[Fix] Turn off DeepGEMM by default (#5263)

2025-04-14 17:45:44 -07:00
parent ac5b78baf6
commit f6772f1497
2 changed files with 6 additions and 2 deletions
--- a/python/sglang/srt/layers/quantization/fp8_kernel.py
+++ b/python/sglang/srt/layers/quantization/fp8_kernel.py
@@ -45,7 +45,9 @@ if _is_cuda:
    from sgl_kernel import sgl_per_token_group_quant_fp8, sgl_per_token_quant_fp8

    sm_version = get_device_sm()
-    if sm_version == 90 and get_bool_env_var("SGL_ENABLE_JIT_DEEPGEMM", default="true"):
+    if sm_version == 90 and get_bool_env_var(
+        "SGL_ENABLE_JIT_DEEPGEMM", default="false"
+    ):
        _enable_jit_deepgemm = True