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

[NPU]Optimize the PR pipeline to reduce E2E runtime (#18767)

Browse Source 
Co-authored-by: Sugar920 <121632458+Sugar920@users.noreply.github.com>
This commit is contained in:
Cherry_ming
2026-02-28 17:06:03 +08:00
committed by GitHub
co-authored by Sugar920
parent 366574b2b8
commit 1eb40d8d45
12 changed files with 17 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/srt/run_suite.py
+2 -3
View File
@@ -99,15 +99,14 @@ suite_ascend = {
TestFile("ascend/test_ascend_tp2_bf16.py", 400),
TestFile("ascend/test_ascend_tp2_fia_bf16.py", 400),
],
"per-commit-4-npu-a2": [
"per-commit-4-npu-a3": [
TestFile("ascend/test_ascend_mla_w8a8int8.py", 400),
TestFile("ascend/test_ascend_hicache_mla.py", 400),
TestFile("ascend/test_ascend_tp4_bf16.py", 400),
TestFile("ascend/test_ascend_w4a4_quantization.py", 600),
],
"per-commit-16-npu-a3": [
TestFile("ascend/test_ascend_deepep.py", 3600),
# TestFile("ascend/test_ascend_deepseek_mtp.py", 2800),
TestFile("ascend/test_ascend_w4a4_quantization.py", 600),
],
}