Add support for ModelOpt MXFP8 dense models (#33786)

Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
2026-02-08 21:16:48 +02:00
parent 1ecfabe525
commit 084aa19f02
6 changed files with 375 additions and 14 deletions
--- a/vllm/config/model.py
+++ b/vllm/config/model.py
@@ -878,6 +878,7 @@ class ModelConfig:
                "moe_wna16",
                "modelopt",
                "modelopt_fp4",
+                "modelopt_mxfp8",
                "petit_nvfp4",
                # Ensure heavy backends are probed last to avoid unnecessary
                # imports during override detection (e.g., MXFP4 imports Triton)