[Misc] remove unused jinaai_serving_reranking (#18878)

Abirdcfly committed over 1 year ago

[Docs] Clean up tables in supported_models.md (#20552)

Michael Yao committed over 1 year ago

[XPU] log clean up for XPU platform (#20553)

Yan Ma committed over 1 year ago

Add docstrings to url_schemes.py to improve readability (#20545)

Michael Yao committed over 1 year ago

[XPU][CI] add v1/core test in xpu hardware ci (#20537)

Liangliang Ma committed over 1 year ago

[CI/Build] Enable phi2 lora test (#20540)

Jee Jee Li committed over 1 year ago

[Refactor]Abstract Platform Interface for Distributed Backend and Add xccl Support for Intel XPU (#19410)

Yang Yang committed over 1 year ago

[Misc] add a tip for pre-commit (#20536)

Reid committed over 1 year ago

Implement OpenAI Responses API [1/N] (#20504)

Woosuk Kwon committed over 1 year ago

[Bugfix] Add `use_cross_encoder` flag to use correct activation in `ClassifierPooler` (#20527)

Cyrus Leung committed over 1 year ago

[BugFix][Spec Decode] Fix spec token ids in model runner (#20530)

Woosuk Kwon committed over 1 year ago

[V1] Support any head size for FlexAttention backend (#20467)

Cyrus Leung committed over 1 year ago

[V0 deprecation] Remove V0 CPU/XPU/TPU backends (#20412)

Woosuk Kwon committed over 1 year ago

[Misc] call the pre-defined func (#20518)

Reid committed over 1 year ago

[Benchmark] Add support for multiple batch size benchmark through CLI in `benchmark_moe.py` (#20516)

Brayden Zhong committed over 1 year ago

[Frontend] Support image object in llm.chat (#19635)

Flora Feng committed over 1 year ago

[TPU][Bugfix] fix the MoE OOM issue (#20339)

Chengji Yao committed over 1 year ago

[BugFix] Fix: ImportError when building on hopper systems (#20513)

Lucas Wilkinson committed over 1 year ago

[Bugfix] Fix missing per_act_token parameter in compressed_tensors_moe (#20509)

Lucia Fang committed over 1 year ago

[BUG] Fix #20484. Support empty sequence in cuda penalty kernel (#20491)

Vadim Gimpelson committed over 1 year ago