[V0][V1][Core] Add outlines integration for V1, and update V0 integration. (#15975)

Nathan Hoos committed over 1 year ago

[Bugfix] [CI] Fix Tensorizer LoRA test (#20760)

Sanger Steel committed over 1 year ago

[Test] Remove docker build from test. (#20542)

QiliangCui committed over 1 year ago

Fix DeepSeek-R1-0528 chat template (#20717)

sfbemerk committed over 1 year ago

[Model][VLM] Support JinaVL Reranker (#20260)

shineran96 committed over 1 year ago

[Model] Add reason parser for Hunyuan A13B Model. (#20625)

Asher committed over 1 year ago

[ROCm][Regression] Remove tensor creation that harms performance on ROCm (#20741)

Gregory Shtrasberg committed over 1 year ago

[Hardware][CPU] Vllm int8 quantization enablement for ARM CPU (#14129)

nishith-fujitsu committed over 1 year ago

Update Dockerfile FlashInfer to v0.2.8rc1 (#20718)

Michael Goin committed over 1 year ago

[Doc] Add engine args back in to the docs (#20674)

Harry Mellor committed over 1 year ago

[Misc] Clean up mark to fork process in BNB tests (#20692)

Isotr0py committed over 1 year ago

Normalize lm-eval command between baseline and correctness test (#18560)

Michael Goin committed over 1 year ago

[CI Bugfix] Skip failing Tensorizer+LoRA test (#20724)

Michael Goin committed over 1 year ago

[doc] fix ordered list (#20749)

Reid committed over 1 year ago

[Bugfix][Build][Non-CUDA] Only referencing CMAKE_CUDA_COMPILER_VERSION on CUDA where it is defined (#20738)

Gregory Shtrasberg committed over 1 year ago

[CI/Build] Fix Basic Models Test (#20728)

Jee Jee Li committed over 1 year ago

[Misc] loose new-model tagger conditions (#20747)

Isotr0py committed over 1 year ago

[KVConnector] Aggregate finished requests on the scheduler (#19555)

Or Ozeri committed over 1 year ago

[TPU][Core]Make load weight exceed hbm error more instructive for customers (#20644)

Chenyaaang committed over 1 year ago

[BugFix] Fix `VllmConfig()` construction on all platforms (#20695)

Nick Hill committed over 1 year ago