chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[kimi k2 thinking] Avoid useless torch.zeros_ (#13596)

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
Xiaoyu Zhang
2025-11-21 13:15:27 +08:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> github-actions[bot] <github-actions[bot]@users.noreply.github.com>
parent 6be65ae462
commit fb04d43428
7 changed files with 252 additions and 256 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/test/test_marlin_moe.py
+1 -1
View File
@@ -2,10 +2,10 @@ from typing import Optional
import pytest
import torch
from sgl_kernel import fused_marlin_moe
from sgl_kernel.scalar_type import ScalarType, scalar_types
from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.moe.fused_moe_triton.fused_marlin_moe import fused_marlin_moe
from sglang.srt.server_args import ServerArgs, set_global_server_args_for_scheduler
from sglang.test.test_marlin_utils import awq_marlin_quantize, marlin_quantize