EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[feature] Ascend NPU graph support (#8027)

Browse Source 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: yezhifeng (D) <y00897525@china.huawei.com>
Co-authored-by: anon189Ty <Stari_Falcon@outlook.com>
Co-authored-by: Maksim <makcum888e@mail.ru>
Co-authored-by: ssshinigami <44640852+ssshinigami@users.noreply.github.com>
This commit is contained in:
VDV1985
2025-08-17 03:25:17 +03:00
committed by GitHub
parent 740f063035
commit 94371dbbd6
18 changed files with 1349 additions and 878 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
test/srt/run_suite.py
View File

@@ -229,6 +229,17 @@ suite_amd = {
TestFile("test_wave_attention_kernels.py", 2),
TestFile("test_wave_attention_backend.py", 150),
],
"per-commit-1-ascend-npu": [
TestFile("test_ascend_tp1_bf16.py", 400),
TestFile("test_ascend_graph_tp1_bf16.py", 400),
],
"per-commit-2-ascend-npu": [
TestFile("test_ascend_tp2_bf16.py", 400),
TestFile("test_ascend_graph_tp2_bf16.py", 400),
],
"per-commit-4-ascend-npu": [
TestFile("test_ascend_mla_w8a8int8.py", 400),
],
"per-commit-2-gpu-amd": [
TestFile("lora/test_lora_tp.py", 116),
TestFile("rl/test_update_weights_from_distributed.py", 103),