minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Re-enable test_mla_int8_deepseek_v3.py after HF token fix (#18123)

Browse Source
This commit is contained in:
Alison Shao
2026-02-02 14:38:42 -08:00
committed by GitHub
parent 027f314050
commit 812fd47cb4
1 changed files with 1 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/mla/test_mla_int8_deepseek_v3.py
+1 -5
View File
@@ -16,11 +16,7 @@ from sglang.test.test_utils import (
) )
# DeepSeek-V3 INT8 quantization tests (channel and block INT8) # DeepSeek-V3 INT8 quantization tests (channel and block INT8)
register_cuda_ci( register_cuda_ci(est_time=341, suite="stage-b-test-large-1-gpu")
est_time=341,
suite="stage-b-test-large-1-gpu",
disabled="HF token doesn't have private repository access",
)
class TestMLADeepseekV3ChannelInt8(CustomTestCase): class TestMLADeepseekV3ChannelInt8(CustomTestCase):