[Bugfix][Frontend] Constrain Anthropic cache_salt to non-empty (#50764)

Omkar Shewale committed 3 months ago

cpu_model_runner.py: skip the warm up if CompilationMode.NONE (#50547)

YAMAMOTO Takashi committed 3 months ago

[Bugfix][KV Connector] Propagate EAGLE state across merged Mooncake store groups (#49069)

Yifan Qiao committed 3 months ago

[Bugfix] serving_llama70B_tp4 benchmark was silently running at tensor_parallel_size=1 (#50766)

Turner Jabbour committed 3 months ago

[Model] Support jina-embeddings-v5-text-nano (EuroBERT encoder backbone) (#50688)

Omkar Shewale committed 3 months ago

[Test][V1] Add sleep/wake correctness regression test for hybrid GDN/… (#44972)

chun-wan committed 3 months ago

[Attention][MiniMax-M3] Add MSA speculative decode verification (#50032)

Jason Li committed 3 months ago

[ROCm][Bugfix][Kimi-K3] Preserve MoE correction bias in FP32 (#50761)

Fangzhou Ai committed 3 months ago

[Model Runner v2] Enable BGE M3 pooling embed token_classify (#50661)

Taneem Ibrahim committed 3 months ago

[Elastic EP] Fix non-contiguous weight transfers (#50641)

Itay Alroy committed 3 months ago

[Bugfix][Models] Accept Qwen3_5MoeTextConfig in Qwen3_5MoeProcessingInfo for transformers 5.x compatibility (#50704)

Rafli Surya Wijaya committed 3 months ago

[1/N] Unify multiple-path encoder cuda graph support (#49934)

Isotr0py committed 3 months ago

[Bugfix][Doc] Fix references to FusedMoE in doc (#50701)

bnellnm committed 3 months ago

[DSV4] Implement Sequence Parallelism (#46789)

Woosuk Kwon committed 3 months ago

[GPT-OSS] Strict tool call and constrained decoding for Harmony (#45560)

yzong-rh committed 3 months ago

Add @hongxiayang as code owner for AMD-specific model files and ROCm docs (#50608)

Hongxia Yang committed 3 months ago

[model registry] some simple typos (#50673)

Ning Xie committed 3 months ago

[Core] Offload raw-prompt preprocessing to renderer thread pool in AsyncLLM (#49608)

Almog Tavor committed 3 months ago

[Benchmark] Add probe requests to vllm bench serve (#49611)

Guan-Ming Chiu committed 3 months ago

[Bugfix][Kernel] Fix dangling temporary in AWQ gemm torch::stable::sum dim arg (#46805)

xiaolinchen committed 3 months ago