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_srt_engine.py
View File

@@ -141,11 +141,11 @@ class TestSRTEngine(CustomTestCase):
model_path=DEFAULT_SMALL_MODEL_NAME_FOR_TEST,
local_data_path=None,
num_shots=5,
num_questions=200,
num_questions=1400,
)
metrics = run_eval(args)
self.assertGreater(metrics["accuracy"], 0.3)
self.assertGreater(metrics["accuracy"], 0.33)
def test_6_engine_cpu_offload(self):
prompt = "Today is a sunny day and I like"