vllm/model_executor/layers/quantization/fp8.py · 2e9034c998e231634a75ab74c5812e0dba2cf3a1 · OpenDAS / vllm_cscc

[W8A8 Block Linear Refactor][2/N] Remove W8A8Fp8BlockLinearOp and adopt Fp8... · 2e9034c9

Maral authored Apr 09, 2026


[W8A8 Block Linear Refactor][2/N] Remove W8A8Fp8BlockLinearOp and adopt Fp8 block linear kernel selections. (#33892)
Signed-off-by: maral <maralbahari.98@gmail.com>
Signed-off-by: Maral <maralbahari.98@gmail.com>

2e9034c9

fp8.py 39.8 KB

Replace fp8.py