Commit Graph

1159 Commits

Author SHA1 Message Date
f42b4c27d8 Include argmax to jit 2024-04-24 08:56:45 +00:00
620e7646d3 Fix cache write 2024-04-24 08:56:30 +00:00
d5fb1c20c1 Fix JAX jit OOM 2024-04-24 07:52:56 +00:00
092e3d6d6d Remove hardcoded path 2024-04-19 08:18:10 +00:00
84284302d8 Minor 2024-04-19 08:08:25 +00:00
743695f586 Fix write_to_kv_cache 2024-04-19 07:51:54 +00:00
62b870fa07 Use FlashAttention kernel 2024-04-17 20:24:45 +00:00
7e3a230c38 Fix paged_attn 2024-04-17 20:06:26 +00:00
186c88c497 explictly return new_kv_caches 2024-04-17 18:42:34 +00:00
ef762cb110 Write kV 2024-04-17 18:21:39 +00:00
756c4e78d3 Add write_to_cache ops 2024-04-17 18:20:55 +00:00
4880de35d2 Add attn_mask 2024-04-17 18:12:20 +00:00
0fb07c08d0 Minor 2024-04-17 18:08:33 +00:00
e4377dd698 Add model runner 2024-04-17 18:04:54 +00:00
5cb213c85e Add flash-attn op 2024-04-17 18:02:28 +00:00
25bbc21ef6 Minor 2024-04-17 18:02:16 +00:00
b25fcc06c2 Minor 2024-04-17 18:02:13 +00:00
6661c030c4 Add paged_attn op 2024-04-17 18:02:00 +00:00
8888d1c474 Fix logit indices 2024-04-17 18:01:43 +00:00
cedb67028a Add gemma 2024-04-17 17:00:10 +00:00
91b47e3f2f JAX-based TPU worker 2024-04-16 17:37:11 +00:00
6d62e4c6aa Add torch to dependencies 2024-04-16 17:06:35 +00:00
de82e95787 Minor 2024-04-16 17:04:46 +00:00
b3b89cf755 Renew TPU executor 2024-04-16 09:42:15 +00:00
6692a30266 Minor 2024-04-16 09:41:53 +00:00
eb0a0466a9 Add JAX requirements 2024-04-16 08:05:54 +00:00
c59c1e7b2c Remove 2024-04-16 08:05:36 +00:00
d4adf92beb Merge branch 'main' into woosuk-tpu 2024-04-16 07:56:53 +00:00
05434764cd LM Format Enforcer Guided Decoding Support (#3868)
Co-authored-by: Simon Mo <simon.mo@hey.com>
2024-04-16 05:54:57 +00:00
4e7ee664e2 [Core] Fix engine-use-ray broken (#4105) 2024-04-16 05:24:53 +00:00
37e84a403d [Typing] Fix Sequence type GenericAlias only available after Python 3.9. (#4092) 2024-04-15 14:47:31 -07:00
4695397dcf [Bugfix] Fix ray workers profiling with nsight (#4095) 2024-04-15 14:24:45 -07:00
d619ae2d19 [Doc] Add better clarity for tensorizer usage (#4090)
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-04-15 13:28:25 -07:00
eb46fbfda2 [Core] Simplifications to executor classes (#4071) 2024-04-15 13:05:09 -07:00
0003e9154b [Misc][Minor] Fix CPU block num log in CPUExecutor. (#4088) 2024-04-15 08:35:55 -07:00
e11e200736 [Bugfix] Fix filelock version requirement (#4075) 2024-04-14 21:50:08 -07:00
Roy
8db1bf32f8 [Misc] Upgrade triton to 2.2.0 (#4061) 2024-04-14 17:43:54 -07:00
aceb17cf2d [Docs] document that mixtral 8x22b is supported (#4073) 2024-04-14 14:35:55 -07:00
563c54f760 [BugFix] Fix tensorizer extra in setup.py (#4072) 2024-04-14 14:12:42 -07:00
2cd6b4f362 [Core] avoid too many cuda context by caching p2p test (#4021) 2024-04-13 23:40:21 -07:00
711a000255 [Frontend] [Core] feat: Add model loading using tensorizer (#3476) 2024-04-13 17:13:01 -07:00
989ae2538d [Kernel] Add punica dimension for Baichuan-13B (#4053) 2024-04-13 07:55:05 -07:00
0a430b4ae2 [Bugfix] fix_small_bug_in_neuron_executor (#4051) 2024-04-13 07:54:03 -07:00
ec8e3c695f [Bugfix] fix_log_time_in_metrics (#4050) 2024-04-13 07:52:36 -07:00
98afde19fc [Core][Distributed] improve logging for init dist (#4042) 2024-04-13 07:12:53 -07:00
5c2e66e487 [Bugfix] More type hint fixes for py 3.8 (#4039) 2024-04-12 21:07:04 -07:00
546e721168 [CI/Test] expand ruff and yapf for all supported python version (#4037) 2024-04-13 01:43:37 +00:00
b8aacac31a [Bugfix] Fix LoRA bug (#4032) 2024-04-12 16:56:37 -07:00
d04973ad54 Fix triton compilation issue (#3984)
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-04-12 16:41:26 -07:00
fbb9d9eef4 [Core] fix custom allreduce default value (#4040) 2024-04-12 16:40:39 -07:00