chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Revert "fix some typos" (#6244)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-05-12 12:53:26 -07:00
committed by GitHub
parent bad7c26fdc
commit e8e18dcdcc
95 changed files with 276 additions and 276 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/sglang/srt/layers/quantization/fp8_utils.py
View File

@@ -357,7 +357,7 @@ def apply_fp8_linear(
# Fused GEMM_DQ
if VLLM_AVAILABLE and use_vllm_cutlass_w8a8_fp8_kernel:
# Fall back to vLLM cutlass w8a8 fp8 kernel
# Fall back to vllm cutlass w8a8 fp8 kernel
output = ops.cutlass_scaled_mm(
qinput,
weight,
@@ -493,7 +493,7 @@ def apply_fp8_linear(
if cutlass_fp8_supported:
try:
if VLLM_AVAILABLE and use_vllm_cutlass_w8a8_fp8_kernel:
# Fall back to vLLM cutlass w8a8 fp8 kernel
# Fall back to vllm cutlass w8a8 fp8 kernel
output = ops.cutlass_scaled_mm(
qinput,
weight,