vllm/model_executor/layers/quantization/fp8.py · 31d5c1797f320b2f407c893673330b3a8766ae47 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf (#19830) · 31d5c179
Luka Govedič authored Jul 11, 2025
```
Signed-off-by: Luka Govedic <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
31d5c179

fp8.py 45.4 KB