Support new DeepGEMM format in per token group quant (part 2: srt) (#7155)

2025-06-14 05:25:40 +08:00
parent 8ab7d93c2e
commit bec3e48402
3 changed files with 19 additions and 4 deletions
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -49,7 +49,7 @@ runtime_common = [

 srt = [
    "sglang[runtime_common]",
-    "sgl-kernel==0.1.7",
+    "sgl-kernel==0.1.8.post1",
    "flashinfer_python==0.2.6.post1",
    "torch==2.7.1",
    "torchaudio==2.7.1",