[Build] Fix release pipeline failing annotation (#28272)

Simon Mo committed about 1 year ago

[doc] add guide about the provided PTX was compiled with an unsupported toolchain (#28305)

youkaichao committed about 1 year ago

[README] Add Arm CPUs to the list of supported targets (#28290)

Fadi Arafeh committed about 1 year ago

Revert "[PerfFix] Avoid separate thread for MP executor shm spin (#28012)" (#28289)

Nicolò Lucchesi committed about 1 year ago

[Log] update shm wait time msg (#28255)

Boyuan Feng committed about 1 year ago

[Feature] Default `ignore_eos` True for `random` dataset (#28227)

Wentao Ye committed about 1 year ago

[CLI] add --max-tokens to `vllm complete` (#28109)

Iceber Gu committed about 1 year ago

[Bugfix] Use latency MOE backend as default for Flashinfer and other misc fixes (#27439)

Pavani Majety committed about 1 year ago

[Core][MM] Add mechanism to configure multimodal fields which should stay on CPU (#28168)

Lukas Geiger committed about 1 year ago

[fix] Revert "fixing mm placeholder replacement issue with gemma3" (#28285)

Kevin H. Luu committed about 1 year ago

[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)

Mengqing Cao committed about 1 year ago

[CPU]Avoid repeated random sample compile (#28260)

Zhang Xiangze committed about 1 year ago

[FixBug]Aeala/ShareGPT_Vicuna_unfiltered marked as multimodal benchmark (#28265)

汪志鹏 committed about 1 year ago

[Perf] Introduce FlattenLogprobs to store logprobs results to reduce GC overhead (#28171)

Jialin Ouyang committed about 1 year ago

[Kernel] LoRA triton kernels support PDL (#27402)

Jee Jee Li committed about 1 year ago

[CI] Reduce Blackwell Fusion test runtime by filtering tests and only run all tests in nightly (#28074)

Copilot committed about 1 year ago

[Bug] Fix missing token_ids for reasoning parser models in chat completions #28246 (#28256)

baonudesifeizhai committed about 1 year ago

[amd][gptoss] Perf gain because of block alignment (#28024)

smit kadvani committed about 1 year ago

Fix issues from #28242 (#28257)

Harry Mellor committed about 1 year ago

Add runai model streamer e2e test for GCS (#28079)

Alexis MacAskill committed about 1 year ago