Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)

Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: dhou-xai <dhou@x.ai>
Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>
This commit is contained in:
Lianmin Zheng
2025-03-03 00:12:04 -08:00
parent 0194948fd9
commit ac2387279e
86 changed files with 4116 additions and 2015 deletions

View File

@@ -141,7 +141,7 @@ class TestDeepseekV3MTP(unittest.TestCase):
metrics = run_eval_few_shot_gsm8k(args)
print(metrics)
self.assertGreater(metrics["accuracy"], 0.62)
self.assertGreater(metrics["accuracy"], 0.60)
if __name__ == "__main__":