Aiter mha fp8 fix (#24991)

Douglas Lehr committed about 1 year ago

[Bugfix][B200] Fix `cutlass_mla` hang (#24966)

Alexander Matveev committed about 1 year ago

[gpt-oss][2] fix types for streaming (#24556)

Andrew Xia committed about 1 year ago

[Kernel] Faster pre-processing time for W4A8 (#23972)

czhu-cohere committed about 1 year ago

[BUG] Exclude .pth files when pulling remote files (#25092)

ahao-anyscale committed about 1 year ago

[Bugfix] Update import path for bc_linter_include (#24766)

Mohammad Miadh Angkad committed about 1 year ago

[Misc] Update owners for KV connector and V1 offloading (#25041)

Yihua Cheng committed about 1 year ago

[V1] Logits processor docs (#22919)

afeldman-nm committed about 1 year ago

[CI Bugfix] Fix failing test_model_load_with_params tests due to tokenizer refactor (#25086)

Michael Goin committed about 1 year ago

[V0 Deprecation] Remove V0 tests in test_sequence.py (#25088)

Woosuk Kwon committed about 1 year ago

[CI] Revert back prepare_prompts and check_answers (#25087)

Woosuk Kwon committed about 1 year ago

Change log level from info to debug for IOProcessor (#24999)

Michael Goin committed about 1 year ago

[V0 Deprecation] Remove unused output processor util (#25023)

Woosuk Kwon committed about 1 year ago

Remove unused find_cuda_init helper script (#25044)

Simon Mo committed about 1 year ago

cleanup: remove adapter commons (#25045)

Simon Mo committed about 1 year ago

[V0 Deprecation] Remove V0 Core tests (#25082)

Woosuk Kwon committed about 1 year ago

[CI Bugfix] Fix failing test_invalid_env (#25078)

Michael Goin committed about 1 year ago

[Docs] vllm/benchmarks/datasets.py fix docstring param format. (#24970)

samzong committed about 1 year ago

Remove old cutlass mla (#23961)

Matthew Bonanni committed about 1 year ago

[Docs] improve code formatting and comments for eliminate griffe build warning. (#25010)

samzong committed about 1 year ago