minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

[CI] Lower GSM8K baselines for B200 nightly after eval unification (#22136)

Browse Source 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kangyan-Zhou
2026-04-22 22:30:54 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 2b4eeb8343
commit 18359aadc8
3 changed files with 11 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/backends/test_flashinfer_trtllm_gen_moe_backend.py
+1 -1
View File
@@ -59,7 +59,7 @@ class FlashinferTrtllmGenMoeBackendFP8Base:
)
metrics = run_eval(args)
print(f"{metrics=}")
self.assertGreater(metrics["score"], 0.93)
self.assertGreater(metrics["score"], 0.89)
class FlashinferTrtllmGenMoeBackendBF16Base: