From 7b5fc71972981eb279a64079bdfe2f01be89370f Mon Sep 17 00:00:00 2001 From: Cheng Wan <54331508+ch-wan@users.noreply.github.com> Date: Fri, 21 Mar 2025 00:45:07 -0400 Subject: [PATCH] fix SUPPORT_CUTLASS_BLOCK_FP8 flag (#4640) --- python/sglang/srt/layers/quantization/fp8_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/sglang/srt/layers/quantization/fp8_utils.py b/python/sglang/srt/layers/quantization/fp8_utils.py index 4b790d3ba..b1a2034b9 100644 --- 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()