Support compressed tensors fp8w8a8 (#4743)

2025-03-27 04:21:25 +08:00
parent 45fdf1f7f3
commit 04e3ff6975
30 changed files with 2386 additions and 113 deletions
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -47,7 +47,6 @@ srt = [
    "sgl-kernel==0.0.5.post3",
    "flashinfer_python==0.2.3",
    "torch==2.5.1",
-    "vllm>=0.6.4.post1,<=0.7.2",
    "cuda-python",
    "outlines>=0.0.44,<=0.1.11",
 ]