[Bugfix]: Qwen3 Coder Tool Parser (#23099)

Yiheng Xu committed about 1 year ago

[Bugfix][gpt-oss] passing the cache config in gpt-oss (#23613)

Wei committed about 1 year ago

[Docs] Fix math rendering in docs (#23676)

Harry Mellor committed about 1 year ago

[Bugfix] Lazy import gpt_oss_triton_kernels_moe for mxfp4 (#23678)

Michael Goin committed about 1 year ago

[gpt-oss] Enable unit test for response API harmony integration (#23533)

Chen Zhang committed about 1 year ago

[quantization] use channel scales for w4a8 + misc fixes (#23570)

czhu-cohere committed about 1 year ago

fix pynccl reduce_scatter (#23648)

yzds committed about 1 year ago

[Feature][Responses API] Support MCP tool in background mode (#23494)

wuhang committed about 1 year ago

feat: add triton fused moe config for GLM-4.5-Air-FP8 on B200 (#23695)

zixuanzhang226 committed about 1 year ago

[Bugfix] UnboundLocalError when GptOss reasoning specified (#23054)

Federico committed about 1 year ago

[Compile] Fix Cmake Warning (#23689)

Wentao Ye committed about 1 year ago

[V1] [Hybrid] Enable Full CUDA graph by default for hybrid models in V1 (#22594)

Thomas Parnell committed about 1 year ago

[V1][P/D]P2pNcclConnector supports flashinfer (#23536)

Zhonghua Deng committed about 1 year ago

[Docs] Move quant supported hardware table to README (#23663)

Harry Mellor committed about 1 year ago

Enhance the pre-notification policy (#23532)

Huzaifa Sidhpurwala committed about 1 year ago

[doc] Hybrid KV Cache Manager design doc (#22688)

Chen Zhang committed about 1 year ago

[Model] Enable video support for InternVL3.5 models (#23658)

Isotr0py committed about 1 year ago

[Misc] Fix comments in `tests/kernels/quantization` (#23675)

Jiangyun Zhu committed about 1 year ago

[Bugfix] Fix incorrect original shape in hashing (#23672)

Cyrus Leung committed about 1 year ago

[v1] Add cross-attention KV cache support for encoder-decoder models (#23664)

Russell Bryant committed about 1 year ago