Log if cuda graph is used & extend cuda graph capture to cuda-graph-max-bs (#6201)

Co-authored-by: SangBin Cho <rkooo567@gmail.com>
This commit is contained in:
Lianmin Zheng
2025-05-12 00:17:33 -07:00
committed by GitHub
parent 7d3a3d4510
commit fba8eccd7e
27 changed files with 293 additions and 121 deletions

View File

@@ -111,7 +111,9 @@ class BaseFlashAttentionTest(CustomTestCase):
if self.speculative_decode:
server_info = requests.get(self.base_url + "/get_server_info")
avg_spec_accept_length = server_info.json()["avg_spec_accept_length"]
avg_spec_accept_length = server_info.json()["internal_states"][0][
"avg_spec_accept_length"
]
print(f"{avg_spec_accept_length=}")
self.assertGreater(avg_spec_accept_length, self.spec_decode_threshold)