feat: Support MXFP4 quantized dense models on AMD CDNA2/CDNA3 GPUs (#19143)

2026-04-16 16:51:32 -07:00
parent f639425ff0
commit 2cc52d8326
8 changed files with 648 additions and 282 deletions
@@ -93,7 +93,7 @@ tracing = [
 srt_hip = [
  "sglang[runtime_common]",
  "torch",
-  "petit_kernel==0.0.2",
+  "petit_kernel==0.0.3",
  "wave-lang==3.8.2",
 ]