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

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

4
test/srt/test_mla_flashinfer.py
View File

@@ -158,7 +158,9 @@ class TestFlashinferMLAMTP(CustomTestCase):
server_info = requests.get(self.base_url + "/get_server_info")
print(f"{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, 2.5)