[Core] Simplify mm processing cache (#22457)

Cyrus Leung committed over 1 year ago

Fix pre-commit error in main (#22462)

Woosuk Kwon committed over 1 year ago

[gpt-oss] Generate ResponseOutputItem from Harmony Message (#22410)

Chen Zhang committed over 1 year ago

[Tool] Fix auto tool call (#22434)

Chen Zhang committed over 1 year ago

[Bugfix] Add missing `packed_modules_mapping` to `DeepseekV2ForCausalLM` (#22352)

fxmarty-amd committed over 1 year ago

[Core] Store only the keys for multi-modal data in P0 (#22198)

Cyrus Leung committed over 1 year ago

[Docs] Update features/disagg_prefill, add v1 examples and development (#22165)

WeiQing Chen committed over 1 year ago

[Doc] update docs for nightly benchmarks (#12022)

Andrew Chan committed over 1 year ago

[Docs] Factor out troubleshooting to its own guide; add section for Ray Observability (#21578)

Ricardo Decal committed over 1 year ago

[Doc] Fix link to prefix caching design (#22384)

Yong Hoon Shin committed over 1 year ago

[Misc] Enhance code formatting in mxfp4.py (#22423)

Woosuk Kwon committed over 1 year ago

Add H20-3e fused MoE kernel tuning configs for GLM-4.5 (#22433)

JaceyShao committed over 1 year ago

[Docs] Add missing dependency for docs build (#22435)

Harry Mellor committed over 1 year ago

feat: Add --enable-log-outputs flag for logging model generations (#20707)

Adrián García García committed over 1 year ago

[Misc] Support routing logic simulation (#21990)

Ming Yang committed over 1 year ago

[Frontend] Update OpenAI error response to upstream format (#22099)

Moritz Sanft committed over 1 year ago

[Model] Switch to Fused RMS norm in Qwen2.5_VL model. (#22184)

vllmellm committed over 1 year ago

[Bench] Split serve.py:main into async/async versions (#22405)

lkchen committed over 1 year ago

[CI] Skip the pooling models that do not support transformers v4.55 (#22411)

wang.yuqi committed over 1 year ago

[Bugfix] EPLB load statistics problem (#22167)

WeiQing Chen committed over 1 year ago