[V1] Refactor parallel sampling support (#13774)

Mark McLoughlin committed over 1 year ago

[Build] Make sure local main branch is synced when VLLM_USE_PRECOMPILED=1 (#13921)

Cody Yu committed over 1 year ago

[Misc][Platform] Move use allgather to platform (#14010)

Mengqing Cao committed over 1 year ago

[Misc] duplicate code in deepseek_v2 (#14106)

wang.yuqi committed over 1 year ago

[Bugfix] Explicitly include "omp.h" for MacOS to avoid installation failure (#14051)

Sheng Yao committed over 1 year ago

Update deprecated Python 3.8 typing (#13971)

Harry Mellor committed over 1 year ago

[v0][structured output] Support reasoning output (#12955)

Ce Gao committed over 1 year ago

[Doc] Source building add clone step (#14086)

qux-bbb committed over 1 year ago

[Misc] Accurately capture the time of loading weights (#14063)

Jun Duan committed over 1 year ago

[Model] Add LoRA support for TransformersModel (#13770)

Jee Jee Li committed over 1 year ago

[v1] Add `__repr__` to KVCacheBlock to avoid recursive print (#14081)

Chen Zhang committed over 1 year ago

[v1][Bugfix] Only cache blocks that are not in the prefix cache (#14073)

Chen Zhang committed over 1 year ago

[ROCm][V1][Bugfix] Add get_builder_cls method to the ROCmAttentionBackend class (#14065)

Sage Moore committed over 1 year ago

[V1][Minor] Do not print attn backend twice (#13985)

Woosuk Kwon committed over 1 year ago

[Doc] Consolidate `whisper` and `florence2` examples (#14050)

Isotr0py committed over 1 year ago

[Documentation] Add more deployment guide for Kubernetes deployment (#13841)

Kuntai Du committed over 1 year ago

[Bugfix][V1][Minor] Fix shutting_down flag checking in V1 MultiprocExecutor (#14053)

Li, Jiang committed over 1 year ago

[Misc][Kernel]: Add GPTQAllSpark Quantization (#12931)

YajieWang committed over 1 year ago

[Bugfix] Add file lock for ModelScope download (#14060)

Jee Jee Li committed over 1 year ago

[Docs] Add `pipeline_parallel_size` to optimization docs (#14059)

Brayden Zhong committed over 1 year ago