Liangsheng Yin 73cf6834f2 Support stop_token_ids in sglang API (#1092)

2024-08-15 00:31:39 +00:00

..

srt/sampling/penaltylib

feat: frequency, min_new_tokens, presence, and repetition penalties (#973)

2024-08-08 04:21:08 -07:00

long_prompt.txt

[Fix] Compatibility of window attention and cuda graph (#1090)

2024-08-14 10:37:01 -07:00

run_eval.py

Fix accuracy test (#1051)

2024-08-12 19:48:40 +10:00

runners.py

[Fix] Compatibility of window attention and cuda graph (#1090)

2024-08-14 10:37:01 -07:00

simple_eval_common.py

Fix CI && python3.8 compatible (#920)

2024-08-04 16:02:05 -07:00

simple_eval_gpqa.py

Improve the structure of CI (#911)

2024-08-03 23:09:21 -07:00

simple_eval_humaneval.py

Fix accuracy test (#1051)

2024-08-12 19:48:40 +10:00

simple_eval_math.py

Improve the structure of CI (#911)

2024-08-03 23:09:21 -07:00

simple_eval_mgsm.py

Add longer accuracy test on CI (#1049)

2024-08-12 09:21:38 +00:00

simple_eval_mmlu.py

Add accuracy test to CI: MMLU (#882)

2024-08-01 21:20:17 -07:00

test_layernorm.py

feat: use FlashInfer rmsnorm and silu (#907)

2024-08-11 14:57:13 +10:00

test_programs.py

Support stop_token_ids in sglang API (#1092)

2024-08-15 00:31:39 +00:00

test_utils.py

ci: add moe test (#1053)

2024-08-13 18:43:23 +10:00