[gpt-oss] Enhance error msg on attention sink init (#22335)

Yongye Zhu committed over 1 year ago

[gpt-oss] Add loop for built-in tool call (#22374)

Woosuk Kwon committed over 1 year ago

[Bugfix] Make condition in triton kernel constexpr (#22370)

Gregory Shtrasberg committed over 1 year ago

[BugFix] Fix triton compile error in `kernel_unified_attention_2/3d` caused by attention sinks (#22368)

Lucas Wilkinson committed over 1 year ago

add the codes to check AMD Instinct GPU number (#22367)

Zhang Jason committed over 1 year ago

[BugFix] Fix FA2 RuntimeError when sinks is provided (#22365)

Lucas Wilkinson committed over 1 year ago

[Minor] Fix type (#22347)

Woosuk Kwon committed over 1 year ago

[gpt-oss] Support chat completion api (#22342)

Woosuk Kwon committed over 1 year ago

[gpt-oss] add model to supported models doc (#22336)

Roger Wang committed over 1 year ago

[gpt-oss] Add Tool/ConversationContext classes and harmony_utils (#22340)

Woosuk Kwon committed over 1 year ago

[Misc] Clean up duplicated hf overrides (#22311)

Isotr0py committed over 1 year ago

[gpt-oss] Add openai-harmony as default dependency (#22332)

Woosuk Kwon committed over 1 year ago

[gpt-oss] flashinfer attention sink init (#22330)

Yongye Zhu committed over 1 year ago

[GptOss] Add GptOss reasoning parser to support structure output (#22322)

Chen Zhang committed over 1 year ago

[ROCm] Add attention sink to use_rocm_custom_paged_attention (#22329)

Woosuk Kwon committed over 1 year ago

Add GPT-OSS model code and config [1/N] (#22327)

Woosuk Kwon committed over 1 year ago

Update transformers to `v4.55` (#21931)

Harry Mellor committed over 1 year ago

Add attention sink in attention backends (#22320)

Woosuk Kwon committed over 1 year ago

Increase openai-python version (#22316)

Woosuk Kwon committed over 1 year ago

Upgrade FA3 for attention sink (#22313)

Woosuk Kwon committed over 1 year ago