recurrent
construction aborted in ggml_backend_meta_alloc_ctx_tensors_from_buft.
Widening the segment list is not the fix. The Meta backend propagates a view's
split descriptor from its parent unchanged, so a view of one sub-range of a
split axis is sized as the whole row on every device; declaring the PLE tail as
a second segment merely moves the abort to "shape mismatch for VIEW" at graph
allocation. The two histories also want opposite policies: the delta-net state
is split by head to match wqkv and ssm_conv1d, while per_layer_tok_embd,
ple_conv1d and ple_norm_conv are all mirrored, so every device computes the
whole dilated conv and needs the whole history. One tensor cannot be both, and
the split state has no per-segment mirroring.
Move the PLE history into its own cache_ple_r_l%d row, mark it MIRRORED, and
return n_embd_r() to n_conv. The row is allocated only on layers where is_ple
holds, so mirroring one 92160-element row per device replaces a 92160-element
tail on all 36 recurrent rows: the recurrent R footprint drops rather than
grows. build_conv_state_at now takes its width from the tensor it was handed
and keys its gather on that tensor, which also drops a cont of a strided view.
* no more ple_hist (use master version)
* llama: give the qwen4exp full memory context its indexer cache
graph_reserve() walks a full memory context, and qwen4exp builds its
sparse attention only when the context exposes an indexer cache. the
full-context constructor left ctx_idx null, so the reserved worst case
was the dense fallback: a smaller graph than the one decode executes.
ggml-alloc then had to grow the compute buffer on the first decode,
past the size reported at load.
with -np 4 -c 32768 -fa on -ctk q8_0 -ctv q8_0 on an IQ1_S qwen4exp,
the reserved CUDA0 buffer was 217.00 MiB against 275.71 MiB actually
used, and CUDA_Host 42.31 MiB against 191.14 MiB. reserving the sparse
graph makes both match exactly, in unified and non-unified cache mode.
Co-authored-by: Pascal <admin@serveurperso.com>
Assisted-by: Claude
* qwen4exp: shrink the PLE hparams storage
llama_hparams is held by value inside llm_graph_params and every llm_graph_input_*,
and llm_graph_params is a stack local in graph_reserve and process_ubatch, so its
width is paid on every worker thread stack.
is_ple_impl spent 2048 bytes carrying 512 bits. It is the one per-layer flag that is
not moved through the loader's uint32 array templates, so a bitset costs nothing in
call sites and also removes the uninitialized read that non-qwen4exp archs had, since
nothing filled the array for them.
The PLE head offsets and vocab sizes are token-space indices; the gather that consumes
them already truncates to int32, so 64-bit storage was never reachable. The gguf arrays
stay uint64 for file compatibility and are narrowed on load.
sizeof(llama_hparams) 34440 -> 31944, sizeof(llm_graph_params) 34872 -> 32376.
* llama: opt-in random-access mmap advice for host-resident gather tables
qwen4exp keeps per_layer_token_embd on the host: 26.8 GiB at IQ4_NL, read
by ggml_get_rows as 16 gathers of ~90-170 bytes per token, spread across
16 head regions ~20M rows apart. Measured over 4.75M gathers, no two
consecutive gathers land on the same 4 KiB page, so the readahead the
loader asks for buys nothing here and the whole table ends up cached to
serve about 4% of itself.
llama_mmap applies POSIX_FADV_SEQUENTIAL, MAP_POPULATE and a whole-file
POSIX_MADV_WILLNEED unconditionally. Those are right for streaming the
file once into buffers and wrong for whatever stays mapped afterwards.
Under LLAMA_MMAP_RANDOM the eager pull-in is skipped and the mapping is
advised random once every tensor has been read, so the load itself keeps
its sequential readahead. That alone drops the table to 4.4% resident but
serializes one NVMe latency per gather.
The second half is what pays for it: the PLE input already computes every
row index for the ubatch before the graph runs, so the pages those rows
fall on are handed to the kernel in one batch and the reads overlap.
POSIX_MADV_WILLNEED on POSIX, PrefetchVirtualMemory on Windows, which
takes the discontiguous ranges in a single call.
Off by default and off for every other model: the batched prefetch keys
off "this mapping was advised random", which nothing sets unless the user
opts in.
-c 512 --chunks 60, cold, IQ1_S, mean of 3:
default 35.3 s 26.82 GiB resident (100%)
advice only 104.5 s 1.19 GiB resident (4.4%)
advice + prefetch 34.2 s 1.19 GiB resident (4.4%)
PPL 4.2346 +/- 0.07862 in all three. IQ1_S KLD is unchanged in every
field, including Mean KLD 0.396070 +/- 0.001931 and Same top p 77.325%.
* llama: narrow the random-access mmap advice to the gather table
The advice was applied per mapping: every mapping the model kept got
POSIX_MADV_RANDOM plus a whole-file POSIX_FADV_RANDOM, and the eager
pull-in was skipped for every file. On qwen4exp that also hit
token_embd.weight, which sits 0.33 GiB past the PLE table in the same
shard and is read densely, not by sparse gathers. Measured over
-c 512 --chunks 60 on IQ1_S it fell to 8.45% resident, against 100% with
the feature off.
A model now nominates its gather tables (qwen4exp: per_layer_tok_embd)
and only those byte ranges are advised. The range is rounded out to
whole pages, which on this model takes in 832 bytes before and 192
after. token_embd goes back to 86.55% resident and the PLE table still
drops to 4.44%; smaps shows one VM_RAND_READ VMA of exactly the table
instead of one over all 27.16 GiB that stays mapped.
posix_fadvise is dropped from the narrowed path. POSIX_FADV_RANDOM
ignores its offset and length and marks the whole open file, and the
FMODE_RANDOM it sets is only read by page_cache_sync_ra() on the read()
path, which a fault on a MADV_RANDOM vma never reaches. POSIX_FADV_
DONTNEED does take a range, so the drop mode keeps it.
The eager pull-in is now skipped only for the files holding a nominated
table, and re-issued as WILLNEED over the rest of such a file, so other
shards load exactly as before.
prefetch_rows() keys off the tensor being nominated rather than off a
mapping-level flag, so the batched readahead lands only where the advice
did.
-c 512 --chunks 60, cold, IQ1_S, mean of 3, total wall:
default 32.50 s
whole mapping 30.05 s
narrowed 30.35 s
PPL 4.2061 in all three. IQ1_S KLD is bit-identical with the feature on
and off, including Mean KLD 0.396070 +/- 0.001931 and Same top p
77.325%. tg128 73.65 +/- 0.33 narrowed against 73.49 +/- 0.34 whole.
Assisted-by: Claude
* llama: fold the random-access prefetch into its own feature flag
LLAMA_MMAP_RANDOM_PREFETCH existed to measure the two halves of the feature
apart, and the measurement is done: on a cold cache over the same wikitext
run, MADV_RANDOM without the batched readahead takes 94.4 s against 36.7 s
for an untouched mapping, while the pair together take 34.1 s. Suppressing
the kernel's readahead only pays if we replace it, so the split let a user
select a 2.6x regression through a documented switch.
Keep the accessor, since the call site reads better than a mode comparison,
but derive it from the mode alone.
* FACP (Fewer Acronym Classes Please)
* qwen4exp: bias the QSA selection per block, not per cell
The QSA bias is a graph input, so it is pinned on the host and uploaded every
decode, and at -c 32768 -np 4 its twelve copies were 768 of the 815 MiB of
reserved host compute buffer.
Only one half of it needs a cell: whether the cell sits in the always-visible
tail, and whether its block was pooled. Both are properties of the block. The
other half - empty, other sequence, or in the future - is the plain visible/not
test the attention mask already carries over the same cells, so add that mask
instead of repeating it. The bias then holds one value per block.
A block sits wholly inside or wholly outside the tail because the tail starts on
a block boundary, so one value per block is exact. Cells no block covers keep
their -inf from the mask.
The mask is F16 and the bias F32, and a mixed ggml_add reinterprets the F16
buffer as float rather than converting it, so the cast is required.
reserved host compute buffer at -c 32768 -np 4:
--kv-unified 814.86 -> 238.86 MiB, CUDA0 721.07 -> 421.07 MiB
--no-kv-unified 214.86 -> 70.86 MiB, CUDA0 317.07 -> 265.07 MiB
Selection is unchanged: over 8192 tokens, four times the budget, every QSA
layer returns identical top-k indices and the logprobs are bitwise equal.
Two things a reviewer should know. A cell whose position divides past the last
block is guarded by an assert rather than handled, because no run reached it.
And the mask's same-position M-RoPE rule cannot fire for text and was never
exercised for images, so the 2D case is unverified.
* clean up code comments
* clean up new comments
* revert LLAMA_MMAP_RANDOM
* nits
* replace some changes with #27795
* improve the m-rope image for get_prev_tokens
* LazyChunkedTensor
* fix lint
* add some validations
* reduce input nodes
* trim output tokens
* nits
* some more sanity checks
* fix llm_graph_input_ple reuse
* exclude from webgpu test
---------
Co-authored-by: danielhanchen <danielhanchen@users.noreply.github.com>
Co-authored-by: danielhanchen <unslothshared@gmail.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Pascal <admin@serveurperso.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
|
||
|
fairydreamingandStanisław Szymczyk
|
7584430716 |
tests : disable DOTS3NOTE arch test for WebGPU (#27654)
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> |
||
|
Aman Gupta
|
bf0a29cc16 |
Deepseek 4: -sm tensor (#26490)
* DSV4: sm tensor * set coarser granularity for head splits * fix dspark * add model saving for dsv4 + allow dflash to return on specific device * add comment about dsv4 seq_rm * simplify * add shared expert delayed allreduce * remove special test for dsv4 |
||
|
Aman GuptaandGeorgi Gerganov
|
b0539c43ed |
DeepseekV4: fix rollback with multi-seq (#26756)
* DeepseekV4: fix rollback with multi-seq * fix model loading * make pending rollback single use * only clear cache for seq_id for full load * add assert for compress ratio * make graph topology static * pass true instead of flags in clear_compressed * cont : clean-up + TODOs --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> |
||
 Gaurav Garg
|
d3371929bb |
[Tensor parallel] Fix meta tensor split state propagation (#27574)
* ggml : fix meta tensor split state propagation * Add test-llama-archs to CI |