Xuan-Son Nguyen efe3626b11 model: support vllm d3 models (#30383) ...

* models: support pplx-decider

* vllm d2

* update

* clarify naming rule

* stricter validation

* d3

2026-10-12 15:01:52 +02:00

..

batched-bench

batch: migrate the rest of examples to llama_batch_ext (#29601)

2026-09-30 18:08:43 +02:00

cli

server: use port 9931 by default (#30159)

2026-10-09 10:40:03 +02:00

completion

llama: support MoE cache over multiple GPUs (#30112)

2026-10-08 15:50:49 +05:30

cvector-generator

batch: migrate the rest of examples to llama_batch_ext (#29601)

2026-09-30 18:08:43 +02:00

export-lora

docs: fix export-lora --lora-scaled syntax [no release] (#24703)

2026-06-18 16:46:17 +02:00

fit-params

server: use port 9931 by default (#30159)

2026-10-09 10:40:03 +02:00

gguf-split

cmake : introduce semantic versioning (#26839)

2026-08-12 14:15:03 +02:00

imatrix

imatrix : include clocale for std::setlocale (#30079)

2026-10-07 10:58:22 +02:00

llama-bench

llama-bench: respect -fitc if bigger than required benchmark size (#28331)

2026-10-09 19:14:30 +02:00

mtmd

model : support MiniCPM-V 4.7 (#29416)

2026-10-10 20:41:59 +02:00

perplexity

batch: migrate the rest of examples to llama_batch_ext (#29601)

2026-09-30 18:08:43 +02:00

quantize

quantize: cap working memory size to avoid loading big tensors onto RAM (#27795)

2026-08-27 18:31:13 +02:00

results

batch: migrate the rest of examples to llama_batch_ext (#29601)

2026-09-30 18:08:43 +02:00

rpc

rpc : turn GGML_RPC_DEBUG into a verbosity level and add logs (#29544)

2026-10-11 17:43:35 +03:00

server

model: support vllm d3 models (#30383)

2026-10-12 15:01:52 +02:00

tokenize

tokenize : drop --stdin mutual-exclusion check (#25672)

2026-07-15 18:41:51 +02:00

tts

args: add --video-* CLI arguments (#24318)

2026-08-27 12:11:12 +02:00

tuning

metal : key the fa-vec tuned table by family instead of SKU (#29075)

2026-09-23 19:23:15 +08:00

ui

ui: fix text attachment preview overflow (#29898)

2026-10-12 10:20:16 +02:00

CMakeLists.txt

metal : per-device tuned (Q, NE) for flash-attn vec (#26570)

2026-08-24 19:22:27 +03:00