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

chore: upgrade flashinfer v0.2.6.post1 jit (#6958)

Browse Source 
Co-authored-by: alcanderian <alcanderian@gmail.com>
Co-authored-by: Qiaolin Yu <qy254@cornell.edu>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
This commit is contained in:
Yineng Zhang
2025-06-09 09:22:39 -07:00
committed by GitHub
parent 98c00a2df1
commit 56ccd3c22c
14 changed files with 189 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
test/srt/test_bench_serving.py
View File

@@ -175,7 +175,7 @@ class TestBenchServing(CustomTestCase):
def test_vlm_online_latency(self):
res = run_bench_serving(
model=DEFAULT_SMALL_VLM_MODEL_NAME_FOR_TEST,
num_prompts=50,
num_prompts=250,
request_rate=1,
other_server_args=[
"--mem-fraction-static",
@@ -194,7 +194,7 @@ class TestBenchServing(CustomTestCase):
self.assertLess(res["median_ttft_ms"], 150)
# TODO: not set yet, need AMD machine
else:
self.assertLess(res["median_ttft_ms"], 90)
self.assertLess(res["median_ttft_ms"], 94)
self.assertLess(res["median_itl_ms"], 8)
def test_online_latency_eagle(self):