doc: Update model references in supported_models.md (#32188)

Andy Zhang committed 10 months ago

[ROCm] [Bugfix] Fix order of mori build in Dockerfile.rocm_base (#32179)

TJian committed 10 months ago

doc: Update model name for Qwen3-Coder in documentation (#32185)

Andy Zhang committed 10 months ago

OffloadingConnector: Add cpu_bytes_to_use configuration (#24498)

Or Ozeri committed 10 months ago

[Feature] Support recording expert indices for rollout router replay (#28284)

Hongxin Xu committed 10 months ago

[P/D] Refactor mooncake connector sender thread using async coroutines (#31573)

dtc committed 10 months ago

[Bugfix] Fix missing scale passing for encoder Triton Attention implementation (#32149)

Isotr0py committed 10 months ago

[Doc] Add documentation for offline API docs feature (#32134)

RickyChen / 陳昭儒 committed 10 months ago

[Doc] Improve LoRA docs (#32159)

Jee Jee Li committed 10 months ago

[doc] fix broken links (#32158)

XlKsyt committed 10 months ago

[Frontend] Fix Flaky MCP Streaming Test (#32153)

daniel-salib committed 10 months ago

[cpu][bench] Add Fused MoE Micro Benchmark for CPU Backend (#32092)

Andika Rachman committed 10 months ago

[Misc] Disable default `--ready-check-timeout-sec` extra call in vllm bench (#30975)

Nicolò Lucchesi committed 10 months ago

[Model] Remove incorrect `SupportsPP` from MTP models (#32150)

Cyrus Leung committed 10 months ago

[Model] Improve multimodal pooling examples (#32085)

wang.yuqi committed 10 months ago

[Model] Avoid hardcoding pooling type (#32119)

Cyrus Leung committed 10 months ago

[Model Runner V2] Remove async barrier (#32083)

Woosuk Kwon committed 10 months ago

[Model Runner V2] Skip building deprecated fields in attn metadata (#32132)

Woosuk Kwon committed 10 months ago

[CI] fix `test_concat_and_cache_mla_rope_fused` (#32117)

Jiangyun Zhu committed 10 months ago

fix offline inference chat response prompt (#32088)

Ning Xie committed 10 months ago