integrate blockwise fp8 kernel (#3529)

2025-02-13 04:39:33 +08:00
parent 4430c0a513
commit 98eecbda54
3 changed files with 124 additions and 23 deletions
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -25,7 +25,7 @@ runtime_common = [
 ]
 srt = [
    "sglang[runtime_common]", "cuda-python",
-    "sgl-kernel>=0.0.3.post4", "torch", "vllm>=0.6.4.post1,<=0.7.2",
+    "sgl-kernel>=0.0.3.post5", "torch", "vllm>=0.6.4.post1,<=0.7.2",
    "flashinfer_python>=0.2.0.post2", "outlines>=0.0.44,<=0.1.11"
 ]