vllm/model_executor/layers/quantization/fp8.py · 6a7988c55bb0a54240f479033313eb98344e6431 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

Refactor pplx init logic to make it modular (prepare for deepep) (#18200) · 6a7988c5
youkaichao authored May 23, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
6a7988c5

fp8.py 41.4 KB