fix: fix typo of comments in w8a8_fp8.py (#4843)

2025-03-28 12:06:47 +08:00
parent 9fdc6d6abc
commit 72031173e4
1 changed files with 1 additions and 1 deletions
--- a/python/sglang/srt/layers/quantization/w8a8_fp8.py
+++ b/python/sglang/srt/layers/quantization/w8a8_fp8.py
@@ -37,7 +37,7 @@ class W8A8Fp8Config(QuantizationConfig):
    Note:
    - For models without offline quantization, weights will be quantized during model loading
    - If CUTLASS is supported: Per-channel weight quantization is used
-    - If CUTLASS is not supported: Falls back to per-token weight quantization
+    - If CUTLASS is not supported: Falls back to per-tensor weight quantization
    """

    def __init__(self, is_checkpoint_fp8_serialized: bool = False):