Commit Graph

258 Commits

Author SHA1 Message Date
Ying Sheng
5942dfc00a [feat] Add session control (#2073) 2024-11-20 00:36:53 -08:00
Lianmin Zheng
7d671e4ad2 Enable overlap by default (#2067) 2024-11-19 22:07:58 -08:00
Yineng Zhang
f239268fad minor: update gsm8k eval (#2091) 2024-11-19 20:36:55 +08:00
Lianmin Zheng
b7a065eae3 Use cuda event wait and synchronization instead of busy waiting (#2089) 2024-11-19 00:21:46 -08:00
Lianmin Zheng
b110453802 Simplify logits penalizer (#2086) 2024-11-18 17:48:28 -08:00
Lianmin Zheng
80e2c4a8de Fix chunked prefill with output logprob (#2083) 2024-11-18 13:16:28 -08:00
Yineng Zhang
766192610e feat: update torch 2.5.1 (#2069) 2024-11-18 21:29:13 +08:00
Lianmin Zheng
4af3f889fc Simplify flashinfer indices update for prefill (#2074)
Co-authored-by: kavioyu <kavioyu@tencent.com>
Co-authored-by: kavioyu <kavioyu@gmail.com>
2024-11-18 00:02:36 -08:00
Lianmin Zheng
a7164b620f Tune the threshold for accuracy tests in CI (#2071) 2024-11-17 21:51:00 -08:00
Lianmin Zheng
116685337e Fix cuda illegal memory access in overlap mode (#2070) 2024-11-17 21:29:30 -08:00
Lianmin Zheng
a9e90b4bce [Minor] Fix styles for overlap mode (#2068) 2024-11-17 19:49:20 -08:00
Tanjiro
8c280cee55 add phi-3 small support (#2062)
Co-authored-by: Tushar Goel <114812108+AI-Tushar@users.noreply.github.com>
2024-11-17 18:47:43 -08:00
Lianmin Zheng
11f881d173 Deprecate --disable-flashinfer and --disable-flashinfer-sampling (#2065) 2024-11-17 16:20:58 -08:00
Lianmin Zheng
38625e2139 Remove monkey_patch_vllm_dummy_weight_loader (#2064) 2024-11-17 15:48:12 -08:00
Lianmin Zheng
c1f401fc58 Revert "chore: update torch v2.5.1" (#2063) 2024-11-17 15:29:38 -08:00
Yineng Zhang
3b878863f7 chore: update torch v2.5.1 (#1849) 2024-11-18 00:06:00 +08:00
Lianmin Zheng
f719d9aebc Launch dp ranks in parallel (#2053)
Co-authored-by: Haotian Liu <6631389+haotian-liu@users.noreply.github.com>
2024-11-16 17:39:39 -08:00
Ke Bao
976bc302e5 Support DP MLA (#1970) 2024-11-16 09:01:43 +00:00
Ke Wen
cf2489762b Add Tensor Parallel to torch_native_llama (#1876) 2024-11-15 21:26:00 -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
Lianmin Zheng
c3eac1b010 Fix torch.compile for MoE (#2033) 2024-11-14 01:30:24 -08:00
Lianmin Zheng
f407fcf9ef Release v0.3.5.post1 (#2022) 2024-11-13 10:27:12 -08:00
Lianmin Zheng
ba069a24d3 Fix grammar backend (#2018) 2024-11-12 21:17:38 -08:00
DarkSharpness
125b1199c5 support parallel grammar preprocessing (#1996)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2024-11-12 08:45:28 -08:00
Xiaoyu Zhang
eff468dd5a fix test_embedding_models prompt length too long's bug (#2015) 2024-11-12 23:21:16 +08:00
Xiaoyu Zhang
027e65248f support echo=true and logprobs in openai api when logprobs=1 in lm-evaluation-harness (#1998) 2024-11-11 23:21:20 -08:00
James Xu
ddeb9d42de Add engine encode (#1995)
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
2024-11-11 11:48:17 -08:00
Lianmin Zheng
1929c06762 Simplify prometheus metrics (#1981)
Co-authored-by: Mohit Reddy <mohitreddy1996@users.noreply.github.com>
2024-11-10 04:39:32 -08:00
Lianmin Zheng
520f0094e4 [CI] balance unit tests (#1977) 2024-11-09 16:46:14 -08:00
Lianmin Zheng
9c939a3d8b Clean up metrics code (#1972) 2024-11-09 15:43:20 -08:00
Lianmin Zheng
549e8b8366 [Minor] Fix a typo in test_torchao.py (#1976) 2024-11-09 15:07:27 -08:00
Yudi Xue
95a4ed129a Fix metrics (#1963) 2024-11-08 23:21:11 -08:00
Chayenne
c77c1e05ba fix black in pre-commit (#1940) 2024-11-08 07:42:47 +08:00
Xuehai Pan
a5e0defb5a minor: Add basic editorconfig and pre-commit hooks to enforce style for whitespaces (#1926) 2024-11-06 13:46:04 +00:00
Chayenne
704f8e8ed1 Add Reward API Docs etc (#1910)
Co-authored-by: Chayenne <zhaochenyang@g.ucla.edu>
2024-11-03 22:33:03 -08:00
Lianmin Zheng
2ce32db6fb Let reward model take text inputs instead of message lists (#1907)
Co-authored-by: Kyle Corbitt <kyle@corbt.com>
2024-11-03 13:27:12 -08:00
Lianmin Zheng
0abbf289a8 Unify the model type checking (#1905) 2024-11-03 12:25:39 -08:00
Lianmin Zheng
c17c578108 Simplify tokenizer manager (#1904) 2024-11-03 08:38:26 -08:00
Lianmin Zheng
d1b31b0684 Improve docs and fix the broken links (#1875) 2024-11-01 17:47:44 -07:00
Yineng Zhang
104bf2609b minor: update nightly eval (#1867) 2024-11-01 21:38:29 +08:00
Yineng Zhang
d86a2d6562 minor: add human eval (#1754) 2024-11-01 14:29:20 +08:00
Liangsheng Yin
b9fd178f1b Fix retraction + overlap (#1860)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2024-10-31 18:27:42 -07:00
Lianmin Zheng
a2e0424abf Fix memory leak for chunked prefill 2 (#1858)
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
2024-10-31 14:51:51 -07:00
Lianmin Zheng
f7102fbd2b Fix mixed chunked prefill (#1850) 2024-10-30 21:20:41 -07:00
DanielC12321
5e00ddebc0 Add new model: Gpt2 (#1833) 2024-10-29 17:52:33 -07:00
Byron Hsu
680cad2023 fix get_memory_pool_size deadlock for DP (#1830) 2024-10-28 23:07:14 -07:00
Byron Hsu
0a24eb850a Fix update_weights deadlock for DP (#1825) 2024-10-28 12:02:23 -07:00
Byron Hsu
6fcd6d7d6d Support token ids in engine.generate (#1820) 2024-10-27 14:02:34 -07:00
Ke Bao
c77762d57f Fix Triton decode kernel & ut (#1819) 2024-10-27 10:54:38 -07:00