[V1] Allow turning off pickle fallback in vllm.v1.serial_utils (#17427)

Russell Bryant committed over 1 year ago

[Bugfix] Fixed mistral tokenizer path when pointing to file (#17457)

Pete Savage committed over 1 year ago

[Fix] Support passing args to logger (#17425)

Aaron Pham committed over 1 year ago

[Docs] Add command for running mypy tests from CI (#17475)

Russell Bryant committed over 1 year ago

[Feature] The Qwen3 reasoning parser supports guided decoding (#17466)

Chauncey committed over 1 year ago

[V1][Metrics] add support for kv event publishing (#16750)

Alec committed over 1 year ago

[Core] Prevent side-channel attacks via cache salting (#17045)

Marko Rosenmueller committed over 1 year ago

[TPU][V1][CI] Update regression test baseline for v6 CI (#17064)

Nicolò Lucchesi committed over 1 year ago

[V1][Bugfix]: vllm v1 verison metric num_gpu_blocks is None (#15755)

rongfu.leng committed over 1 year ago

[Misc] Remove deprecated files (#17447)

Chauncey committed over 1 year ago

Make the _apply_rotary_emb compatible with dynamo (#17435)

Lu Fang committed over 1 year ago

[MODEL ADDITION] Ovis2 Model Addition (#15826)

Marco committed over 1 year ago

[Bugfix] Fix AttributeError: 'State' object has no attribute 'engine_client' (#17434)

Chauncey committed over 1 year ago

[Hardware][Intel GPU] Upgrade to torch 2.7 (#17444)

Kunshang Ji committed over 1 year ago

[Intel GPU] [CI]Fix XPU ci, setuptools >=80.0 have build issue (#17298)

Kunshang Ji committed over 1 year ago

Support LoRA for Mistral3 (#17428)

Michael Goin committed over 1 year ago

Fix some speculative decode tests with tl.dot (#17371)

Huy Do committed over 1 year ago

Fix call to `logger.info_once` (#17416)

Harry Mellor committed over 1 year ago

Improve configs - `ModelConfig` (#17130)

Harry Mellor committed over 1 year ago

Update PyTorch to 2.7.0 (#16859)

Huy Do committed over 1 year ago