vllm/model_executor/layers/quantization/fp8.py · ab9f2cfd1942f7ddfee658ce86ea96b4789862af · OpenDAS / vllm_cscc · GitLab

"benchmarks/benchmark_latency.py" did not exist on "c45f3c3ab60f4bf4eaab791a76028b8b07ffe9bd"

Find file Blame History Permalink

[Feature] Add `VLLM_USE_DEEP_GEMM_E8M0` Env to Control E8M0 Scale (#21968) · f7dcce7a
Wentao Ye authored Aug 11, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
f7dcce7a

fp8.py 48.8 KB