FP4 weight loading and inference (2/2) (#3972)

2025-04-08 17:26:21 -07:00
parent 5039d54772
commit 11d760d56a
6 changed files with 262 additions and 1 deletions
--- a/python/sglang/srt/layers/linear.py
+++ b/python/sglang/srt/layers/linear.py
@@ -47,6 +47,7 @@ WEIGHT_LOADER_V2_SUPPORTED = [
    "GPTQLinearMethod",
    "FBGEMMFp8LinearMethod",
    "ModelOptFp8LinearMethod",
+    "ModelOptFp4LinearMethod",
    "IPEXAWQLinearMethod",
 ]