Upstream triton fp4 weight preshuffle (#28888)

Aleksandr Malyshev committed 12 months ago

GPU Model Runner V2 (#25266)

Woosuk Kwon committed 12 months ago

[CI] Add batch invariant test to ci (#27842)

Wentao Ye committed 12 months ago

[CI/Build] Fix illegal memory access and unsupported test in kernels/attention/test_cache.py (#29118)

rasmith committed 12 months ago

[Misc] Move dynamic seed initialization to `EngineArgs` (#29165)

Cyrus Leung committed 12 months ago

[Doc] Update plugin doc (#28532)

wangxiyuan committed 12 months ago

[Perf] These changes enhance the NUMA functionality of vllm for systems with more than one NUMA nodes per socket (#25559)

skaraban3807 committed 12 months ago

Fix mistral config (#29172)

Julien Denize committed 12 months ago

Tool Call Parser logs should not contain user input / model output except on DEBUG (#29160)

sfbemerk committed 12 months ago

fix cross attention (#28346)

who who who committed 12 months ago

Revert "Revert #28875 (#29159)" (#29179)

Cyrus Leung committed 12 months ago

Update Dockerfile to use gcc-toolset-14 and fix test case failures on power (ppc64le) (#28957)

Bhagyashri committed 12 months ago

[Core] Align whisper closer to other multimodal models (#27292)

Russell Bryant committed 12 months ago

[V0 deprecation] Remove more V0 references (#29088)

Cyrus Leung committed 12 months ago

[Misc] remove useless v1 env (#29164)

WeiQing Chen committed 12 months ago

Revert #28875 (#29159)

Cyrus Leung committed 12 months ago

[CI Failure] Fix Gemma3 RoPE configuration for sliding attention layers (#29111)

Huamin Li committed 12 months ago

[Minor][Clean] Remove the legacy assertion in video (#29150)

Canlin Guo committed 12 months ago

[Small] Capture AttributeError when checking ray dependency. (#29024)

Chenheli Hua committed 12 months ago

[Bugfix] Fix default MM LoRA alignment for single str prompts (#29140)

Alex Brooks committed 12 months ago