Commit Graph

52 Commits

Author SHA1 Message Date
Pratyush Patel
8f15789314 Add more metrics to serving benchmark. (#2819) 2025-01-10 23:30:44 +08:00
Lianmin Zheng
bdc1acf6cd Misc fix for min_p_sampling, --cuda-graph-bs (#2761) 2025-01-07 02:52:53 -08:00
Lianmin Zheng
dc3bee4815 Fix test and benchmark scripts (#2598) 2024-12-26 07:56:26 -08:00
Ying Sheng
8a56b43175 [Bench] Flush cache before benchmarking (#2566) 2024-12-24 11:21:21 +08:00
Lianmin Zheng
a2486eb58f Fix a bug with logprob streaming + chunked prefill (#2403) 2024-12-08 03:55:27 -08:00
Lianmin Zheng
3ddb1c4679 [Minor] Fix logger and style (#2325) 2024-12-02 20:45:53 -08:00
bjmsong
01017d4c20 Support LoRA in Completion API (#2243)
Co-authored-by: root <bjmsong@126.com>
2024-11-29 16:13:38 -08:00
Byron Hsu
4b0a1c9365 Replace prob based with threshold based load balancing (#2170) 2024-11-24 23:17:11 -08:00
Lianmin Zheng
8e1adb8441 Allow overwrite flashinfer use_tensorcore (#2169) 2024-11-24 20:58:17 -08:00
Byron Hsu
cbedd1db1d [router] cache-aware load-balancing router v1 (#2114) 2024-11-23 08:34:48 -08:00
Yineng Zhang
ad47749b82 fix: resolve bench_serving args (#2139) 2024-11-23 17:45:42 +08:00
Yunmeng
60769be14d Add concurrency option for benchmark (#2136) 2024-11-23 17:07:07 +08:00
bjmsong
ad30d5cf9a Benchmark with Pytorch Profiler easily (#2110)
Co-authored-by: root <bjmsong@126.com>
2024-11-21 23:29:50 -08:00
Yineng Zhang
55bd97f3e5 minor: add dataset dump and questions shuffle (#2093) 2024-11-19 14:07:27 -08:00
Lianmin Zheng
2558d6a675 Fix the default arguments of bench_offline_throughput.py & simplify detokenizer manager (#2042) 2024-11-15 05:02:44 -08:00
zolinthecow
f6dd648620 Offline LLM Engine Benchmark Throughput (#1968)
Co-authored-by: ByronHsu <byronhsu1230@gmail.com>
2024-11-14 21:59:33 -08:00
Ke Bao
b808a38365 Filter empty prompt in random bench serving (#2011) 2024-11-12 14:53:41 +08:00
Byron Hsu
8169c6f4ef Add gen-shared-prefix dataset in bench_serving (#1990) 2024-11-11 08:39:56 +08:00
Yineng Zhang
793b79dbe9 feat: support truss endpoint for benchmark serving (#1906) 2024-11-03 12:56:10 -08:00
Lianmin Zheng
175afed370 Improve benchmark scripts (#1672) 2024-10-14 21:53:01 -07:00
Lianmin Zheng
4a292f670d [Minor] Add some utility functions (#1671) 2024-10-14 20:08:03 -07:00
Ying Sheng
04b262cd91 [Fix] Fix major performance bug in certain cases (#1563)
Co-authored-by: hnyls2002 <hnyls2002@gmail.com>
2024-10-04 08:51:11 +00:00
Lianmin Zheng
5e62a6b706 Add bench_server_latency.py (#1452) 2024-09-18 00:56:06 -07:00
Lianmin Zheng
e4d68afcf0 [Minor] Many cleanup (#1357) 2024-09-09 04:14:11 -07:00
min-xu-et
fa13b95d6b fixed a typo (#1143) 2024-08-18 14:29:09 -07:00
Lianmin Zheng
3c1f5a9220 Fix duplicated imports in hf_transformers_utils.py (#1141) 2024-08-17 18:03:00 -07:00
Lianmin Zheng
57d0bd91ec Improve benchmark (#1140) 2024-08-17 17:43:23 -07:00
Lianmin Zheng
41598e0d8e Add longer accuracy test on CI (#1049) 2024-08-12 09:21:38 +00:00
Lianmin Zheng
8207637029 Improve end-to-end throughput test and its coverage (#1039) 2024-08-11 18:27:33 -07:00
Roger Wang
05c50a82b8 Minor bugfix on benchmark serving (#1005) 2024-08-10 02:53:50 +10:00
Juwan Yoo
ab7875941b feat: frequency, min_new_tokens, presence, and repetition penalties (#973) 2024-08-08 04:21:08 -07:00
Ying Sheng
ae7ee01a8e Add accuracy test to CI: MMLU (#882) 2024-08-01 21:20:17 -07:00
Yineng Zhang
f52eda35ea misc: update e2e test benchmark config (#825) 2024-07-30 19:19:23 +10:00
Ying Sheng
ae5c0fc442 Support disable_ignore_eos in bench_serving.py (#824) 2024-07-30 01:42:07 -07:00
Ying Sheng
db6089e6f3 Revert "Organize public APIs" (#815) 2024-07-29 19:40:28 -07:00
Liangsheng Yin
c8e9fed87a Organize public APIs (#809) 2024-07-29 15:34:16 -07:00
Yineng Zhang
768e05d08f fix benchmark (#743)
Co-authored-by: hnyls2002 <hnyls2002@gmail.com>
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
2024-07-26 21:26:13 +10:00
Ying Sheng
30d8e130e7 Improve benchmark scripts (#717) 2024-07-24 14:44:14 -07:00
zhyncs
fa7ccb3316 feat: add e2e latency (#704) 2024-07-24 05:51:10 +10:00
zhyncs
9fdea29d05 misc: fix typo (#698) 2024-07-23 02:00:27 +10:00
Ying Sheng
df7c4c19b4 Fix trt benchmark (#697) 2024-07-22 23:32:41 +10:00
zhyncs
d198791fe8 misc: update output token logic (#695) 2024-07-22 19:34:05 +10:00
zhyncs
c07526e46c fix: update bench serving (#694) 2024-07-22 18:23:33 +10:00
zhyncs
65bd13386b misc: recommend to use chat model for benchmark (#690) 2024-07-22 00:13:33 +10:00
zhyncs
6a846bb1fd misc: update output file logic (#686) 2024-07-21 18:07:30 +10:00
zhyncs
0fdb3127a1 feat: update bench serving (#685) 2024-07-21 16:46:58 +10:00
Lianmin Zheng
77e592e8e0 support non-streaming benchmark (#682) 2024-07-20 18:36:42 -07:00
zhyncs
4b4a67f814 feat: support TRT LLM benchmark and multiple benchmarks (#670) 2024-07-20 11:05:35 -07:00
Lianmin Zheng
9592a1f3bd Fix random dataset (#671) 2024-07-20 01:57:43 -07:00
Lianmin Zheng
35759efa91 Support random dataset in bench_serving.py (#669) 2024-07-20 01:06:43 -07:00