Commit Graph

118 Commits

Author SHA1 Message Date
Lianmin Zheng
b2ccf36d4d Fix memory leak during abort (#2238) 2024-11-28 02:22:15 -08:00
Ying Sheng
37c8a5761f [feat] Support session control for vision language models (#2210) 2024-11-27 00:03:29 -08:00
Rin Intachuen
1aea19f64b Input_embeds support (#2052) 2024-11-25 16:35:04 -08:00
Lianmin Zheng
731146f6cb Fix mixed chunked prefill in overlap mode (#2158) 2024-11-24 07:17:37 -08:00
Lianmin Zheng
5652c56535 Update CI threshold & Improve code style (#2159) 2024-11-24 06:29:38 -08:00
Lianmin Zheng
c211e7b669 Simplify batch update (#2154) 2024-11-24 04:47:10 -08:00
Xuehai Pan
62a4a339eb docs: fix module docstrings and copyright headers (#2077) 2024-11-22 22:16:53 +08:00
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
Lianmin Zheng
ffd20fcd03 Make constrained decoding work for overlap scheduler (#2095) 2024-11-19 15:04:43 -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
116685337e Fix cuda illegal memory access in overlap mode (#2070) 2024-11-17 21:29:30 -08:00
Lianmin Zheng
ebaa2f3199 Rename arguments --disable-nan-detection to --enable-nan-detection (#2066) 2024-11-17 16:53:44 -08:00
Ke Bao
62832bb272 Support cuda graph for DP attention (#2061) 2024-11-17 16:29:20 -08:00
Lianmin Zheng
edad373135 Fix illegal memory access in overlap mode & Use more fused triton kernels for building meta data (#2051) 2024-11-16 16:14:23 -08:00
Ke Bao
976bc302e5 Support DP MLA (#1970) 2024-11-16 09:01:43 +00:00
HAI
e5c6715003 Fix core (MI300X) with --enable-overlap (#2048) 2024-11-15 21:24:42 -08:00
Lianmin Zheng
54479d6f30 Fix grammar backend for tensor parallelism (#2020) 2024-11-13 01:49:45 -08:00
Lianmin Zheng
ba069a24d3 Fix grammar backend (#2018) 2024-11-12 21:17:38 -08:00
Lianmin Zheng
78c1d6445f Fix finish reason (#2013) 2024-11-11 23:24:41 -08:00
Lianmin Zheng
befc6beb86 Fix a typo in io_struct.py (#2008) 2024-11-11 16:34:10 -08:00
yizhang2077
a8aad9357d qwen2vl fix bug for #1971 #1897 (#1984) 2024-11-10 08:10:45 -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
Chayenne
c77c1e05ba fix black in pre-commit (#1940) 2024-11-08 07:42:47 +08:00
Lzhang-hub
a146d9990e support prometheus metrics (#1853)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
2024-11-05 20:42:53 -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
DarkSharpness
b77a02cdfd [Performance] Support both xgrammar and outlines for constrained decoding (#1752) 2024-10-25 21:47:02 +00:00
Lianmin Zheng
c555ce2ca2 Revert "Fix memory leak when doing chunked prefill" (#1797) 2024-10-25 10:24:44 -07:00
Liangsheng Yin
a2f5e7555f Fix memory leak when doing chunked prefill (#1787) 2024-10-25 08:01:17 -07:00
Lianmin Zheng
8f8f96a621 Fix the perf regression due to additional_stop_token_ids (#1773) 2024-10-23 16:45:21 -07:00
Liangsheng Yin
3f5ac88d02 Fix out of memory message. (#1771) 2024-10-23 15:20:39 -07:00
Liangsheng Yin
94cde10920 Llama3.2 vision model support (#1551) 2024-10-21 15:01:21 -07:00
Lianmin Zheng
09603c6dc9 Maintain seq_lens_sum to make more FlashInfer operations non-blocking (#1741) 2024-10-21 01:43:16 -07:00
Lianmin Zheng
b121bc03a3 Simplify batch result resolution (#1735) 2024-10-20 19:47:14 -07:00
Lianmin Zheng
e12358dc91 Simplify the usage of device (#1734) 2024-10-20 18:17:41 -07:00
Lianmin Zheng
b48edff67f Split the overlapped version of TpModelWorkerClient into a separate file (#1726) 2024-10-20 00:29:29 -07:00
Lianmin Zheng
59cbf47626 Unify the memory pool api and tp worker API (#1724) 2024-10-19 23:19:26 -07:00
Yineng Zhang
cbbc82b7b8 Support qwen2 vl model (#1721)
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: ispobock <ISPObaoke@163.com>
2024-10-19 21:44:38 -07:00
Lianmin Zheng
769bf11c05 Fix the race condition in overlap mode (#1712) 2024-10-19 06:50:56 -07:00
Lianmin Zheng
f0f8a7699b Simplify the nan detection and greedy check in sampler (#1709) 2024-10-18 20:21:24 -07:00
Lianmin Zheng
2bcfba1b08 Skip unnecessary penalizer (#1707) 2024-10-18 17:54:03 -07:00
Lianmin Zheng
392f2863c8 Add dtype for more operations (#1705) 2024-10-18 12:18:15 -07:00
Lianmin Zheng
6d0fa73ece Simplify flashinfer utilities (#1704) 2024-10-17 22:54:14 -07:00
havetc
ecb8bad276 Returning a per request metric for number of cached_tokens read (#1599) 2024-10-16 11:49:22 -07:00
Lianmin Zheng
9116b2896f Add a new event loop (#1677) 2024-10-16 01:33:20 -07:00
Liangsheng Yin
b6b4094621 Fix filter_batch function call (#1681) 2024-10-15 22:59:26 -07:00
Lianmin Zheng
4a292f670d [Minor] Add some utility functions (#1671) 2024-10-14 20:08:03 -07:00
Lianmin Zheng
24f3e1511c [Minor] Improve style (#1666) 2024-10-14 05:25:00 -07:00