minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

refactor(moe): de-duplicate triton MoE runner path into shared helpers (#23019)

Browse Source 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Cheng Wan
2026-04-17 17:05:13 -07:00
committed by GitHub
co-authored by Claude Opus 4.7
parent fd7db0eace
commit 5f7aee726a
322 changed files with 589 additions and 704 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/quant/test_block_int8.py
+1 -1
View File
@@ -4,7 +4,7 @@ import unittest
import torch
from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.moe.fused_moe_triton.fused_moe import fused_moe
from sglang.srt.layers.moe.moe_runner.triton_utils.fused_moe import fused_moe
from sglang.srt.layers.moe.topk import TopKConfig, select_experts
from sglang.srt.server_args import ServerArgs, set_global_server_args_for_scheduler
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
test/registered/quant/test_int8_kernel.py
+1 -1
View File
@@ -4,7 +4,7 @@ import unittest
import torch
from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.moe.fused_moe_triton.fused_moe import fused_moe
from sglang.srt.layers.moe.moe_runner.triton_utils.fused_moe import fused_moe
from sglang.srt.layers.moe.topk import TopKConfig, select_experts
from sglang.srt.layers.quantization.int8_kernel import per_token_quant_int8
from sglang.srt.server_args import ServerArgs, set_global_server_args_for_scheduler