[Neuron] trim attention kernel tests to fit trn1.2x instance (#14988)

Liangfu Chen committed over 1 year ago

[Bugfix] Fix bnb quantization for models with both HF-format and Mistral-format weights (#14950)

Tristan Leclercq committed over 1 year ago

[V1] TPU - Fix CI/CD runner (#14974)

Alexander Matveev committed over 1 year ago

[V1] Guard Against Main Thread Usage (#14972)

Robert Shaw committed over 1 year ago

[CI/Build] Use `AutoModelForImageTextToText` to load VLMs in tests (#14945)

Cyrus Leung committed over 1 year ago

[Bugfix] Fix interface for Olmo2 on V1 (#14976)

Roger Wang committed over 1 year ago

[Bugfix] Make Gemma3 MM V0 only for now (#14971)

Roger Wang committed over 1 year ago

[Fix][Structured Output] using vocab_size to construct matcher (#14868)

Aaron Pham committed over 1 year ago

[Bugfix][Model] Mixtral: use unused head_dim config argument (#14961)

Quentin committed over 1 year ago

[Bugfix] Fix precommit - line too long in pixtral.py (#14960)

Tyler Michael Smith committed over 1 year ago

[V1] Default MLA to V1 (#14921)

Simon Mo committed over 1 year ago

Add patch merger (#14957)

Patrick von Platen committed over 1 year ago

[Doc] Fix misleading log during multi-modal profiling (#14955)

Cyrus Leung committed over 1 year ago

[Bugfix][ROCm] running new process using spawn method for rocm in tests. (#14810)

vllmellm committed over 1 year ago

[Misc] Add `--seed` option to offline multi-modal examples (#14934)

Cyrus Leung committed over 1 year ago

[Bugfix] Fix Ultravox on V1 (#14929)

Cyrus Leung committed over 1 year ago

[V1][TPU] Apply the ragged paged attention kernel fix and remove the padding. (#14846)

iefgnoix committed over 1 year ago

fix minor miscalled method (#14327)

kushanam committed over 1 year ago

[MISC] More AMD unused var clean up (#14926)

Lu Fang committed over 1 year ago

setup.py: drop assumption about local `main` branch (#14692)

Russell Bryant committed over 1 year ago