Support piecewise cuda graph for MLA (#11812)

This commit is contained in:
Ke Bao
2025-11-10 09:13:48 +08:00
committed by GitHub
parent 885cfca273
commit db24d34603
10 changed files with 196 additions and 89 deletions
+1 -1
View File
@@ -103,7 +103,7 @@ suites = {
TestFile("test_original_logprobs.py", 41),
TestFile("test_page_size.py", 60),
TestFile("test_penalty.py", 82),
TestFile("test_piecewise_cuda_graph.py", 180),
TestFile("test_piecewise_cuda_graph.py", 300),
TestFile("test_priority_scheduling.py", 130),
TestFile("test_pytorch_sampling_backend.py", 66),
TestFile("test_radix_attention.py", 105),