Wentao Ye 42d440c22b [Perf] Use Triton instead of Torch for DeepGEMM Per Token Group Quant (#20841) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2025-07-12 19:38:45 -07:00

..

__init__.py

[Model] New model support for microsoft/Phi-4-mini-flash-reasoning (#20702)

2025-07-12 06:02:10 -07:00

deep_gemm.py

[Perf] Use Triton instead of Torch for DeepGEMM Per Token Group Quant (#20841)

2025-07-12 19:38:45 -07:00