66 Commits

Author SHA1 Message Date
Zhuohan Li
e90fc21f2e
[Hardware][Neuron] Refactor neuron support (#3471) 2024-03-22 01:22:17 +00:00
Roy
f1c0fc3919
Migrate logits computation and gather to model_runner (#3233) 2024-03-20 23:25:01 +00:00
SangBin Cho
6e435de766
[1/n][Chunked Prefill] Refactor input query shapes (#3236) 2024-03-20 14:46:05 -07:00
Antoni Baum
426ec4ec67
[1/n] Triton sampling kernel (#3186)
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-03-20 14:45:08 -07:00
Woosuk Kwon
5ee14494e4
[Misc] Remove cache stream and cache events (#3461) 2024-03-20 00:38:53 -07:00
Antoni Baum
49eedea373
[Core] Zero-copy asdict for InputMetadata (#3475) 2024-03-18 22:56:40 +00:00
Woosuk Kwon
abfc4f3387
[Misc] Use dataclass for InputMetadata (#3452)
Co-authored-by: youkaichao <youkaichao@126.com>
2024-03-17 10:02:46 +00:00
Zhuohan Li
2f8844ba08
Re-enable the 80 char line width limit (#3305) 2024-03-10 19:49:14 -07:00
Cade Daniel
8437bae6ef
[Speculative decoding 3/9] Worker which speculates, scores, and applies rejection sampling (#3103) 2024-03-08 23:32:46 -08:00
ElizaWszola
b35cc93420
Fix auto prefix bug (#3239) 2024-03-07 16:37:28 -08:00
Michael Goin
385da2dae2
Measure model memory usage (#3120) 2024-03-07 11:42:42 -08:00
Hongxia Yang
05af6da8d9
[ROCm] enable cupy in order to enable cudagraph mode for AMD GPUs (#3123)
Co-authored-by: lcskrishna <lollachaitanya@gmail.com>
2024-03-04 18:14:53 -08:00
Antoni Baum
22de45235c
Push logprob generation to LLMEngine (#3065)
Co-authored-by: Avnish Narayan <avnish@anyscale.com>
2024-03-04 19:54:06 +00:00
Sage Moore
ce4f5a29fb
Add Automatic Prefix Caching (#2762)
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-03-02 00:50:01 -08:00
Liangfu Chen
3b7178cfa4
[Neuron] Support inference with transformers-neuronx (#2569) 2024-02-28 09:34:34 -08:00
Nick Hill
7d2dcce175
Support per-request seed (#2514) 2024-02-21 11:47:00 -08:00
Zhuohan Li
537c9755a7
[Minor] Small fix to make distributed init logic in worker looks cleaner (#2905) 2024-02-18 14:39:00 -08:00
Woosuk Kwon
25e86b6a61
Don't use cupy NCCL for AMD backends (#2855) 2024-02-14 12:30:44 -08:00
Woosuk Kwon
7e45107f51
[Fix] Fix memory profiling when GPU is used by multiple processes (#2863) 2024-02-13 19:52:34 -08:00
Terry
2a543d6efe
Add LoRA support for Mixtral (#2831)
* add mixtral lora support

* formatting

* fix incorrectly ported logic

* polish tests

* minor fixes and refactoring

* minor fixes

* formatting

* rename and remove redundant logic

* refactoring

* refactoring

* minor fix

* minor refactoring

* fix code smell
2024-02-14 00:55:45 +01:00
Woosuk Kwon
a463c333dd
Use CuPy for CUDA graphs (#2811) 2024-02-13 11:32:06 -08:00
Kunshang Ji
96b6f475dd
Remove hardcoded device="cuda" to support more devices (#2503)
Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2024-02-01 15:46:39 -08:00
Tao He
d69ff0cbbb
Fixes assertion failure in prefix caching: the lora index mapping should respect prefix_len (#2688)
Signed-off-by: Tao He <sighingnow@gmail.com>
2024-01-31 18:00:13 +01:00
zhaoyang-star
9090bf02e7
Support FP8-E5M2 KV Cache (#2279)
Co-authored-by: zhaoyang <zhao.yang16@zte.com.cn>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-01-28 16:43:54 -08:00
Hanzhi Zhou
380170038e
Implement custom all reduce kernels (#2192) 2024-01-27 12:46:35 -08:00
Antoni Baum
9b945daaf1
[Experimental] Add multi-LoRA support (#1804)
Co-authored-by: Chen Shen <scv119@gmail.com>
Co-authored-by: Shreyas Krishnaswamy <shrekris@anyscale.com>
Co-authored-by: Avnish Narayan <avnish@anyscale.com>
2024-01-23 15:26:37 -08:00
Cade Daniel
18bfcdd05c
[Speculative decoding 2/9] Multi-step worker for draft model (#2424) 2024-01-21 16:31:47 -08:00
Zhuohan Li
ef9b636e2d
Simplify broadcast logic for control messages (#2501) 2024-01-19 11:23:30 -08:00
shiyi.c_98
d10f8e1d43
[Experimental] Prefix Caching Support (#1669)
Co-authored-by: DouHappy <2278958187@qq.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-01-17 16:32:10 -08:00
Roy
9f659bf07f
[Minor] Optimize cuda graph memory usage (#2437) 2024-01-14 18:40:51 +01:00
Woosuk Kwon
35c4bc20d9
[Minor] Fix err msg (#2431) 2024-01-12 14:02:52 -08:00
Ben
cb7a1c1cbf
Suggest using dtype=half when OOM. 2024-01-12 12:33:29 -08:00
Jiaxiang
6549aef245
[DOC] Add additional comments for LLMEngine and AsyncLLMEngine (#1011) 2024-01-11 19:26:49 -08:00
Woosuk Kwon
c884819135
Fix eager mode performance (#2377) 2024-01-08 10:11:06 -08:00
Zhuohan Li
fd4ea8ef5c
Use NCCL instead of ray for control-plane communication to remove serialization overhead (#2221) 2024-01-03 11:30:22 -08:00
Hanzhi Zhou
31bff69151
Make _prepare_sample non-blocking and use pinned memory for input buffers (#2207) 2023-12-19 16:52:46 -08:00
Woosuk Kwon
21d5daa4ac
Add warning on CUDA graph memory usage (#2182) 2023-12-18 18:16:17 -08:00
Woosuk Kwon
c3372e87be
Remove dependency on CuPy (#2152) 2023-12-17 01:49:07 -08:00
Woosuk Kwon
e1d5402238
Fix all-reduce memory usage (#2151) 2023-12-17 01:44:45 -08:00
Woosuk Kwon
37ca558103
Optimize model execution with CUDA graph (#1926)
Co-authored-by: Chen Shen <scv119@gmail.com>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
2023-12-16 21:12:08 -08:00
Woosuk Kwon
f1c8520146
[BugFix] Fix input positions for long context with sliding window (#2088) 2023-12-13 12:28:13 -08:00
Woosuk Kwon
30bad5c492
Fix peak memory profiling (#2031) 2023-12-12 22:01:53 -08:00
Woosuk Kwon
5f09cbdb63
Fix broken sampler tests (#1896)
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
2023-12-02 16:06:17 -08:00
Woosuk Kwon
27feead2f8
Refactor Worker & InputMetadata (#1843) 2023-11-29 22:16:37 -08:00
Yanming W
e0c6f556e8
[Build] Avoid building too many extensions (#1624) 2023-11-23 16:31:19 -08:00
boydfd
4bb6b67188
fix RAM OOM when load large models in tensor parallel mode. (#1395)
Co-authored-by: ran_lin <rlin@thoughtworks.com>
2023-11-20 19:02:42 -08:00
Simon Mo
5ffc0d13a2
Migrate linter from pylint to ruff (#1665) 2023-11-20 11:58:01 -08:00
Yanming W
8efe23f150
Fix input_metadata.selected_token_indices in worker prepare_inputs (#1546) 2023-11-08 14:19:12 -08:00
Antoni Baum
9738b84a08
Force paged attention v2 for long contexts (#1510) 2023-11-01 16:24:32 -07:00
Woosuk Kwon
0ce8647dc5
Fix integer overflows in attention & cache ops (#1514) 2023-10-31 15:19:30 -07:00