Jee Jee Li and GitHub
86222a3dab
[VLM] Merged multi-modal processor for GLM4V ( #12449 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com >
2025-02-08 20:32:16 +00:00
youkaichao and GitHub
91dd8f7aa6
[bugfix] respect distributed_executor_backend in world_size=1 ( #12934 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2025-02-08 16:17:08 +08:00
Woosuk Kwon and GitHub
3243158336
[V1] Move KV block hashes from Request to KVCacheManager ( #12922 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
2025-02-07 19:14:10 -08:00
TJian and GitHub
eaa92d4437
[ROCm] [Feature] [Doc] [Dockerfile] [BugFix] Support Per-Token-Activation Per-Channel-Weight FP8 Quantization Inferencing ( #12501 )
2025-02-07 08:13:43 -08:00
0630d4537a
[V1] Logprobs and prompt logprobs support ( #9880 )
...
This PR is adding support for sample logprobs & prompt logprobs to vLLM v1.
New behavior:
- During model execution, model runner computes sample logprobs (if user-provided logprobs setting is not None) and prompt logprobs (if user-provided prompt_logprobs setting is not None). For both sample and prompt logprobs, the engine core returns 3 vectors: token ids, token logprob values, token ranks. Ranks reflect tokens' 1-indexed positions in the vocabulary vector after sorting the vocabulary by log probability in descending order.
- In scheduler.update_from_output(), sample and prompt logprobs are incorporated into the EngineCoreOutput data structure which is transferred to the engine client. If multiprocessing is enabled, then sample and prompt logprobs will be (de)serialized when the EngineCoreOutput data structure is (de)serialized.
- During output processing, the LogprobsProcessor transforms the triplet of token ids, token logprobs values, and token ranks into the OpenAI-compatible List[Dict[token id,Logprob]] format (for sample and prompt logprobs respectively.)
- Each Logprob instance (whether sample- or prompt-) consists of a token's log-probability, rank, and detokenized string representation. Note that logprob detokenization is handled by the LogprobsProcessor not the detokenizer.
Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com >
Signed-off-by: Nick Hill <nhill@redhat.com >
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com >
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com >
Co-authored-by: Nick Hill <nhill@redhat.com >
2025-02-07 07:26:20 -08:00
Cyrus Leung and GitHub
ce26b16268
[Misc] Remove unnecessary detokenization in multimodal processing ( #12868 )
2025-02-07 06:21:17 -08:00
Maximilien de Bayser and GitHub
6e1fc61f0f
Prevent unecessary requests to huggingface hub ( #12837 )
2025-02-06 21:37:41 -08:00
aff404571b
Add Bamba Model ( #10909 )
...
Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com >
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com >
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com >
2025-02-06 15:22:42 -08:00
467a96a541
[V1] LoRA Support ( #10957 )
...
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com >
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com >
2025-02-06 09:32:51 -08:00
youkaichao and GitHub
09b95e36ab
[torch.compile] PyTorch 2.6 and nightly compatibility ( #12393 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2025-02-07 01:09:07 +08:00
Isotr0py and GitHub
85ac82d228
[Kernel] Make rotary_embedding ops more flexible with input shape ( #12777 )
2025-02-06 08:46:13 -08:00
Dipika Sikka and GitHub
7ca9934fe7
[Misc] Update w2 scale loading for GPTQMarlinMoE ( #12757 )
2025-02-06 01:02:14 -08:00
Lu Fang and GitHub
56534cd577
[Bugfix] Fix the test_ultravox.py's license ( #12806 )
...
Signed-off-by: Lu Fang <lufang@fb.com >
2025-02-06 13:25:54 +08:00
Sumit Vij and GitHub
d88506dda4
[Model] LoRA Support for Ultravox model ( #11253 )
2025-02-05 19:54:13 -08:00
Cyrus Leung and GitHub
75404d041b
[VLM] Update compatibility with transformers 4.49
2025-02-05 19:09:45 -08:00
Roger Wang and GitHub
bf3b79efb8
[VLM] Qwen2.5-VL
2025-02-05 13:31:38 -08:00
Rahul Tuli and GitHub
3b2005e1db
Add: Support for Sparse24Bitmask Compressed Models
2025-02-05 13:30:43 -08:00
75e94309e8
[Perf] Mem align KV caches for CUDA devices (MLA perf improvement) ( #12676 )
...
Signed-off-by: simon-mo <xmo@berkeley.edu >
Signed-off-by: Lucas Wilkinson <lcwilkins@redhat.com >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
Co-authored-by: simon-mo <xmo@berkeley.edu >
2025-02-04 18:22:24 -08:00
Mark McLoughlin and GitHub
233df6f5c4
[V1][Metrics] Add request_success_total counter, labelled with finish reason ( #12579 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com >
2025-02-04 19:46:54 -05:00
Cyrus Leung and GitHub
18016a5e62
[Bugfix] Fix CI failures for InternVL and Mantis models ( #12728 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-02-04 23:54:23 +08:00
815079de8e
[VLM] merged multimodal processor and V1 support for idefics3 ( #12660 )
...
Signed-off-by: Isotr0py <2037008807@qq.com >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
2025-02-04 20:00:51 +08:00
Woosuk Kwon and GitHub
18a88fcccc
[V1] Remove scheduling constraint on partial requests ( #12674 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
2025-02-04 02:43:58 -08:00
d1ca7df84d
[VLM] Merged multi-modal processor for InternVL-based models ( #12553 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
Signed-off-by: Isotr0py <2037008807@qq.com >
Co-authored-by: Isotr0py <2037008807@qq.com >
2025-02-04 16:44:52 +08:00
c36ac98d01
[AMD][ROCm] Enable DeepSeek model on ROCm ( #12662 )
...
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com >
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com >
2025-02-04 08:24:11 +00:00
Thomas Parnell and GitHub
bb392af434
[Doc] Replace ibm-fms with ibm-ai-platform ( #12709 )
...
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com >
2025-02-04 07:05:04 +00:00
Russell Bryant and GitHub
73b35cca7f
[Core] Improve hash collision avoidance in prefix caching ( #12621 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com >
2025-02-03 16:28:20 -08:00
Cody Yu and GitHub
5095e96606
[V1] Revert uncache_blocks and support recaching full blocks ( #12415 )
...
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com >
2025-02-03 15:04:53 -08:00
Cody Yu and GitHub
cf58b9c4ca
[MISC] Remove model input dumping when exception ( #12582 )
...
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com >
2025-02-03 13:34:16 -08:00
Russell Bryant and GitHub
33e0602e59
[Misc] Fix improper placement of SPDX header in scripts ( #12694 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com >
2025-02-03 11:16:59 -08:00
a1a2aaadb9
[Model]: Add transformers backend support ( #11330 )
...
# Adds support for `transformers` as a backend
Following https://github.com/huggingface/transformers/pull/35235 , a
bunch of models should already be supported, we are ramping up support
for more models.
Thanks @Isotr0py for the TP support, and @hmellor for his help as well!
This includes:
- `trust_remote_code=True` support: any model on the hub, if it
implements attention the correct way can be natively supported!!
- tensor parallel support
---------
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Signed-off-by: Isotr0py <2037008807@qq.com >
Co-authored-by: Isotr0py <41363108+Isotr0py@users.noreply.github.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Isotr0py <2037008807@qq.com >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
Co-authored-by: Michael Goin <mgoin64@gmail.com >
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2025-02-03 21:30:38 +08:00
youkaichao and GitHub
20579c0fae
make sure mistral_common not imported for non-mistral models ( #12669 )
...
When people use deepseek models, they find that they need to solve cv2
version conflict, see https://zhuanlan.zhihu.com/p/21064432691 .
I added the check, and make all imports of `cv2` lazy.
---------
Signed-off-by: youkaichao <youkaichao@gmail.com >
2025-02-03 13:40:25 +08:00
Russell Bryant and GitHub
e489ad7a21
[Misc] Add SPDX-License-Identifier headers to python source files ( #12628 )
...
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com >
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com >
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com >
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com >
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com >
2025-02-02 11:58:18 -08:00
Shawn Du and GitHub
f8ece6e17f
[Core][v1] Unify allocating slots in prefill and decode in KV cache manager ( #12608 )
...
As mentioned in RFC https://github.com/vllm-project/vllm/issues/12254 ,
this PR achieves the task: combine allocate_slots and append_slots.
There should be no functionality change, except that in decode, also
raise exception when num_tokens is zero (like prefill), and change the
unit test case accordingly.
@comaniac @rickyyx @WoosukKwon @youkaichao @heheda12345 @simon-mo
---------
Signed-off-by: Shawn Du <shawnd200@outlook.com >
2025-02-02 16:40:58 +08:00
Chen Zhang and GitHub
89003c4082
[v1][Bugfix] Add extra_keys to block_hash for prefix caching ( #12603 )
...
This pr adds extra key to block hash, to generate different hash value
for two blocks with the same token string but different extra_keys in
their parent blocks. For example, it can generate different hash value
for the second block of the following two requests:
```python
request1 = make_request(
request_id=0,
prompt_token_ids=[_ for _ in range(6)],
mm_positions=[{
"offset": 0,
"length": 3
}, {
"offset": 3,
"length": 3
}],
mm_hashes=["hash1", "hash2"],
)
request2 = make_request(
request_id=1,
prompt_token_ids=[_ for _ in range(6)],
mm_positions=[{
"offset": 0,
"length": 3
}, {
"offset": 3,
"length": 3
}],
mm_hashes=["hash3", "hash2"],
)
```
---------
Signed-off-by: Chen Zhang <zhangch99@outlook.com >
2025-01-31 13:13:04 -08:00
cabaf4eff3
[Attention] MLA decode optimizations ( #12528 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
Signed-off-by: simon-mo <xmo@berkeley.edu >
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
Co-authored-by: simon-mo <simon.mo@hey.com >
Co-authored-by: Michael Goin <mgoin64@gmail.com >
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com >
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com >
Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com >
Co-authored-by: simon-mo <xmo@berkeley.edu >
2025-01-30 23:49:37 -08:00
Lucas Wilkinson and GitHub
9798b2fb00
[Kernel] Update cutlass_scaled_mm to support 2d group (blockwise) scaling ( #11868 )
2025-01-30 18:33:00 -08:00
Mark McLoughlin and GitHub
f17f1d4608
[V1][Metrics] Add GPU cache usage % gauge ( #12561 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com >
2025-01-29 18:31:01 -08:00
Jinzhen Lin and GitHub
27b78c73ca
[Kernel] add triton fused moe kernel for gptq/awq ( #12185 )
2025-01-29 09:07:09 -05:00
Yanyi Liu and GitHub
ff7424f491
[Frontend] Support override generation config in args ( #12409 )
...
Signed-off-by: liuyanyi <wolfsonliu@163.com >
2025-01-29 01:41:01 -08:00
+30
d93bf4da85
[Model] Refactoring of MiniCPM-V and add MiniCPM-o-2.6 support for vLLM ( #12069 )
...
Signed-off-by: hzh <hezhihui_thu@163.com >
Signed-off-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com >
Signed-off-by: shaochangxu.scx <shaochangxu.scx@antgroup.com >
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
Signed-off-by: NickLucche <nlucches@redhat.com >
Signed-off-by: Isotr0py <2037008807@qq.com >
Signed-off-by: Roger Wang <ywang@roblox.com >
Signed-off-by: Rafael Vasquez <rafvasq21@gmail.com >
Signed-off-by: Akshat Tripathi <akshat@krai.ai >
Signed-off-by: Oleg Mosalov <oleg@krai.ai >
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com >
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com >
Signed-off-by: Yida Wu <yidawu@alumni.cmu.edu >
Signed-off-by: Chenguang Li <757486878@qq.com >
Signed-off-by: youkaichao <youkaichao@gmail.com >
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com >
Signed-off-by: Chen Zhang <zhangch99@outlook.com >
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Signed-off-by: Shanshan Shen <467638484@qq.com >
Signed-off-by: elijah <f1renze.142857@gmail.com >
Signed-off-by: Yikun <yikunkero@gmail.com >
Signed-off-by: mgoin <michael@neuralmagic.com >
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
Signed-off-by: Konrad Zawora <kzawora@habana.ai >
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com >
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com >
Signed-off-by: Rui Qiao <ruisearch42@gmail.com >
Co-authored-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com >
Co-authored-by: shaochangxu <85155497+shaochangxu@users.noreply.github.com >
Co-authored-by: shaochangxu.scx <shaochangxu.scx@antgroup.com >
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk >
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com >
Co-authored-by: sixgod <evethwillbeok@outlook.com >
Co-authored-by: Isotr0py <2037008807@qq.com >
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com >
Co-authored-by: Rafael Vasquez <rafvasq21@gmail.com >
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
Co-authored-by: Akshat Tripathi <Akshat.tripathi6568@gmail.com >
Co-authored-by: Oleg Mosalov <oleg@krai.ai >
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com >
Co-authored-by: Avshalom Manevich <12231371+avshalomman@users.noreply.github.com >
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com >
Co-authored-by: Yangcheng Li <liyangcheng.lyc@alibaba-inc.com >
Co-authored-by: Siyuan Li <94890248+liaoyanqing666@users.noreply.github.com >
Co-authored-by: Concurrensee <yida.wu@amd.com >
Co-authored-by: Chenguang Li <757486878@qq.com >
Co-authored-by: youkaichao <youkaichao@gmail.com >
Co-authored-by: Alex Brooks <alex.brooks@ibm.com >
Co-authored-by: Chen Zhang <zhangch99@outlook.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Shanshan Shen <467638484@qq.com >
Co-authored-by: elijah <30852919+e1ijah1@users.noreply.github.com >
Co-authored-by: Yikun Jiang <yikunkero@gmail.com >
Co-authored-by: Steve Luo <36296769+SunflowerAries@users.noreply.github.com >
Co-authored-by: mgoin <michael@neuralmagic.com >
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
Co-authored-by: Konrad Zawora <kzawora@habana.ai >
Co-authored-by: TJian <tunjian1996@gmail.com >
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com >
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com >
Co-authored-by: maang-h <55082429+maang-h@users.noreply.github.com >
Co-authored-by: Elfie Guo <164945471+elfiegg@users.noreply.github.com >
Co-authored-by: Rui Qiao <161574667+ruisearch42@users.noreply.github.com >
Co-authored-by: Roger Wang <ywang@roblox.com >
2025-01-29 09:24:59 +00:00
036ca94c25
[Bugfix] handle alignment of arguments in convert_sparse_cross_attention_mask_to_dense ( #12347 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com >
Signed-off-by: Wallas Santos <wallashss@ibm.com >
Co-authored-by: Wallas Santos <wallashss@ibm.com >
2025-01-29 08:54:35 +00:00
Mark McLoughlin and GitHub
46fb056749
[V1][Metrics] Add TTFT and TPOT histograms ( #12530 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com >
2025-01-29 04:11:16 +00:00
a7e3eba66f
[Frontend] Support reasoning content for deepseek r1 ( #12473 )
...
Signed-off-by: Ce Gao <cegao@tensorchord.ai >
Co-authored-by: Rafael Vasquez <rafvasq21@gmail.com >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
Co-authored-by: Michael Goin <mgoin@redhat.com >
2025-01-29 11:38:08 +08:00
Mark McLoughlin and GitHub
c386c43ca3
[V1][Metrics] Add per-request prompt/generation_tokens histograms ( #12516 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com >
2025-01-28 22:07:22 +00:00
Mark McLoughlin and GitHub
3fd1fb63ef
[V1][Metrics] Hook up IterationStats for Prometheus metrics ( #12478 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com >
2025-01-28 16:38:38 +00:00
Cyrus Leung and GitHub
8f58a51358
[VLM] Merged multi-modal processor and V1 support for Qwen-VL ( #12504 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-01-28 16:25:05 +00:00
Gabriel Marinho and GitHub
0f465ab533
[FEATURE] Enables offline /score for embedding models ( #12021 )
...
Signed-off-by: Gabriel Marinho <gmarinho@ibm.com >
2025-01-28 11:30:13 +08:00
ddee88d0ff
[Neuron][Kernel] NKI-based flash-attention kernel with paged KV cache ( #11277 )
...
Signed-off-by: Liangfu Chen <liangfc@amazon.com >
Co-authored-by: Jiangfei Duan <jfduan@outlook.com >
2025-01-27 17:31:16 -08:00
Harry Mellor and GitHub
823ab79633
Update pre-commit hooks ( #12475 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-01-27 17:23:08 -07:00
6116ca8cd7
[Feature] [Spec decode]: Enable MLPSpeculator/Medusa and prompt_logprobs with ChunkedPrefill ( #10132 )
...
Signed-off-by: NickLucche <nlucches@redhat.com >
Signed-off-by: wallashss <wallashss@ibm.com >
Co-authored-by: wallashss <wallashss@ibm.com >
2025-01-27 13:38:35 -08:00
