[gpt-oss] Convert user input to harmony format (#22402)

Chen Zhang committed over 1 year ago

preload heavy modules when mp method is forkserver (#22214)

Lionel Villard committed over 1 year ago

Optimize logger init performance by using module-level constants (#22373)

ZiTian.Zhao committed over 1 year ago

Update `hf_xet` pin to resolve hangs (#22356)

Harry Mellor committed over 1 year ago

[Bugfix] Add proper comparison for package versions (#22314)

Syed Muhammad Bin Asif committed over 1 year ago

[Bugfix]: Fix the streaming output for function calls in the minimax (#22015)

qscqesze committed over 1 year ago

Use float32 for test_completion.py (#22385)

Michael Goin committed over 1 year ago

[Bugfix] Fix wrong method name in Intern-S1 image processor (#22417)

Cyrus Leung committed over 1 year ago

[Qwen3] Enable dual-chunk-attention support for Qwen3 models. (#21924)

Tao He committed over 1 year ago

[XPU]Fix `flash_attn_varlen_func` interface on xpu (#22350)

Kunshang Ji committed over 1 year ago

[Attention] Support multiple attention metadata builders per kv_cache_spec + proper local attention no hybrid kv cache fix (#21588)

Lucas Wilkinson committed over 1 year ago

Support encoder_only attention for FlexAttention (#22273)

Maximilien de Bayser committed over 1 year ago

[model] Support MiniCPM-V 4.0 (#22166)

tc-mb committed over 1 year ago

Update `flashinfer-python==0.2.10` (#22389)

Michael Goin committed over 1 year ago

Fix trtllm-gen attention env and add attention sink (#22378)

Lain committed over 1 year ago

[gpt-oss] fix model config with hf_config (#22401)

Yongye Zhu committed over 1 year ago

[gpt-oss] add demo tool server (#22393)

Chen Zhang committed over 1 year ago

[Bug] Fix B200 DeepGEMM E8M0 Accuracy Issue (#22399)

Wentao Ye committed over 1 year ago

[v1] - Mamba1 Attention Metadata (#21249)

Asaf Joseph Gardin committed over 1 year ago

[gpt-oss] flashinfer mxfp4 (#22339)

Yongye Zhu committed over 1 year ago