wang.yuqi
6e36f4fa6c
improve chunked prefill performance
...
[Bugfix] Fix #7592 vllm 0.5.4 enable_chunked_prefill throughput is slightly lower than 0.5.3~0.5.0. (#7874 )
2024-09-02 14:20:12 -07:00
Alexander Matveev
3f60f2244e
[Core] Combine async postprocessor and multi-step ( #7921 )
2024-08-29 11:18:26 -07:00
Cody Yu
e3580537a4
[Performance] Enable chunked prefill and prefix caching together ( #7753 )
2024-08-28 00:36:31 -07:00
Alexander Matveev
f508e03e7f
[Core] Async_output_proc: Add virtual engine support (towards pipeline parallel) ( #7911 )
2024-08-28 00:02:30 -07:00
youkaichao
bc6e42a9b1
[hardware][rocm] allow rocm to override default env var ( #7926 )
2024-08-27 19:50:06 -07:00
Jonathan Berkhahn
9c71c97ae2
[mypy] Enable mypy type checking for vllm/core ( #7229 )
2024-08-28 07:11:14 +08:00
Megha Agarwal
2eedede875
[Core] Asynchronous Output Processor ( #7049 )
...
Co-authored-by: Alexander Matveev <alexm@neuralmagic.com>
2024-08-26 20:53:20 -07:00
Cody Yu
2deb029d11
[Performance][BlockManagerV2] Mark prefix cache block as computed after schedule ( #7822 )
2024-08-26 11:24:53 -07:00
Cody Yu
3ac50b47d0
[MISC] Add prefix cache hit rate to metrics ( #7606 )
2024-08-19 11:52:07 -07:00
SangBin Cho
ff7ec82c4d
[Core] Optimize SPMD architecture with delta + serialization optimization ( #7109 )
2024-08-18 17:57:20 -07:00
Mahesh Keralapura
93478b63d2
[Core] Fix tracking of model forward time in case of PP>1 ( #7440 )
...
[Core] Fix tracking of model forward time to the span traces in case of PP>1 (#7440 )
2024-08-16 13:46:01 -07:00
William Lin
2ecf7b1757
[core] [3/N] multi-step args and sequence.py ( #7452 )
2024-08-14 12:32:45 -07:00
Cade Daniel
baa240252e
[Core] Fix edge case in chunked prefill + block manager v2 ( #7380 )
2024-08-09 23:48:49 +00:00
Mahesh Keralapura
933790c209
[Core] Add span metrics for model_forward, scheduler and sampler time ( #7089 )
2024-08-09 13:55:13 -07:00
Alexander Matveev
fc7b8d1eef
[Performance] e2e overheads reduction: Small followup diff ( #7364 )
2024-08-09 15:49:36 +00:00
Alexander Matveev
e02ac55617
[Performance] Optimize e2e overheads: Reduce python allocations ( #7162 )
2024-08-08 21:34:28 -07:00
Zach Zheng
782e53ab59
[Bugfix][fast] Fix the get_num_blocks_touched logic ( #6849 )
2024-08-08 10:43:30 -07:00
Rui Qiao
746709642c
[Misc] Fix typos in scheduler.py ( #7285 )
...
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2024-08-07 17:06:01 -07:00
afeldman-nm
fd95e026e0
[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) ( #4942 )
...
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-08-06 16:51:47 -04:00
xiaobochen123
660470e5a3
[Core] Optimize evictor-v2 performance ( #7193 )
2024-08-06 12:34:25 -07:00
Woosuk Kwon
6ce01f3066
[Performance] Optimize get_seqs ( #7051 )
2024-08-01 18:29:52 -07:00
youkaichao
c8a7e93273
[core][scheduler] simplify and improve scheduler ( #6867 )
2024-07-31 23:51:09 -07:00
youkaichao
6ca8031e71
[core][misc] improve free_finished_seq_groups ( #6865 )
...
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-07-30 14:32:12 -07:00
Nick Hill
5cf9254a9c
[BugFix] Fix use of per-request seed with pipeline parallel ( #6698 )
2024-07-30 10:40:08 -07:00
Antoni Baum
9ed82e7074
[Misc] Small perf improvements ( #6520 )
2024-07-19 12:10:56 -07:00
Mor Zusman
9ad32dacd9
[BugFix][Model] Jamba - Handle aborted requests, Add tests and fix cleanup bug ( #6425 )
...
Co-authored-by: Mor Zusman <morz@ai21.com>
2024-07-16 01:32:55 +00:00
Swapnil Parekh
4d6ada947c
[CORE] Adding support for insertion of soft-tuned prompts ( #4645 )
...
Co-authored-by: Swapnil Parekh <swapnilp@ibm.com>
Co-authored-by: Joe G <joseph.granados@h2o.ai>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
2024-07-09 13:26:36 -07:00
Mor Zusman
9d6a8daa87
[Model] Jamba support ( #4115 )
...
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: Erez Schwartz <erezs@ai21.com>
Co-authored-by: Mor Zusman <morz@ai21.com>
Co-authored-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: Tomer Asida <tomera@ai21.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
2024-07-02 23:11:29 +00:00
Murali Andoorveedu
c5832d2ae9
[Core] Pipeline Parallel Support ( #4412 )
...
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
2024-07-02 10:58:08 -07:00
Alexander Matveev
3476ed0809
[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) ( #5602 )
2024-07-01 20:10:37 -07:00
youkaichao
64e8d2a783
[core][misc] remove logical block ( #5882 )
2024-06-27 13:34:55 -07:00
Cyrus Leung
0e9164b40a
[mypy] Enable type checking for test directory ( #5017 )
2024-06-15 04:45:31 +00:00
leiwen83
1b8a0d71cf
[Core][Bugfix]: fix prefix caching for blockv2 ( #5364 )
...
Signed-off-by: Lei Wen <wenlei03@qiyi.com>
Co-authored-by: Lei Wen <wenlei03@qiyi.com>
2024-06-14 17:23:56 -07:00
Michael Goin
94a07bbdd8
[Bugfix] Fix typo in scheduler.py (requeset -> request) ( #5470 )
2024-06-12 21:59:44 +00:00
Bla_ckB
45f92c00cf
[Bugfix] Fix KeyError: 1 When Using LoRA adapters ( #5164 )
2024-06-09 16:23:14 -07:00
limingshu
dc49fb892c
Addition of lacked ignored_seq_groups in _schedule_chunked_prefill ( #5296 )
2024-06-07 13:35:42 +00:00
Kaiyang Chen
10c38e3e46
[Misc]: Implement CPU/GPU swapping in BlockManagerV2 ( #3834 )
2024-06-03 13:37:11 -07:00
Zhuohan Li
8279078e21
[Bugfix] Remove deprecated @abstractproperty ( #5174 )
2024-06-01 22:40:25 +00:00
afeldman-nm
4238bc82f2
[Core] Cross-attention KV caching and memory-management (towards eventual encoder/decoder model support) ( #4837 )
2024-05-29 16:09:13 +00:00
Michał Moskal
d4f3985907
[Core] Sliding window for block manager v2 ( #4545 )
...
Co-authored-by: Ruth Evans <ruthevans@Ruths-MacBook-Pro.local>
2024-05-28 11:07:07 +09:00
leiwen83
e64fde4b01
[Core][Bugfix]: fix prefix caching for blockv2 ( #4764 )
...
Co-authored-by: Lei Wen <wenlei03@qiyi.com>
2024-05-24 10:07:09 -07:00
Antoni Baum
65ae8c2c8f
[Core] Fix scheduler considering "no LoRA" as "LoRA" ( #4897 )
2024-05-20 17:48:32 -07:00
SangBin Cho
2e9a2227ec
[Lora] Support long context lora ( #4787 )
...
Currently we need to call rotary embedding kernel for each LoRA, which makes it hard to serve multiple long context length LoRA. Add batched rotary embedding kernel and pipe it through.
It replaces the rotary embedding layer to the one that is aware of multiple cos-sin-cache per scaling factors.
Follow up of https://github.com/vllm-project/vllm/pull/3095/files
2024-05-18 16:05:23 +09:00
SangBin Cho
e7c46b9527
[Scheduler] Warning upon preemption and Swapping ( #4647 )
...
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
2024-05-13 23:50:44 +09:00
Chang Su
e254497b66
[Model][Misc] Add e5-mistral-7b-instruct and Embedding API ( #3734 )
2024-05-11 11:30:37 -07:00
youkaichao
20cfcdec99
[Core][Optimization] change python dict to pytorch tensor for blocks to swap ( #4659 )
2024-05-08 12:07:05 -07:00
youkaichao
469f85c782
[Core][Optimization] change copy-on-write from dict[int, list] to list ( #4648 )
2024-05-07 11:06:32 -07:00
youkaichao
63575bc2e1
[Core][Optimization] change python dict to pytorch tensor ( #4607 )
2024-05-06 21:30:27 -07:00
Cody Yu
bc8ad68455
[Misc][Refactor] Introduce ExecuteModelData ( #4540 )
2024-05-03 17:47:07 -07:00
SangBin Cho
0f8a91401c
[Core] Ignore infeasible swap requests. ( #4557 )
2024-05-02 14:31:20 -07:00
