Yonghye Kwon 838093f192 llama : remove simple batch splitting for DSV4 (#31300) ...

* llama : fix DSV4 compressor padding for simple batches

Count actual tokens per sequence when padding compressor writes. Add a graph reuse regression test for odd-sized DeepSeek V4 and V4.1 batches.

Assisted-by: Codex

* tests : cover multiple sequences in DSV4 padding regression

Exercise one and two sequences at different positions while keeping a fixed ubatch shape.

Assisted-by: Codex

* llama : remove simple batch splitting for DSV4

Use the existing sequence splitting to keep n_seq_tokens consistent with
the compressor padding calculation. Extend the graph reuse regression to
6-token batches.

Assisted-by: Codex

2026-10-28 23:25:47 +08:00

..

models

model : add LiquidAI/d1-2B and LiquidAI/d1-omni-2B (#31275)

2026-10-27 23:36:32 +01:00

CMakeLists.txt

llama : add a GPU cache for MoE experts kept in host memory (#29887)

2026-10-07 21:07:45 +03:00

llama-adapter.cpp

lora : support prism.hadamard folded weights (#30910)

2026-10-22 08:12:17 +03:00

llama-adapter.h

llama : re-enable manual LoRA adapter free (#19983)

2026-03-18 12:03:26 +02:00

llama-arch.cpp

model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B (#31252)

2026-10-27 17:06:40 +01:00

llama-arch.h

model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B (#31252)

2026-10-27 17:06:40 +01:00

llama-batch.cpp

spec : add lilicorr support (#30506)

2026-10-15 05:49:25 +02:00

llama-batch.h

model: fix vllm d3 multi seq case (#30408)

2026-10-13 00:23:01 +02:00

llama-chat.cpp

chat : add Granite 4.1 chat template (#23518)

2026-05-28 13:13:33 +02:00

llama-chat.h

chat : add Granite 4.1 chat template (#23518)

2026-05-28 13:13:33 +02:00

llama-context.cpp

model : add LiquidAI/d1-2B and LiquidAI/d1-omni-2B (#31275)

2026-10-27 23:36:32 +01:00

llama-context.h

llama : skip logits buffer allocation when graph produces no logits (#30255)

2026-10-13 11:24:20 +03:00

llama-cparams.cpp

cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)

2025-06-15 10:08:58 +03:00

llama-cparams.h

llama: create new fused op for QSA mask (#30640)

2026-10-22 01:02:22 +08:00

llama-ext.h

tests : refactor test-llama-archs to not link internal libllama symbols (#30880)

2026-10-26 12:16:02 +02:00

llama-grammar.cpp

common, grammar: add recursive depth limit, make it a requirement (#31153)

2026-10-25 23:53:08 +01:00

llama-grammar.h

grammar: limit recursion depth to prevent stack overflow (#29495) (#29755)

2026-10-25 12:10:10 +01:00

llama-graph.cpp

model : add LiquidAI/d1-2B and LiquidAI/d1-omni-2B (#31275)

2026-10-27 23:36:32 +01:00

llama-graph.h

llama : build the k-pool sparse selection independently of the kq_mask shape (#31243)

2026-10-27 21:57:45 +08:00

llama-hparams.cpp

llama: add llama_batch_ext (#24669)

2026-09-24 16:25:07 +02:00

llama-hparams.h

model : add LiquidAI/d1-2B and LiquidAI/d1-omni-2B (#31275)

2026-10-27 23:36:32 +01:00

llama-impl.cpp

llama : optimize vocabulary loading (#30679)

2026-10-21 12:03:27 +03:00

llama-impl.h

llama : optimize vocabulary loading (#30679)

2026-10-21 12:03:27 +03:00

llama-io.cpp

server : avoid checkpoint data host copies (#22558)

2026-05-02 18:03:25 +03:00

llama-io.h

llama : fix K/V and recurrent state cleanup after failed restores (#27530)

2026-09-26 10:23:03 +03:00

llama-kv-cache-dsa-iswa.cpp

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache-dsa-iswa.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache-dsa.cpp

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache-dsa.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache-dsv4.cpp

llama : remove simple batch splitting for DSV4 (#31300)

2026-10-28 23:25:47 +08:00

llama-kv-cache-dsv4.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache-iswa.cpp

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache-iswa.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache-msa.cpp

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache-msa.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cache.cpp

tests : adjust constants to reduce irrelevant warnings (#31254)

2026-10-28 11:26:38 +02:00

llama-kv-cache.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-kv-cells.h

add GLM-5.3-Flash (GLM5-Next) support (#27773)

2026-09-30 14:20:32 +08:00

llama-memory-hybrid-idx.cpp

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-memory-hybrid-idx.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-memory-hybrid-iswa.cpp

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-memory-hybrid-iswa.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-memory-hybrid.cpp

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-memory-hybrid.h

llama : remove obsolete n_pad from memory instances (#31200)

2026-10-27 07:53:44 +02:00

llama-memory-recurrent.cpp

llama : move no_alloc out of llama_hparams (#31141)

2026-10-26 16:21:25 +02:00

llama-memory-recurrent.h

llama : move no_alloc out of llama_hparams (#31141)

2026-10-26 16:21:25 +02:00

llama-memory.cpp

llama : move no_alloc out of llama_hparams (#31141)

2026-10-26 16:21:25 +02:00

llama-memory.h

llama : move no_alloc out of llama_hparams (#31141)

2026-10-26 16:21:25 +02:00

llama-mmap.cpp

llama : split llama_prefetch() into merge and prefetch steps (#30532)

2026-10-15 09:12:45 +02:00

llama-mmap.h

llama-mmap : avoid a second full-size copy of each tensor with direct-io (#29749)

2026-10-01 09:44:31 +02:00

llama-model-loader.cpp

model: DSV4.1 flash (#31086)

2026-10-25 09:43:51 +08:00

llama-model-loader.h

llama : do not map foreign ranges into a backend buffer (#30405)

2026-10-13 17:28:15 +03:00

llama-model-saver.cpp

tests : refactor test-llama-archs to not link internal libllama symbols (#30880)

2026-10-26 12:16:02 +02:00

llama-model-saver.h

tests : refactor test-llama-archs to not link internal libllama symbols (#30880)

2026-10-26 12:16:02 +02:00

llama-model.cpp

model : add LiquidAI/d1-2B and LiquidAI/d1-omni-2B (#31275)

2026-10-27 23:36:32 +01:00

llama-model.h

llama : move no_alloc out of llama_hparams (#31141)

2026-10-26 16:21:25 +02:00

llama-moe-cache.cpp

llama : move no_alloc out of llama_hparams (#31141)

2026-10-26 16:21:25 +02:00

llama-moe-cache.h

llama : move no_alloc out of llama_hparams (#31141)

2026-10-26 16:21:25 +02:00

llama-quant.cpp

model : add LiquidAI/LFM3-Audio-2B and LiquidAI/LFM3-Omni-2B (#31257)

2026-10-27 18:47:14 +01:00

llama-quant.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-sampler.cpp

llama: fix exhausting CPU and MEM caused by dry sequence breaker (#31035)

2026-10-25 12:31:09 +01:00

llama-sampler.h

llama : support multi-output backend sampling (#25532)

2026-08-10 16:58:56 +03:00

llama-version.h.in

llama: fix whole source code rebuilt on each new commit (#28278)

2026-09-03 23:53:04 +02:00

llama-vocab.cpp

common, grammar: add recursive depth limit, make it a requirement (#31153)

2026-10-25 23:53:08 +01:00

llama-vocab.h

mtmd : add Soprano TTS support (#28607)

2026-10-24 01:09:50 +02:00

llama.cpp

llama : move no_alloc out of llama_hparams (#31141)

2026-10-26 16:21:25 +02:00

unicode-data.cpp

unicode : add opt-in NFC normalization for Unigram tokenizers (#30390)

2026-10-14 08:33:24 +03:00

unicode-data.h

unicode : add opt-in NFC normalization for Unigram tokenizers (#30390)

2026-10-14 08:33:24 +03:00

unicode.cpp

llama : optimize vocabulary loading (#30679)

2026-10-21 12:03:27 +03:00

unicode.h

llama : optimize vocabulary loading (#30679)

2026-10-21 12:03:27 +03:00