fix SUPPORT_CUTLASS_BLOCK_FP8 flag (#4640)

7b5fc719 · Cheng Wan · GitHub · ad4e58bf · 7b5fc719
Unverified Commit 7b5fc719 authored Mar 21, 2025 by Cheng Wan Committed by GitHub Mar 20, 2025
Show whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

python/sglang/srt/layers/quantization/fp8_utils.py python/sglang/srt/layers/quantization/fp8_utils.py +1 -1

No files found.
--- a/python/sglang/srt/layers/quantization/fp8_utils.py
+++ b/python/sglang/srt/layers/quantization/fp8_utils.py
@@ -82,7 +82,7 @@ def normalize_e4m3fn_to_e4m3fnuz(


 def cutlass_block_fp8_supported() -> bool:
-    if get_bool_env_var("SUPPORT_CUTLASS_BLOCK_FP8"):
+    if not get_bool_env_var("SUPPORT_CUTLASS_BLOCK_FP8"):
        return False
    if _is_cuda:
        major, minor = torch.cuda.get_device_capability()