[Benchmark] Add sampling parameters to benchmark_serving. (#16022)

Hyesoo Yang committed over 1 year ago

[Model] fix model testing for TeleChat2ForCausalLM and V0 llama4 (#16112)

Lucia Fang committed over 1 year ago

[Model] use AutoWeightsLoader for phi, gemma, deepseek (#16088)

Jonghyun Choe committed over 1 year ago

[Bugfix] fix use_atomic_add support of marlin kernel when using v1 engine (#15946)

Jinzhen Lin committed over 1 year ago

[Misc] Remove redundant code (#16098)

Chauncey committed over 1 year ago

[Misc] format output for encoder_decoder.py (#16095)

Reid committed over 1 year ago

Fix some capitalisations in generated examples doc titles (#16094)

Harry Mellor committed over 1 year ago

Revert "doc: add info for macos clang errors (#16049)" (#16091)

yihong committed over 1 year ago

[doc] fix 404 (#16082)

Reid committed over 1 year ago

fix: support clang17 for macos and fix the real libomp (#16086)

yihong committed over 1 year ago

[CI] Fix benchmark script level (#16089)

Kevin H. Luu committed over 1 year ago

[Misc] Auto detect bitsandbytes pre-quantized models (#16027)

Tristan Leclercq committed over 1 year ago

[V1][Spec Decode] Update N-gram Proposer Interface (#15750)

Woosuk Kwon committed over 1 year ago

[Bugfix][TPU] Fix V1 TPU worker for sliding window (#16059)

Michael Goin committed over 1 year ago

[Kernel][Minor] Re-fuse triton moe weight application (#16071)

bnellnm committed over 1 year ago

Revert "[V1] Scatter and gather placeholders in the model runner" (#16075)

Roger Wang committed over 1 year ago

[V1] Scatter and gather placeholders in the model runner (#15712)

Cyrus Leung committed over 1 year ago

[V1] DP scale-out (1/N): Use zmq ROUTER/DEALER sockets for input queue (#15906)

Nick Hill committed over 1 year ago

[CI] Reorganize .buildkite directory (#16001)

Kevin H. Luu committed over 1 year ago

[Bugfix] Fix default behavior/fallback for pp in v1 (#16057)

Michael Goin committed over 1 year ago