vllm/model_executor/layers/quantization/fp8.py · 418d2f8bfb5593bce89641d79849900f7294b859 · OpenDAS / vllm_cscc

TJian authored May 14, 2025


Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>

612c2edb

fp8.py 40.6 KB