[Piecewise CUDA Graph] Support ModelOpt FP8 (#13094)

This commit is contained in:
b8zhong
2025-11-18 12:46:24 +08:00
committed by GitHub
parent 4ce8fb3cc2
commit f33860777c
4 changed files with 48 additions and 8 deletions
+1 -1
View File
@@ -94,7 +94,7 @@ suites = {
TestFile("test_original_logprobs.py", 41),
TestFile("test_page_size.py", 60),
TestFile("test_penalty.py", 82),
TestFile("test_piecewise_cuda_graph.py", 450),
TestFile("test_piecewise_cuda_graph.py", 600),
TestFile("test_priority_scheduling.py", 130),
TestFile("test_pytorch_sampling_backend.py", 66),
TestFile("test_radix_attention.py", 105),