[Core] Remove legacy input mapper/processor from V0 (#15686)

Cyrus Leung committed over 1 year ago

[Minor][Models] Pass partial_rotary_factor parameter to rope (#17266)

Wanrui Dai committed over 1 year ago

[Misc] Validate `stop_token_ids` contents (#17268)

Nick Hill committed over 1 year ago

[Doc] small fix (#17277)

Reid committed over 1 year ago

[Doc] Fix wrong github link in LMCache examples (#17274)

Kuntai Du committed over 1 year ago

[Bugfix] Fix Mistral3 spatial merge error (#17270)

Michael Goin committed over 1 year ago

[Bugfix] Fix cutlass dispatch for fp8/int8 to properly invoke M<=16 c… (#16751)

TherLF committed over 1 year ago

[Bugfix] Fix missing ARG in Dockerfile for arm64 platforms (#17261)

Lennart K. M. Schulz committed over 1 year ago

[BugFix] Fix vllm_flash_attn install issues (#17267)

Lucas Wilkinson committed over 1 year ago

[V1][Spec Decode] Make eagle compatible with prefix caching. (#17137)

Lily Liu committed over 1 year ago

[Metrics] Fix minor inconsistencies in bucket progression (#17262)

Cyrus Leung committed over 1 year ago

[doc] Add feature status legend (#17257)

Reid committed over 1 year ago

[Feature] support sequence parallelism using compilation pass (#16155)

cascade committed over 1 year ago

[NVIDIA] Support Cutlass MLA for Blackwell GPUs (#16032)

Kaixi Hou committed over 1 year ago

[Bugfix] Fix Lora Name Parsing (#17196)

Alex Brooks committed over 1 year ago

[Misc] Change buckets of histogram_iteration_tokens to [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8096] to represent number of tokens (#17033)

Flex Wang committed over 1 year ago

[MISC] Use string annotation types for class definitions (#17244)

Jade Zheng committed over 1 year ago

[Bugfix] Get a specific type of layer from forward context (#17222)

Chen Zhang committed over 1 year ago

[Bugfix] Fix QWen2 VL multimodal mapping (#17240)

Jee Jee Li committed over 1 year ago

[Misc] Make cached tokenizer pickle-compatible (#17048)

Cyrus Leung committed over 1 year ago