[V1][Core] Remove unused speculative config from scheduler (#15818)

Mark McLoughlin committed over 1 year ago

Fix Transformers backend compatibility check (#15290)

Harry Mellor committed over 1 year ago

[V1] TPU CI - Add basic perf regression test (#15414)

Alexander Matveev committed over 1 year ago

fix: change GB to GiB in logging close #14979 (#15807)

yihong committed over 1 year ago

[V1][Spec Decode] Remove deprecated spec decode config params (#15466)

shangmingc committed over 1 year ago

[Bugfix] Check dimensions of multimodal embeddings in V1 (#15816)

Cyrus Leung committed over 1 year ago

Upgrade `transformers` to `v4.50.3` (#13905)

Harry Mellor committed over 1 year ago

[Bugfix] Fix missing return value in load_weights method of adapters.py (#15542)

Mrm committed over 1 year ago

[Bugfix] Fix Crashing When Loading Modules With Batchnorm Stats (#15813)

Alex Brooks committed over 1 year ago

[Model] Update support for NemotronNAS models (#15008)

Naveassaf committed over 1 year ago

[V1] Fully Transparent Implementation of CPU Offloading (#15354)

youkaichao committed over 1 year ago

fix: better install requirement for install in setup.py (#15796)

yihong committed over 1 year ago

Recommend developing with Python 3.12 in developer guide (#15811)

Harry Mellor committed over 1 year ago

[Feature][ROCm]Enable fusion pass for torch.compile on ROCm (#15050)

Charlie Fu committed over 1 year ago

[Benchmark] Update Vision Arena Dataset and HuggingFaceDataset Setup (#15748)

Jennifer Zhao committed over 1 year ago

[Misc] update the comments (#15780)

Chengyang LIU committed over 1 year ago

[V1][Scheduler] Avoid calling `_try_schedule_encoder_inputs` for every request (#15778)

Woosuk Kwon committed over 1 year ago

fix: Comments to English for better dev experience (#15768)

yihong committed over 1 year ago

[Bugfix] Added `embed_is_patch` mask for fuyu model (#15731)

kYLe committed over 1 year ago

fix: lint fix a ruff checkout syntax error (#15767)

yihong committed over 1 year ago