[Ascend]Support of piecewise graph compilation for prefill on NPU (#12287)

Co-authored-by: ronnie_zheng <zl19940307@163.com>
This commit is contained in:
Vladimir221
2025-12-11 21:10:07 +08:00
committed by GitHub
co-authored by ronnie_zheng
parent 5d804a3767
commit 27032cecd9
10 changed files with 289 additions and 40 deletions
+1
View File
@@ -361,6 +361,7 @@ suite_xpu = {
suite_ascend = {
"per-commit-1-npu-a2": [
TestFile("ascend/test_ascend_graph_tp1_bf16.py", 400),
TestFile("ascend/test_ascend_piecewise_graph_prefill.py", 400),
TestFile("ascend/test_ascend_hicache_mha.py", 400),
TestFile("ascend/test_ascend_sampling_backend.py", 400),
TestFile("ascend/test_ascend_tp1_bf16.py", 400),