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
98d6682cd1
[VLM] Remove image_input_type from VLM config ( #5852 )
...
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
Co-authored-by: Roger Wang <ywang@roblox.com >
2024-07-02 07:57:09 +00:00
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
Nick Hill
c87ebc3ef9
[BugFix] Ensure worker model loop is always stopped at the right time ( #5987 )
2024-07-01 16:17:58 -07:00
sroy745
80ca1e6a3a
[Speculative Decoding 2/2 ] Integrate typical acceptance sampler into Spec Decode Worker ( #5348 )
2024-07-01 00:33:05 -07:00
Cyrus Leung
51e971d39e
[Bugfix] Support eos_token_id from config.json ( #5954 )
2024-06-29 11:19:02 +00:00
William Lin and Antoni Baum
906a19cdb0
[Misc] Extend vLLM Metrics logging API ( #5925 )
...
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com >
2024-06-29 10:36:06 +08:00
Ilya Lavrenov
57f09a419c
[Hardware][Intel] OpenVINO vLLM backend ( #5379 )
2024-06-28 13:50:16 +00:00
Cyrus Leung and ywang96
5cbe8d155c
[Core] Registry for processing model inputs ( #5214 )
...
Co-authored-by: ywang96 <ywang@roblox.com >
2024-06-28 12:09:56 +00:00
Nick Hill
365791ff81
[BugFix] Fix min_tokens behaviour for multiple eos tokens ( #5849 )
2024-06-27 11:31:11 -07:00
Antoni Baum
67882dbb44
[Core] Add fault tolerance for RayTokenizerGroupPool ( #5748 )
2024-06-25 10:15:10 -07:00
Woo-Yeon Lee
2ce5d6688b
[Speculative Decoding] Support draft model on different tensor-parallel size than target model ( #5414 )
2024-06-25 09:56:06 +00:00
rohithkrn
f5dda63eb5
[LoRA] Add support for pinning lora adapters in the LRU cache ( #5603 )
2024-06-21 15:42:46 -07:00
Michael Goin
8065a7e220
[Frontend] Add FlexibleArgumentParser to support both underscore and dash in names ( #5718 )
2024-06-20 17:00:13 -06:00
zifeitong
78687504f7
[Bugfix] AsyncLLMEngine hangs with asyncio.run ( #5654 )
2024-06-19 13:57:12 -07:00
Michael Goin
afed90a034
[Frontend][Bugfix] Fix preemption_mode -> preemption-mode for CLI arg in arg_utils.py ( #5688 )
2024-06-19 14:41:42 -04:00
Ronen Schaffer
7879f24dcc
[Misc] Add OpenTelemetry support ( #4687 )
...
This PR adds basic support for OpenTelemetry distributed tracing.
It includes changes to enable tracing functionality and improve monitoring capabilities.
I've also added a markdown with print-screens to guide users how to use this feature. You can find it here
2024-06-19 01:17:03 +09:00
728c4c8a06
[Hardware][Intel GPU] Add Intel GPU(XPU) inference backend ( #3814 )
...
Co-authored-by: Jiang Li <jiang1.li@intel.com >
Co-authored-by: Abhilash Majumder <abhilash.majumder@intel.com >
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com >
2024-06-17 11:01:25 -07:00
Cyrus Leung
0e9164b40a
[mypy] Enable type checking for test directory ( #5017 )
2024-06-15 04:45:31 +00:00
Sanger Steel
6e2527a7cb
[Doc] Update documentation on Tensorizer ( #5471 )
2024-06-14 11:27:57 -07:00
Cyrus Leung
77490c6f2f
[Core] Remove duplicate processing in async engine ( #5525 )
2024-06-14 10:04:42 -07:00
Cyrus Leung
03dccc886e
[Misc] Add vLLM version getter to utils ( #5098 )
2024-06-13 11:21:39 -07:00
Woosuk Kwon
1a8bfd92d5
[Hardware] Initial TPU integration ( #5292 )
2024-06-12 11:53:03 -07:00
sasha0552
dcbf4286af
[Frontend] Customizable RoPE theta ( #5197 )
2024-06-11 10:42:26 -07:00
Ali Panahi
00e6a2dc53
[Bugfix] fix lora_dtype value type in arg_utils.py ( #5398 )
2024-06-11 10:40:23 -07:00
maor-ps and DarkLight1337
351d5e7b82
[Bugfix] OpenAI entrypoint limits logprobs while ignoring server defined --max-logprobs ( #5312 )
...
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk >
2024-06-11 10:30:31 +08:00
Nick Hill
a008629807
[Misc] Various simplifications and typing fixes ( #5368 )
2024-06-11 10:29:02 +08:00
Alex Wu
0f83ddd4d7
[Bugfix][Frontend/Core] Don't log exception when AsyncLLMEngine gracefully shuts down. ( #5290 )
2024-06-05 15:18:12 -07:00
Michael Goin
065aff6c16
[Bugfix] Make EngineArgs use named arguments for config construction ( #5285 )
2024-06-05 15:16:56 -07:00
zifeitong
974fc9b845
[Bugfix] Fix prompt_logprobs when SamplingParams.detokenize is set to True ( #5226 )
2024-06-04 19:37:28 -07:00
Kaiyang Chen
10c38e3e46
[Misc]: Implement CPU/GPU swapping in BlockManagerV2 ( #3834 )
2024-06-03 13:37:11 -07:00
Cyrus Leung
7a64d24aad
[Core] Support image processor ( #4197 )
2024-06-02 22:56:41 -07:00
chenqianfzh
b9c0605a8e
[Feature][Kernel] Support bitsandbytes quantization and QLoRA ( #4776 )
2024-06-01 14:51:10 -06:00
Cyrus Leung
a9bcc7afb2
[Doc] Use intersphinx and update entrypoints docs ( #5125 )
2024-05-30 09:59:23 -07:00
Junichi Sato
dfba529b40
[Bugfix] Remove the last EOS token unless explicitly specified ( #5077 )
2024-05-28 17:15:35 -07:00
Cyrus Leung and Roger Wang
5ae5ed1e60
[Core] Consolidate prompt arguments to LLM engines ( #4328 )
...
Co-authored-by: Roger Wang <ywang@roblox.com >
2024-05-28 13:29:31 -07:00
Michał Moskal and Ruth Evans
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
1102bef219
[Bugfix / Core] Prefix Caching Guards (merged with main) ( #4846 )
...
Co-authored-by: rsnm2 <rshaw@neuralmagic.com >
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com >
2024-05-27 15:18:17 -07:00
Nick Hill
eb6d3c264d
[Core] Eliminate parallel worker per-step task scheduling overhead ( #4894 )
2024-05-23 06:17:27 +09:00
Cody Yu
a3a73ab069
[Misc] Load FP8 kv-cache scaling factors from checkpoints ( #4893 )
...
The 2nd PR for #4532 .
This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).
2024-05-22 13:28:20 -07:00
sasha0552
9b9a10d6cb
[Frontend] Dynamic RoPE scaling ( #4638 )
2024-05-22 01:32:35 -04:00
Kante Yin
14772eeb8e
[Bugfix] Fix flag name for max_seq_len_to_capture ( #4935 )
...
Signed-off-by: kerthcet <kerthcet@gmail.com >
2024-05-21 09:30:52 -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
zifeitong
a5675d348b
[Bugfix] Properly set distributed_executor_backend in ParallelConfig ( #4816 )
2024-05-15 07:22:09 -07:00
SangBin Cho
65bf2ac165
[Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API ( #4681 )
...
This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend.
It also refactors subquery_start_loc which was not refactored in the previous PR
2024-05-15 14:00:10 +09:00
Nick Hill and SAHIL SUNEJA
676a99982f
[Core] Add MultiprocessingGPUExecutor ( #4539 )
...
Co-authored-by: SAHIL SUNEJA <suneja@us.ibm.com >
2024-05-14 10:38:59 -07:00
Sanger Steel
8bc68e198c
[Frontend] [Core] perf: Automatically detect vLLM-tensorized model, update tensorizer to version 2.9.0 ( #4208 )
2024-05-13 14:57:07 -07:00
SangBin Cho and Robert Shaw
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
Cyrus Leung
f12b20decc
[Frontend] Move async logic outside of constructor ( #4674 )
2024-05-08 22:48:33 -07:00
Murali Andoorveedu