423330263b
[Feature] Pluggable platform-specific scheduler ( #13161 )
...
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <Yannick.Schnider1@ibm.com>
2025-02-19 17:16:38 +08:00
caf7ff4456
[V1][Core] Generic mechanism for handling engine utility ( #13060 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-02-19 17:09:22 +08:00
f525c0be8b
[Model][Speculative Decoding] DeepSeek MTP spec decode ( #12755 )
...
Signed-off-by: Lu Fang <fanglu@fb.com>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2025-02-19 17:06:23 +08:00
983a40a8bb
[Bugfix] Fix Positive Feature Layers in Llava Models ( #13514 )
...
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
2025-02-19 08:50:07 +00:00
d5d214ac7f
[1/n][CI] Load models in CI from S3 instead of HF ( #13205 )
...
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
2025-02-19 07:34:59 +00:00
30172b4947
[V1] Optimize handling of sampling metadata and req_ids list ( #13244 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-02-18 12:15:33 -08:00
a4d577b379
[V1][Tests] Adding additional testing for multimodal models to V1 ( #13308 )
...
Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
2025-02-18 09:53:14 -08:00
3809458456
[Bugfix] Fix invalid rotary embedding unit test ( #13431 )
...
Signed-off-by: Liangfu Chen <liangfc@amazon.com>
2025-02-18 11:52:03 +00:00
b53d79983c
Add outlines fallback when JSON schema has enum ( #13449 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-02-18 06:49:41 +00:00
67ef8f666a
[Model] Enable quantization support for `transformers` backend ( #12960 )
2025-02-17 19:52:47 -08:00
cd4a72a28d
[V1][Spec decode] Move drafter to model runner ( #13363 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-17 15:40:12 -08:00
4c21ce9eba
[V1] Get input tokens from scheduler ( #13339 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-17 11:01:07 -08:00
1f69c4a892
[Model] Support Mamba2 (Codestral Mamba) ( #9292 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
2025-02-17 20:17:50 +08:00
46cdd59577
[Feature][Spec Decode] Simplify the use of Eagle Spec Decode ( #12304 )
...
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-02-16 19:32:26 -08:00
5d2965b7d7
[Bugfix] Fix 2 Node and Spec Decode tests ( #13341 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-02-16 22:20:22 +08:00
124776ebd5
[ci] skip failed tests for flashinfer ( #13352 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-02-16 22:09:15 +08:00
dc0f7ccf8b
[BugFix] Enhance test_pos_encoding to support execution on multi-devices ( #13187 )
...
Signed-off-by: wchen61 <wchen61@foxmail.com>
2025-02-16 08:59:49 +00:00
80f63a3966
[V1][Spec Decode] Ngram Spec Decode ( #12193 )
...
Signed-off-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2025-02-15 18:05:11 -08:00
9206b3d7ec
[V1][PP] Run engine busy loop with batch queue ( #13064 )
2025-02-15 03:59:01 -08:00
2ad1bc7afe
[V1][Metrics] Add iteration_tokens_total histogram from V0 ( #13288 )
2025-02-15 03:56:19 -08:00
e7eea5a520
[V1][CI] Fix failed v1-test because of min_p ( #13316 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-14 17:29:51 -08:00
a12934d3ec
[V1][Core] min_p sampling support ( #13191 )
...
Signed-off-by: Aoyu <aoyuzhan@amazon.com>
Co-authored-by: Aoyu <aoyuzhan@amazon.com>
2025-02-14 15:50:05 -08:00
3bcb8c75da
[Core] Reduce TTFT with concurrent partial prefills ( #10235 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2025-02-14 15:36:07 -08:00
5e5c8e091e
[Quant][Perf] Use moe_wna16 kernel by default for MoEs with many experts ( #13236 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-02-14 12:53:42 -08:00
6224a9f620
Support logit_bias in v1 Sampler ( #13079 )
2025-02-14 04:34:59 -08:00
45f90bcbba
[WIP] TPU V1 Support Refactored ( #13049 )
2025-02-14 00:21:53 -08:00
b0ccfc565a
[Bugfix][V1] GPUModelRunner._update_states should return True when there is a finished request in batch ( #13126 )
2025-02-13 22:39:20 -08:00
cbc40128eb
[V1] LoRA - Enable Serving Usecase ( #12883 )
...
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2025-02-14 14:21:12 +08:00
f2b20fe491
Consolidate Llama model usage in tests ( #13094 )
2025-02-13 22:18:03 -08:00
09545c0a94
[Bugfix/CI] Turn test_compressed_tensors_2of4_sparse back on ( #13250 )
2025-02-13 20:19:25 -08:00
c1e37bf71b
[Kernel][Bugfix] Refactor and Fix CUTLASS 2:4 Sparse Kernels ( #13198 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2025-02-14 00:01:14 +00:00
d84cef76eb
[Frontend] Add `/v1/audio/transcriptions` OpenAI API endpoint ( #12909 )
2025-02-13 07:23:45 -08:00
37dfa60037
[Bugfix] Missing Content Type returns 500 Internal Server Error ( #13193 )
2025-02-13 06:52:22 -08:00
1bc3b5e71b
[VLM] Separate text-only and vision variants of the same model architecture ( #13157 )
2025-02-13 06:19:15 -08:00
c9d3ecf016
[VLM] Merged multi-modal processor for Molmo ( #12966 )
2025-02-13 04:34:00 -08:00
9605c1256e
[V1][core] Implement pipeline parallel on Ray ( #12996 )
2025-02-13 08:02:46 +00:00
04f50ad9d1
[Bugfix] deepseek_r1_reasoning_parser put reason content in wrong field in certain edge case ( #13097 )
2025-02-12 23:11:26 -08:00
bc55d13070
[VLM] Implement merged multimodal processor for Mllama ( #11427 )
2025-02-12 20:26:21 -08:00
4fc5c23bb6
[NVIDIA] Support nvfp4 quantization ( #12784 )
2025-02-12 19:51:51 -08:00
14b7899d10
[CI] Fix failing FP8 cpu offload test ( #13170 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-02-12 19:16:06 +00:00
36a08630e8
[CORE] [QUANT] Support for GPTQModel's `dynamic` quantization per module override/control ( #7086 )
2025-02-12 09:19:43 -08:00
82cabf53a3
[Misc] Delete unused LoRA modules ( #13151 )
2025-02-12 08:58:24 -08:00
314cfade02
[Frontend] Generate valid tool call IDs when using `tokenizer-mode=mistral` ( #12332 )
2025-02-12 08:29:56 -08:00
e92694b6fe
[Neuron][Kernel] Support Longer Sequences in NKI-based Flash PagedAttention and Improve Efficiency ( #12921 )
...
Signed-off-by: Lingfan Yu <lingfany@amazon.com>
2025-02-11 21:12:37 -08:00
974dfd4971
[Model] IBM/NASA Prithvi Geospatial model ( #12830 )
2025-02-11 20:34:30 -08:00
3ee696a63d
[RFC][vllm-API] Support tokenizer registry for customized tokenizer in vLLM ( #12518 )
...
Signed-off-by: Keyun Tong <tongkeyun@gmail.com>
2025-02-12 12:25:58 +08:00
6c4dbe23eb
[BugFix] Pop instead of del CUDA_VISIBLE_DEVICES ( #12962 )
...
Signed-off-by: Hollow Man <hollowman@opensuse.org>
2025-02-12 00:21:50 +08:00
75e6e14516
[V1][Metrics] Add several request timing histograms ( #12644 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-02-11 10:14:00 -05:00
110f59a33e
[Bugfix] fix flaky test ( #13089 )
...
Signed-off-by: மனோஜ்குமார் பழனிச்சாமி <smartmanoj42857@gmail.com>
2025-02-11 14:41:20 +00:00
41c5dd45b9
[V1][Metrics] Add GPU prefix cache hit rate % gauge ( #12592 )
2025-02-11 08:27:25 +00:00
fc6485d277
[Bugfix]: Reasoning output bug according to the chat template change ( #13025 )
...
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
2025-02-11 15:49:03 +08:00
78a141d768
[Misc] LoRA - Refactor Punica ops tests ( #12970 )
...
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2025-02-11 07:26:03 +00:00
cb080f32e3
[Bugfix] Support missing tool parameters in mistral tokenizer ( #12884 )
...
Signed-off-by: Florian Greinacher <florian.greinacher@siemens.com>
2025-02-11 03:33:33 +00:00
08b2d845d6
[Model] Ultravox Model: Support v0.5 Release ( #12912 )
...
Signed-off-by: Farzad Abdolhosseini <farzad@fixie.ai>
2025-02-10 22:02:48 +00:00
2ae889052c
Fix seed parameter behavior in vLLM ( #13007 )
...
Signed-off-by: மனோஜ்குமார் பழனிச்சாமி <smartmanoj42857@gmail.com>
2025-02-10 23:26:50 +08:00
51f0b5f7f6
[Bugfix] Clean up and fix multi-modal processors ( #13012 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-02-10 10:45:21 +00:00
b2496bb07f
[core] fix sleep mode and pytorch checkpoint compatibility ( #13001 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-02-10 13:03:43 +08:00
59fff4a01a
[core] improve error handling when wake up from sleep mode ( #12981 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-02-10 09:38:57 +08:00
cf797aa856
[core] port pynvml into vllm codebase ( #12963 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-02-09 15:00:00 +08:00
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
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
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
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
ce26b16268
[Misc] Remove unnecessary detokenization in multimodal processing ( #12868 )
2025-02-07 06:21:17 -08:00
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
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
85ac82d228
[Kernel] Make rotary_embedding ops more flexible with input shape ( #12777 )
2025-02-06 08:46:13 -08:00
7ca9934fe7
[Misc] Update w2 scale loading for GPTQMarlinMoE ( #12757 )
2025-02-06 01:02:14 -08:00
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
d88506dda4
[Model] LoRA Support for Ultravox model ( #11253 )
2025-02-05 19:54:13 -08:00
75404d041b
[VLM] Update compatibility with transformers 4.49
2025-02-05 19:09:45 -08:00
bf3b79efb8
[VLM] Qwen2.5-VL
2025-02-05 13:31:38 -08:00
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
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
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
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
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
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
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
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
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
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
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
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
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
9798b2fb00
[Kernel] Update `cutlass_scaled_mm` to support 2d group (blockwise) scaling ( #11868 )
2025-01-30 18:33:00 -08:00
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
27b78c73ca
[Kernel] add triton fused moe kernel for gptq/awq ( #12185 )
2025-01-29 09:07:09 -05:00
ff7424f491
[Frontend] Support override generation config in args ( #12409 )
...
Signed-off-by: liuyanyi <wolfsonliu@163.com>
2025-01-29 01:41:01 -08:00
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
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
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
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
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
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
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
2bc3fbba0c
[FlashInfer] Upgrade to 0.2.0 ( #11194 )
...
Signed-off-by: Bowen Wang <abmfy@icloud.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2025-01-27 18:19:24 +00:00
3f1fc7425a
[V1][CI/Test] Do basic test for top-p & top-k sampling ( #12469 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-01-27 09:40:04 -08:00
01ba927040
[V1][Metrics] Add initial Prometheus logger ( #12416 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-01-27 12:26:28 -05:00
0cc6b383d7
[Frontend] Support scores endpoint in run_batch ( #12430 )
...
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
2025-01-27 04:30:17 +00:00
0034b09ceb
[Frontend] Rerank API (Jina- and Cohere-compatible API) ( #12376 )
...
Signed-off-by: Kyle Mistele <kyle@mistele.com>
2025-01-26 19:58:45 -07:00
72f4880425
[Bugfix/CI] Fix broken kernels/test_mha.py ( #12450 )
2025-01-26 10:39:03 -08:00
aa2cd2c43d
[Bugfix] Disable w16a16 2of4 sparse CompressedTensors24 ( #12417 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
2025-01-26 19:59:58 +08:00
9ddc35220b
[Frontend] generation_config.json for maximum tokens( #12242 )
...
Signed-off-by: Matthew Hendrey <matthew.hendrey@gmail.com>
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: shangmingc <caishangming@linux.alibaba.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Yuan Tang <terrytangyuan@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-01-26 19:59:25 +08:00
f1fc0510df
[Misc] Add FA2 support to ViT MHA layer ( #12355 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-25 15:07:35 +08:00
df5dafaa5b
[Misc] Remove deprecated code ( #12383 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-24 14:45:20 -05:00
ab5bbf5ae3
[Bugfix][Kernel] Fix CUDA 11.8 being broken by FA3 build ( #12375 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-01-24 15:27:59 +00:00
24b0205f58
[V1][Frontend] Coalesce bunched `RequestOutput`s ( #12298 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
2025-01-23 17:17:41 -08:00
e97f802b2d
[FP8][Kernel] Dynamic kv cache scaling factors computation ( #11906 )
...
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
2025-01-23 18:04:03 +00:00
978b45f399
[Kernel] Flash Attention 3 Support ( #12093 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-01-23 06:45:48 -08:00
f0ef37233e
[V1] Add `uncache_blocks` ( #12333 )
2025-01-23 04:19:21 +00:00
68c4421b6d
[AMD][Quantization] Add TritonScaledMMLinearKernel since int8 is broken for AMD ( #12282 )
...
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
2025-01-23 00:10:37 +00:00
7206ce4ce1
[Core] Support `reset_prefix_cache` ( #12284 )
2025-01-22 18:52:27 +00:00
68ad4e3a8d
[Core] Support fully transparent sleep mode ( #11743 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-22 14:39:32 +08:00
64ea24d0b3
[ci/lint] Add back default arg for pre-commit ( #12279 )
...
Signed-off-by: kevin <kevin@anyscale.com>
2025-01-22 01:15:27 +00:00
df76e5af26
[VLM] Simplify post-processing of replacement info ( #12269 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-21 16:48:13 -08:00
347eeebe3b
[Misc] Remove experimental dep from tracing.py ( #12007 )
...
Signed-off-by: Adrian Cole <adrian.cole@elastic.co>
2025-01-21 11:51:55 -08:00
18fd4a8331
[Bugfix] Multi-sequence broken ( #11898 )
...
Signed-off-by: Andy Lo <andy@mistral.ai>
2025-01-21 11:51:35 -08:00
132a132100
[v1][stats][1/n] Add RequestStatsUpdate and RequestStats types ( #10907 )
...
Signed-off-by: rickyx <rickyx@anyscale.com>
2025-01-21 11:51:13 -08:00
5fe6bf29d6
[BugFix] Fix GGUF tp>1 when vocab_size is not divisible by 64 ( #12230 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-01-21 12:23:14 +08:00
18572e3384
[Bugfix] Fix `HfExampleModels.find_hf_info` ( #12223 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-20 15:35:36 +00:00
b37d82791e
[Model] Upgrade Aria to transformers 4.48 ( #12203 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-20 17:58:48 +08:00
59a0192fb9
[Core] Interface for accessing model from `VllmRunner` ( #10353 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-20 15:00:59 +08:00
83609791d2
[Model] Add Qwen2 PRM model support ( #12202 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-20 14:59:46 +08:00
bbe5f9de7d
[Model] Support for fairseq2 Llama ( #11442 )
...
Signed-off-by: Martin Gleize <mgleize@meta.com>
Co-authored-by: mgleize user <mgleize@a100-st-p4de24xlarge-4.fair-a100.hpcaas>
2025-01-19 10:40:40 -08:00
81763c58a0
[V1] Add V1 support of Qwen2-VL ( #12128 )
...
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: imkero <kerorek@outlook.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-19 19:52:13 +08:00
32eb0da808
[Misc] Support register quantization method out-of-tree ( #11969 )
2025-01-18 16:13:16 -08:00
02798ecabe
[Model] Port deepseek-vl2 processor, remove dependency ( #12169 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-18 13:59:39 +08:00
da02cb4b27
[core] further polish memory profiling ( #12126 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-18 12:25:08 +08:00
58fd57ff1d
[Bugfix] Fix score api for missing max_model_len validation ( #12119 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com>
2025-01-17 16:24:22 +00:00
87a0c076af
[core] allow callable in collective_rpc ( #12151 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-17 20:47:01 +08:00
07934cc237
[Misc][LoRA] Improve the readability of LoRA error messages ( #12102 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-17 19:32:28 +08:00
69d765f5a5
[V1] Move more control of kv cache initialization from model_executor to EngineCore ( #11960 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2025-01-17 07:39:35 +00:00
d75ab55f10
[Misc] Add deepseek_vl2 chat template ( #12143 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-17 06:34:48 +00:00
62b06ba23d
[Model] Add support for deepseek-vl2-tiny model ( #12068 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-16 17:14:48 +00:00
874f7c292a
[Bugfix] Fix max image feature size for Llava-one-vision ( #12104 )
...
Signed-off-by: Roger Wang <ywang@roblox.com>
2025-01-16 14:54:06 +00:00
bf53e0c70b
Support torchrun and SPMD-style offline inference ( #12071 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-16 19:58:53 +08:00
dd7c9ad870
[Bugfix] Remove hardcoded `head_size=256` for Deepseek v2 and v3 ( #12067 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-16 10:11:54 +00:00
edce722eaa
[Bugfix] use right truncation for non-generative tasks ( #12050 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2025-01-16 00:31:01 +08:00
de0526f668
[Misc][Quark] Upstream Quark format to VLLM ( #10765 )
...
Signed-off-by: kewang-xlnx <kewang@xilinx.com>
Signed-off-by: kewang2 <kewang2@amd.com>
Co-authored-by: kewang2 <kewang2@amd.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2025-01-15 11:05:15 -05:00
97eb97b5a4
[Model]: Support internlm3 ( #12037 )
2025-01-15 11:35:17 +00:00
3adf0ffda8
[Platform] Do not raise error if _Backend is not found ( #12023 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
2025-01-15 10:14:15 +00:00
994fc655b7
[V1][Prefix Cache] Move the logic of num_computed_tokens into KVCacheManager ( #12003 )
2025-01-15 07:55:30 +00:00
ad34c0df0f
[core] platform agnostic executor via collective_rpc ( #11256 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-15 13:45:21 +08:00
0794e7446e
[Misc] Add multipstep chunked-prefill support for FlashInfer ( #10467 )
2025-01-15 12:47:49 +08:00
42f5e7c52a
[Kernel] Support MulAndSilu ( #11624 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-15 02:29:53 +00:00
bb354e6b2d
[Bugfix] Fix various bugs in multi-modal processor ( #12031 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-14 12:16:11 +00:00
f7b3ba82c3
[MISC] fix typo in kv transfer send recv test ( #11983 )
2025-01-13 05:07:48 +00:00
619ae268c3
[V1] [2/n] Logging and Metrics - `OutputProcessor` Abstraction ( #11973 )
...
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
2025-01-13 04:54:10 +00:00
d14e98d924
[Model] Support GGUF models newly added in `transformers` 4.46.0 ( #9685 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-01-13 00:13:44 +00:00
9597a095f2
[V1][Core][1/n] Logging and Metrics ( #11962 )
...
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
2025-01-12 21:02:02 +00:00
263a870ee1
[Hardware][TPU] workaround fix for MoE on TPU ( #11764 )
2025-01-12 10:53:51 -05:00
8bddb73512
[Hardware][CPU] Multi-LoRA implementation for the CPU backend ( #11100 )
...
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>
Co-authored-by: Oleg Mosalov <oleg@krai.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2025-01-12 13:01:52 +00:00
f967e51f38
[Model] Initialize support for Deepseek-VL2 models ( #11578 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-01-12 00:17:24 -08:00
d697dc01b4
[Bugfix] Fix RobertaModel loading ( #11940 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-01-11 14:05:09 +00:00
a991f7d508
[Doc] Basic guide for writing unit tests for new models ( #11951 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-11 21:27:24 +08:00
7a3a83e3b8
[CI/Build] Move model-specific multi-modal processing tests ( #11934 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-11 13:50:05 +08:00
899136b857
[ci] fix broken distributed-tests-4-gpus ( #11937 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-11 09:07:24 +08:00
aa1e77a19c
[Hardware][CPU] Support MOE models on x86 CPU ( #11831 )
...
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-01-10 11:07:58 -05:00
482cdc494e
[Doc] Rename offline inference examples ( #11927 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-01-10 23:50:29 +08:00
241ad7b301
[ci] Fix sampler tests ( #11922 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-10 20:45:33 +08:00
d85c47d6ad
Replace "online inference" with "online serving" ( #11923 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-01-10 12:05:56 +00:00
ac2f3f7fee
[Bugfix] Validate lora adapters to avoid crashing server ( #11727 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-10 15:56:36 +08:00
cf5f000d21
[torch.compile] Hide KV cache behind torch.compile boundary ( #11677 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-01-10 13:14:42 +08:00
b844b99ad3
[VLM] Enable tokenized inputs for merged multi-modal processor ( #11900 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-10 03:24:00 +00:00
9a228348d2
[Misc] Provide correct Pixtral-HF chat template ( #11891 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-09 10:19:37 -07:00
bd82872211
[ci]try to fix flaky multi-step tests ( #11894 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-09 14:47:29 +00:00
405eb8e396
[platform] Allow platform specify attention backend ( #11609 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
2025-01-09 21:46:50 +08:00
0bd1ff4346
[Bugfix] Override dunder methods of placeholder modules ( #11882 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-09 09:02:53 +00:00
1fe554bac3
treat do_lower_case in the same way as the sentence-transformers library ( #11815 )
...
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
2025-01-09 11:05:43 +08:00
615e4a5401
[CI] Turn on basic correctness tests for V1 ( #10864 )
2025-01-08 21:20:44 -05:00
56fe4c297c
[TPU][Quantization] TPU `W8A8` ( #11785 )
...
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-01-08 19:33:29 +00:00
aba8d6ee00
[Doc] Move examples into categories ( #11840 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-01-08 13:09:53 +00:00
2a0596bc48
[VLM] Reorganize profiling/processing-related code ( #11812 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-08 18:59:58 +08:00
889e662eae
[misc] improve memory profiling ( #11809 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-01-08 06:36:03 +00:00
8f37be38eb
[Bugfix] Comprehensively test and fix LLaVA-NeXT feature size calculation ( #11800 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-07 18:25:02 +08:00
b278557935
[Kernel][LoRA]Punica prefill kernels fusion ( #11234 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Abatom <abzhonghua@gmail.com>
Co-authored-by: Zhonghua Deng <abatom@163.com>
2025-01-07 04:01:39 +00:00
08fb75c72e
[Bugfix] Fix LLaVA-NeXT feature size precision error (for real) ( #11772 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-07 01:10:54 +00:00
91b361ae89
[V1] Extend beyond image modality and support mixed-modality inference with Llava-OneVision ( #11685 )
...
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-06 19:58:16 +00:00
e20c92bb61
[Kernel] Move attn_type to Attention.__init__() ( #11690 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-01-07 00:11:28 +08:00
32c9eff2ff
[Bugfix][V1] Fix molmo text-only inputs ( #11676 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-06 15:22:25 +00:00
996357e480
[VLM] Separate out profiling-related logic ( #11746 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-06 16:02:21 +08:00
022c5c6944
[V1] Refactor get_executor_cls ( #11754 )
2025-01-06 07:59:16 +00:00
9e764e7b10
[distributed] remove pynccl's redundant change_state ( #11749 )
2025-01-06 09:05:48 +08:00
635b897246
[distributed] remove pynccl's redundant stream ( #11744 )
2025-01-05 23:09:11 +08:00
47831430cc
[Bugfix][V1] Fix test_kv_cache_utils.py ( #11738 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-04 16:07:59 +00:00
ba214dffbe
[Bugfix] Fix precision error in LLaVA-NeXT ( #11735 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-04 23:45:57 +08:00
eed11ebee9
[VLM] Merged multi-modal processors for LLaVA-NeXT-Video and LLaVA-OneVision ( #11717 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-04 11:40:53 +00:00
300acb8347
[Core][Bugfix] Use correct device to initialize GPU data during CUDA-graph-capture ( #11233 )
...
Signed-off-by: Yan Burman <yanburman@users.noreply.github.com>
Signed-off-by: Ido Asraff <idoa@atero.ai>
2025-01-04 14:50:16 +08:00
d91457d529
[V1] Add kv cache utils tests. ( #11513 )
...
Signed-off-by: xcnick <xcnick0412@gmail.com>
2025-01-04 14:49:46 +08:00
80c751e7f6
[V1] Simplify Shutdown ( #11659 )
2025-01-03 17:25:38 +00:00
e1a5c2f0a1
[Model] Whisper model implementation ( #11280 )
...
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com>
2025-01-03 16:39:19 +08:00
8c38ee7007
[VLM] Merged multi-modal processor for LLaVA-NeXT ( #11682 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-02 16:39:27 +00:00
a115ac46b5
[VLM] Move supported limits and max tokens to merged multi-modal processor ( #11669 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2025-01-01 15:44:42 +00:00
73001445fb
[V1] Implement Cascade Attention ( #11635 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-01-01 21:56:46 +09:00
11d8a091c6
[Misc] Optimize Qwen2-VL LoRA test ( #11663 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-01 14:42:23 +08:00
365801fedd
[VLM] Add max-count checking in data parser for single image models ( #11661 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-12-31 22:15:21 -08:00
4db72e57f6
[Bugfix][Refactor] Unify model management in frontend ( #11660 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2025-01-01 02:21:51 +00:00
e7c7c5e822
[V1][VLM] V1 support for selected single-image models. ( #11632 )
...
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Isotr0py <2037008807@qq.com>
2024-12-31 21:17:22 +00:00
8c3230d8c1
[V1] Simpify vision block hash for prefix caching by removing offset from hash ( #11646 )
2024-12-31 08:56:01 +00:00
2c5718809b
[Bugfix] Move the _touch(computed_blocks) call in the allocate_slots method to after the check for allocating new blocks. ( #11565 )
2024-12-31 06:29:04 +00:00
82c49d3260
[Misc][LoRA] Support Rank Stabilized LoRA (RSLoRA) ( #6909 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-30 22:15:58 -08:00
74fa1d123c
[Bugfix] Fix OpenAI parallel sampling when using xgrammar ( #11637 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-12-31 03:43:54 +00:00
b12e87f942
[platforms] enable platform plugins ( #11602 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-30 20:24:45 +08:00
3682e33f9f
[v1] fix compilation cache ( #11598 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-30 04:24:12 +00:00
4fb8e329fd
[V1] [5/N] API Server: unify `Detokenizer` and `EngineCore` input ( #11545 )
...
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
2024-12-28 20:51:57 +00:00
328841d002
[bugfix] interleaving sliding window for cohere2 model ( #11583 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-28 16:55:42 +00:00
d34be24bb1
[Model] Support InternLM2 Reward models ( #11571 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-12-28 06:14:10 +00:00
df04dffade
[V1] [4/N] API Server: ZMQ/MP Utilities ( #11541 )
2024-12-28 01:45:08 +00:00
55509c2114
[MODEL] LoRA support for Jamba model ( #11209 )
...
Signed-off-by: Erez Schwartz <erezs@ai21.com>
2024-12-27 17:58:21 +00:00
101418096f
[VLM] Support caching in merged multi-modal processor ( #11396 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-27 17:22:48 +00:00
7af553ea30
[Misc] Abstract the logic for reading and writing media content ( #11527 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-27 19:21:23 +08:00
46d4359450
[CI] Fix broken CI ( #11543 )
2024-12-26 18:49:16 -08:00
371d04d39b
[V1] Use FlashInfer Sampling Kernel for Top-P & Top-K Sampling ( #11394 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-12-27 09:32:38 +09:00
2072924d14
[Model] [Quantization] Support deepseek_v3 w8a8 fp8 block-wise quantization ( #11523 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: HandH1998 <1335248067@qq.com>
2024-12-26 15:33:30 -08:00
eec906d811
[Misc] Add placeholder module ( #11501 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-26 13:12:51 +00:00
dcb1a944d4
[V1] Adding min tokens/repetition/presence/frequence penalties to V1 sampler ( #10681 )
...
Signed-off-by: Sourashis Roy <sroy@roblox.com>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-12-26 19:02:58 +09:00
aa25985bd1
[Misc][LoRA] Fix LoRA weight mapper ( #11495 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-26 15:52:48 +08:00
51a624bf02
[Misc] Move some multimodal utils to modality-specific modules ( #11494 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-26 04:23:20 +00:00
fc601665eb
[Misc] Update disaggregation benchmark scripts and test logs ( #11456 )
...
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
2024-12-25 06:58:48 +00:00
9832e5572a
[V1] Unify VLLM_ENABLE_V1_MULTIPROCESSING handling in RayExecutor ( #11472 )
2024-12-24 19:49:46 -08:00
3f3e92e1f2
[Model] Automatic conversion of classification and reward models ( #11469 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-24 18:22:22 +00:00
196c34b0ac
[Misc] Move weights mapper ( #11443 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-24 13:05:25 +00:00
b1b1038fbd
[Bugfix] Fix Qwen2-VL LoRA weight loading ( #11430 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-24 09:56:10 +00:00
9edca6bf8f
[Frontend] Online Pooling API ( #11457 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-24 17:54:30 +08:00
a491d6f535
[V1] TP Ray executor ( #11107 )
...
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2024-12-23 23:00:12 +00:00
63afbe9215
[CI] Expand OpenAI test_chat.py guided decoding tests ( #11048 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-12-23 18:35:38 +00:00
8cef6e02dc
[Misc] add w8a8 asym models ( #11075 )
2024-12-23 13:33:20 -05:00
5bfb30a529
[Bugfix] Fix CFGGuide and use outlines for grammars that can't convert to GBNF ( #11389 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-12-23 23:06:20 +08:00
f1d1bf6288
[Bugfix] Fix fully sharded LoRAs with Mixtral ( #11390 )
...
Signed-off-by: Jason Greene <jason.greene@redhat.com>
2024-12-22 23:25:10 +08:00
29c748930e
[CI] Fix flaky entrypoint tests ( #11403 )
...
Signed-off-by: Roger Wang <ywang@roblox.com>
2024-12-21 21:08:44 -08:00
995f56236b
[Core] Loading model from S3 using RunAI Model Streamer as optional loader ( #10192 )
...
Signed-off-by: OmerD <omer@run.ai>
2024-12-20 16:46:24 +00:00
86c2d8fd1c
[Bugfix] Fix spec decoding when seed is none in a batch ( #10863 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com>
2024-12-20 05:15:31 +00:00
e24113a8fe
[Model] Refactor Qwen2-VL to use merged multimodal processor ( #11258 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-19 16:28:00 +00:00
6c7f881541
[Model] Add JambaForSequenceClassification model ( #10860 )
...
Signed-off-by: Yehoshua Cohen <yehoshuaco@ai21.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Yehoshua Cohen <yehoshuaco@ai21.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-19 22:48:06 +08:00
5aef49806d
[Feature] Add load generation config from model ( #11164 )
...
Signed-off-by: liuyanyi <wolfsonliu@163.com>
Signed-off-by: Yanyi Liu <wolfsonliu@163.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2024-12-19 10:50:38 +00:00
6142ef0ada
[VLM] Merged multimodal processor for Qwen2-Audio ( #11303 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-19 06:14:17 +00:00
a30482f054
[CI] Expand test_guided_generate to test all backends ( #11313 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-12-19 04:00:38 +00:00
17ca964273
[Model] IBM Granite 3.1 ( #11307 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-12-19 11:27:24 +08:00
5a9da2e6e9
[Bugfix][Build/CI] Fix sparse CUTLASS compilation on CUDA [12.0, 12.2) ( #11311 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-12-19 02:43:30 +00:00
ca5f54a9b9
[Bugfix] fix minicpmv test ( #11304 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-12-18 10:34:26 -08:00
996aa70f00
[Bugfix] Fix broken phi3-v mm_processor_kwargs tests ( #11263 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-12-18 10:16:40 -08:00
60508ffda9
[Kernel]: Cutlass 2:4 Sparsity + FP8/Int8 Quant Support ( #10995 )
...
Co-authored-by: Faraz Shahsavan <faraz.shahsavan@gmail.com>
Co-authored-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
2024-12-18 09:57:16 -05:00
8b79f9e107
[Bugfix] Fix guided decoding with tokenizer mode mistral ( #11046 )
2024-12-17 22:34:08 -08:00
bf8717ebae
[V1] Prefix caching for vision language models ( #11187 )
...
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
2024-12-17 16:37:59 -08:00
c77eb8a33c
[Bugfix] Set temperature=0.7 in test_guided_choice_chat ( #11264 )
2024-12-17 16:34:06 -08:00
2d1b9baa8f
[Bugfix] Fix request cancellation without polling ( #11190 )
2024-12-17 12:26:32 -08:00
66d4b16724
[Frontend] Add OpenAI API support for input_audio ( #11027 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-16 22:09:58 -08:00
0064f697d3
[CI] Add test case with JSON schema using references + use xgrammar by default with OpenAI parse ( #10935 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-12-17 11:39:58 +08:00
551603feff
[core] overhaul memory profiling and fix backward compatibility ( #10511 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-16 13:32:25 -08:00
d927dbcd88
[Model] Refactor Ultravox to use merged input processor ( #11198 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-12-16 10:09:53 +00:00
bddbbcb132
[Model] Support Cohere2ForCausalLM (Cohere R7B) ( #11203 )
2024-12-16 09:56:19 +00:00
b10609e6a1
[Misc] Clean up multi-modal processor ( #11207 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-15 06:30:28 +00:00
93abf23a64
[VLM] Fully dynamic prompt replacement in merged input processor ( #11199 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-14 17:52:18 +00:00
9c3dadd1c9
[Frontend] Add `logits_processors` as an extra completion argument ( #11150 )
...
Signed-off-by: Brad Hilton <brad.hilton.nw@gmail.com>
2024-12-14 16:46:42 +00:00
0920ab9131
[Doc] Reorganize online pooling APIs ( #11172 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-14 00:22:22 +08:00
c31d4a57a6
[Core] support LoRA and prompt adapter in content-based hashing for Block Manager v2 prefix caching ( #8240 )
2024-12-13 07:51:25 -08:00
eeec9e3390
[Frontend] Separate pooling APIs in offline inference ( #11129 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-13 10:40:07 +00:00
be39e3cd18
[core] clean up cudagraph batchsize padding logic ( #10996 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-13 06:57:50 +00:00
1efce68605
[Bugfix] Use runner_type instead of task in GritLM ( #11144 )
...
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
2024-12-13 04:09:53 +00:00
30870b4f66
[torch.compile] Dynamic fp8 + rms_norm fusion ( #10906 )
...
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-12-13 03:19:23 +00:00
78ed8f57d8
[Misc][V1] Fix type in v1 prefix caching ( #11151 )
2024-12-13 00:57:40 +00:00
85362f028c
[Misc][LoRA] Ensure Lora Adapter requests return adapter name ( #11094 )
...
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-12 09:25:16 +00:00
62de37a38e
[core][distributed] initialization from StatelessProcessGroup ( #10986 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-12 09:04:19 +00:00
1da8f0e1dd
[Model] Add support for embedding model GritLM ( #10816 )
...
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
2024-12-12 06:39:16 +00:00
4e11683368
[V1] VLM preprocessor hashing ( #11020 )
...
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: Alexander Matveev <alexm@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-12-12 00:55:30 +00:00
d1e21a979b
[CI/Build] Split up VLM tests ( #11083 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-12 06:18:16 +08:00
8f10d5e393
[Misc] Split up pooling tasks ( #10820 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-11 01:28:00 -08:00
2e33fe4191
[CI/Build] Check transformers v4.47 ( #10991 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-11 05:02:02 +00:00
ffa48c9146
[Model] PP support for Mamba-like models ( #10992 )
...
Signed-off-by: mzusman <mor.zusmann@gmail.com>
2024-12-10 21:53:37 -05:00
d5c5154fcf
[Misc] LoRA + Chunked Prefill ( #9057 )
2024-12-11 10:09:20 +08:00
d05f88679b
[Misc][LoRA] Add PEFTHelper for LoRA ( #11003 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-10 11:12:01 +00:00
ebf778061d
monitor metrics of tokens per step using cudagraph batchsizes ( #11031 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-09 22:35:36 -08:00
28b3a1c7e5
[V1] Multiprocessing Tensor Parallel Support for v1 ( #9856 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-12-10 06:28:14 +00:00
a811dd6608
[Model] merged input processor for Phi-3-Vision models ( #10977 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-12-09 12:55:10 -08:00
ca871491ed
[Misc][LoRA] Abstract PunicaWrapper ( #10955 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-09 12:54:44 -08:00
fd57d2b534
[torch.compile] allow candidate compile sizes ( #10984 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-08 11:05:21 +00:00
78029b34ed
[BugFix][Kernel]: fix illegal memory access in causal_conv1d when conv_states is None ( #10928 )
...
Signed-off-by: xffxff <1247714429@qq.com>
2024-12-08 01:21:18 +08:00
c889d5888b
[Doc] Explicitly state that PP isn't compatible with speculative decoding yet ( #10975 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-07 17:20:49 +00:00
39e227c7ae
[Model] Update multi-modal processor to support Mantis(LLaVA) model ( #10711 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-07 17:10:05 +00:00
955fa9533a
[3/N] Support and implement merged input processor for LLaVA model ( #10676 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-12-07 00:50:58 -08:00
222f5b082a
[CI/Build] Fix broken multimodal test ( #10950 )
2024-12-06 10:41:23 +00:00
9743d64e4e
[ci][build] add tests for python only compilation ( #10915 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-05 08:54:47 -08:00
998eeafe58
[CI/Build] Bump test transformers version ( #10106 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-05 16:05:52 +00:00
571da8fc43
[Misc][LoRA] Clean up the function interface of Punica ( #10917 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-05 13:22:28 +00:00
8d370e91cb
[Bugfix] Fallback to outlines for complex json schemas ( #10899 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-12-05 11:14:06 +08:00
01d079fd8e
[LoRA] Change lora_tokenizers capacity ( #10796 )
...
Signed-off-by: Xin Yang <xyang19@gmail.com>
2024-12-04 17:40:16 +00:00
d2bd88b122
[CI/Build] Replace mean with torch.all in test_pynccl.py ( #10876 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-12-04 03:23:21 +00:00
3bc94cab69
[V1] VLM - Run the mm_mapper preprocessor in the frontend process ( #10640 )
...
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-12-03 10:33:10 +00:00
9323a3153b
[Core][Performance] Add XGrammar support for guided decoding and set it as default ( #10785 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
2024-12-03 15:17:00 +08:00
dc5ce861bf
[torch.compile] remove compilation_context and simplify code ( #10838 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-03 06:19:02 +00:00
21fe7b481a
[core][distributed] add pynccl broadcast ( #10843 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-03 04:53:23 +00:00
b45f0d7946
[Misc][LoRA] Move the implementation of lora bias to punica.py ( #10829 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-02 17:53:36 +00:00
ef31eabc68
[Model]: add some tests for aria model ( #10770 )
...
Signed-off-by: xffxff <1247714429@qq.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2024-12-02 05:36:36 +00:00
073a4bd1c0
[Kernel] Use `out` arg in flash_attn_varlen_func ( #10811 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-12-01 17:55:39 -08:00
0590ec3fd9
[Core] Implement disagg prefill by StatelessProcessGroup ( #10502 )
...
This PR provides initial support for single-node disaggregated prefill in 1P1D scenario.
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: YaoJiayi <120040070@link.cuhk.edu.cn>
2024-12-01 19:01:00 -06:00
d2f058e76c
[Misc] Rename embedding classes to pooling ( #10801 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-01 14:36:51 +08:00
133707123e
[Model] Replace embedding models with pooling adapter ( #10769 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-01 08:02:54 +08:00
fa6ecb9aa7
[Model] Clean up MiniCPMV ( #10751 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-29 04:47:06 +00:00
5fc5ce0fe4
[Model] Added GLM-4 series hf format model support vllm==0.6.4 ( #10561 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2024-11-28 14:53:31 +00:00
a79b122400
[V1] Do not allocate beyond the max_model_len ( #10730 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-11-28 00:13:15 -08:00
d9b4b3f069
[Bug][CLI] Allow users to disable prefix caching explicitly ( #10724 )
...
Signed-off-by: rickyx <rickyx@anyscale.com>
2024-11-27 23:59:28 -08:00
395b1c7454
[Frontend] don't block event loop in tokenization (preprocess) in OpenAI compatible server ( #10635 )
...
Signed-off-by: Tomer Asida <tomera@ai21.com>
2024-11-27 13:21:10 -08:00
197b4484a3
[Bugfix][Mamba] Fix Multistep on Mamba-like models ( #10705 )
...
Signed-off-by: mzusman <mor.zusmann@gmail.com>
2024-11-27 19:02:27 +00:00
308cc5e21e
[ci] fix slow tests ( #10698 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-27 09:26:14 -08:00
1209261e93
[Model] Support telechat2 ( #10311 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: xiangw2 <xiangw2@chinatelecom.cn>
Co-authored-by: Isotr0py <2037008807@qq.com>
2024-11-27 11:32:35 +00:00
1bf905ddaa
[Bugfix][SpecDecode] apply sampling parameters to target probabilities for consistency in rejection sampling. ( #10198 )
...
Signed-off-by: jeongin601 <0200angela@gmail.com>
Signed-off-by: jeong_in.bae <jeong_in.bae@navercorp.com>
2024-11-27 05:07:30 +00:00
0a71900bc9
Remove hard-dependencies of Speculative decode to CUDA workers ( #10587 )
...
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
2024-11-26 17:57:11 -08:00
db66e018ea
[Bugfix] Fix for Spec model TP + Chunked Prefill ( #10232 )
...
Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
Signed-off-by: Sourashis Roy <sroy@roblox.com>
Co-authored-by: Sourashis Roy <sroy@roblox.com>
2024-11-26 09:11:16 -08:00
334d64d1e8
[ci] add vllm_test_utils ( #10659 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-26 00:20:04 -08:00
9a88f89799
custom allreduce + torch.compile ( #10121 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2024-11-25 22:00:16 -08:00
519e8e4182
[v1] EngineArgs for better config handling for v1 ( #10382 )
...
Signed-off-by: rickyx <rickyx@anyscale.com>
2024-11-25 21:09:43 -08:00
9db713a1dc
[Model] Add OLMo November 2024 model ( #10503 )
2024-11-25 17:26:40 -05:00
b1d920531f
[Model]: Add support for Aria model ( #10514 )
...
Signed-off-by: xffxff <1247714429@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2024-11-25 18:10:55 +00:00
c27df94e1f
[Bugfix] Fix chunked prefill with model dtype float32 on Turing Devices ( #9850 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-11-25 12:23:32 -05:00
d04b13a380
[Bug]: Authorization ignored when root_path is set ( #10606 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2024-11-25 16:21:41 +00:00
ed46f14321
[Model] Support `is_causal` HF config field for Qwen2 model ( #10621 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-25 09:51:20 +00:00
05d1f8c9c6
[misc] move functions to config.py ( #10624 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-25 09:27:30 +00:00
25d806e953
[misc] add torch.compile compatibility check ( #10618 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-24 23:40:08 -08:00
571841b7fc
[torch.compile] support encoder based models ( #10613 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-25 05:24:33 +00:00
214efc2c3c
Support Cross encoder models ( #10400 )
...
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Flavia Beo <flavia.beo@ibm.com>
Co-authored-by: Flavia Beo <flavia.beo@ibm.com>
2024-11-24 18:56:20 -08:00
1700c543a5
[Bugfix] Fix LoRA weight sharding ( #10450 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-11-23 17:23:17 -08:00
c8acd80548
[2/N] handling placeholders in merged multi-modal processor ( #10485 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-22 21:25:09 -08:00
4634a89d18
Prefix Cache Aware Scheduling [1/n] ( #10128 )
...
Signed-off-by: rickyx <rickyx@anyscale.com>
2024-11-22 21:15:55 -08:00
7d8ffb344f
[Bugfix] Internal Server Error when tool_choice is incorrect. ( #10567 )
...
Signed-off-by: Varun Shenoy <varun.vinayak.shenoy@oracle.com>
2024-11-22 21:13:29 -08:00
4aba6e3d1a
[core] gemma2 full context length support ( #10584 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-22 20:13:54 -08:00
978b39744b
[Misc] Add pynccl wrappers for all_gather and reduce_scatter ( #9432 )
2024-11-22 22:14:03 -05:00
9195dbdbca
[Bugfix][Frontend] Update Llama Chat Templates to also support Non-Tool use ( #10164 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-11-23 10:17:38 +08:00
97814fbf0f
[v1] Refactor KVCacheManager for more hash input than token ids ( #10507 )
...
Signed-off-by: rickyx <rickyx@anyscale.com>
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2024-11-22 23:27:25 +00:00
eebad39f26
[torch.compile] support all attention backends ( #10558 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-22 14:04:42 -08:00
db100c5cde
[bugfix] fix full graph tests ( #10581 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-22 10:02:14 -08:00
33e0a2540a
[9/N] torch.compile LLM usage ( #10552 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-21 19:13:31 -08:00
7560ae5caf
[8/N] enable cli flag without a space ( #10529 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-21 12:30:42 -08:00
2385b60d83
[Kernel] Register punica ops directly ( #10522 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-11-21 09:18:11 -08:00
da7e702c6f
[Bug]: When apply continue_final_message for OpenAI server, the "echo":false is ignored ( #10180 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2024-11-21 16:24:32 +00:00
d5ec121f95
[Model] Expose `dynamic_image_size` as mm_processor_kwargs for InternVL2 models ( #10518 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-11-21 14:20:08 +00:00
8b0fe06c89
[torch.compile] Inductor code caching fix ( #10273 )
...
Signed-off-by: luka <luka@neuralmagic.com>
Signed-off-by: Luka Govedic <luka.govedic@gmail.com>
2024-11-20 21:44:57 -08:00
6c1208d083
[Core] Add Sliding Window Support with Flashinfer ( #10462 )
...
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
2024-11-20 19:56:47 -08:00
388ee3de66
[torch.compile] limit inductor threads and lazy import quant ( #10482 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-20 18:36:33 -08:00
c68f7ede6a
[Bugfix]: allow extra fields in requests to openai compatible server ( #10463 )
...
Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>
2024-11-20 16:42:21 -05:00
0cd3d9717e
[7/N] torch.compile, reduce compilation time ( #10460 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-20 11:20:38 -08:00
63f1fde277
[Hardware][CPU] Support chunked-prefill and prefix-caching on CPU ( #10355 )
...
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2024-11-20 10:57:39 +00:00
d200972e7f
[Bugfix] Marlin 2:4 temp fix for large M dim (>256) ( #10464 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2024-11-19 19:40:33 -08:00
b00b33d77e
[Model][Quantization] HQQ support through Marlin kernel expansion ( #9766 )
...
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
2024-11-19 13:31:12 -08:00
803f37eaaa
[6/N] torch.compile rollout to users ( #10437 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-19 10:09:03 -08:00
8c1fb50705
[Platform][Refactor] Extract func `get_default_attn_backend` to `Platform` ( #10358 )
...
Signed-off-by: Mengqing Cao <cmq0113@163.com>
2024-11-19 11:22:26 +08:00
96d999fbe8
[Kernel] Initial Machete W4A8 support + Refactors ( #9855 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2024-11-18 12:59:29 -07:00
6b2d25efc7
[Hardware][XPU] AWQ/GPTQ support for xpu backend ( #10107 )
...
Signed-off-by: yan ma <yan.ma@intel.com>
2024-11-18 11:18:05 -07:00
c7dec926f6
[VLM] Report multi_modal_placeholders in output ( #10407 )
...
Signed-off-by: Linkun Chen <lkchen+anyscale@github.com>
2024-11-18 16:06:16 +08:00
4fd9375028
[2/N][torch.compile] make compilation cfg part of vllm cfg ( #10383 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-16 18:02:14 -08:00
361c29e174
[Bugfix] Fix M-RoPE position calculation when chunked prefill is enabled ( #10388 )
...
Signed-off-by: imkero <kerorek@outlook.com>
2024-11-17 02:10:00 +08:00
32e46e000f
[Frontend] Automatic detection of chat content format from AST ( #9919 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-16 13:35:40 +08:00
79ee45b428
[Misc] Bump up test_fused_moe tolerance ( #10364 )
...
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
2024-11-15 16:31:18 +00:00
b311efd0bd
[Misc] Fix import error in tensorizer tests and cleanup some code ( #10349 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-15 09:34:17 +00:00
2ac6d0e75b
[Misc] Consolidate pooler config overrides ( #10351 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-15 06:59:00 +00:00
b40cf6402e
[Model] Support Qwen2 embeddings and use tags to select model tests ( #10184 )
2024-11-14 20:23:09 -08:00
bf2ddc6610
[bugfix] Fix static asymmetric quantization case ( #10334 )
...
Signed-off-by: Daniël de Kok <me@danieldk.eu>
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: Daniël de Kok <me@danieldk.eu>
2024-11-15 09:35:11 +08:00
972112d82f
[Bugfix] Fix unable to load some models ( #10312 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-14 16:55:54 -08:00
11cd1ae6ad
[Tool parsing] Improve / correct mistral tool parsing ( #10333 )
2024-11-15 00:42:49 +00:00
4a18fd14ba
Support Roberta embedding models ( #9387 )
...
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Flavia Beo <flavia.beo@ibm.com>
Co-authored-by: Flavia Beo <flavia.beo@ibm.com>
2024-11-14 21:23:29 +00:00
29f3ef26a3
[ci][distributed] disable hanging tests ( #10317 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-14 00:23:39 -08:00
f67ce05d0b
[Frontend] Pythonic tool parser ( #9859 )
...
Signed-off-by: Mike Depinet <mike@fixie.ai>
2024-11-14 04:14:34 +00:00
15bb8330aa
[Bugfix] Fix tensor parallel for qwen2 classification model ( #10297 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-11-14 10:54:59 +08:00
ac49b59d8b
[Bugfix] bitsandbytes models fail to run pipeline parallel ( #10200 )
...
Signed-off-by: Hoang Cong Duc <hoangcongducltt@gmail.com>
2024-11-13 09:56:39 -07:00
0b8bb86bf1
[1/N] Initial prototype for multi-modal processor ( #10044 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-13 12:39:03 +00:00
1b886aa104
[Model] Adding Support for Qwen2VL as an Embedding Model. Using MrLight/dse-qwen2-2b-mrl-v1 ( #9944 )
...
Signed-off-by: FurtherAI <austin.veselka@lighton.ai>
Co-authored-by: FurtherAI <austin.veselka@lighton.ai>
2024-11-13 08:28:13 +00:00
3945c82346
[Model] Add support for Qwen2-VL video embeddings input & multiple image embeddings input with varied resolutions ( #10221 )
...
Signed-off-by: imkero <kerorek@outlook.com>
2024-11-13 07:07:22 +00:00
0d4ea3fb5c
[core][distributed] use tcp store directly ( #10275 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-12 17:36:08 -08:00
112fa0bbe5
[V1] Fix CI tests on V1 engine ( #10272 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-11-12 16:17:20 -08:00
8a06428c70
[LoRA] Adds support for bias in LoRA ( #5733 )
...
Signed-off-by: Umesh Deshpande <udeshpa@us.ibm.com>
Co-authored-by: Umesh Deshpande <udeshpa@us.ibm.com>
2024-11-12 11:08:40 -08:00
b41fb9d3b1
[Encoder Decoder] Update Mllama to run with both FlashAttention and XFormers ( #9982 )
...
Signed-off-by: Sourashis Roy <sroy@roblox.com>
2024-11-12 10:53:57 -08:00
47db6ec831
[Frontend] Add per-request number of cached token stats ( #10174 )
2024-11-12 16:42:28 +00:00
7f5edb5900
[Misc][LoRA] Replace hardcoded cuda device with configurable argument ( #10223 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-11-12 11:10:15 +08:00
eea55cca5b
[1/N] torch.compile user interface design ( #10237 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-11 18:01:06 -08:00
6ace6fba2c
[V1] `AsyncLLM` Implementation ( #9826 )
...
Signed-off-by: Nick Hill <nickhill@us.ibm.com>
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-11-11 23:05:38 +00:00
8a7fe47d32
[misc][distributed] auto port selection and disable tests ( #10226 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-11 11:54:59 -08:00
330e82d34a
[v1][torch.compile] support managing cudagraph buffer ( #10203 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-11-11 11:10:27 -08:00
e6de9784d2
[core][distributed] add stateless process group ( #10216 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-11 09:02:14 -08:00
36e4acd02a
[LoRA][Kernel] Remove the unused libentry module ( #10214 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-11-11 09:43:23 +00:00
58170d6503
[Hardware][CPU] Add embedding models support for CPU backend ( #10193 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-11-11 08:54:28 +00:00
73b9083e99
[misc] improve cloudpickle registration and tests ( #10202 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-11 00:10:53 +00:00
51c2e1fcef
[CI/Build] Split up models tests ( #10069 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-09 11:39:14 -08:00
b09895a618
[Frontend][Core] Override HF `config.json` via CLI ( #5836 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-09 16:19:27 +00:00
f192aeba74
[Bugfix] Enable some fp8 and quantized fullgraph tests ( #10171 )
...
Signed-off-by: Bill Nell <bill@neuralmagic.com>
2024-11-09 08:01:27 +00:00
47672f38b5
[CI/Build] Fix VLM broadcast tests `tensor_parallel_size` passing ( #10161 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-11-09 04:02:59 +00:00
e0191a95d8
[0/N] Rename `MultiModalInputs` to `MultiModalKwargs` ( #10040 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-09 11:31:02 +08:00
127c07480e
[Kernel][Triton] Add Triton implementation for scaled_mm_triton to support fp8 and int8 SmoothQuant, symmetric case ( #9857 )
...
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
2024-11-08 19:59:22 -05:00
4f93dfe952
[torch.compile] Fuse RMSNorm with quant ( #9138 )
...
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: youkaichao <youkaichao@126.com>
2024-11-08 21:20:08 +00:00
e1b5a82179
Rename vllm.logging to vllm.logging_utils ( #10134 )
2024-11-08 20:53:24 +00:00
f6778620a9
Disable spec-decode + chunked-prefill for draft models with tensor parallelism > 1 ( #10136 )
...
Signed-off-by: Sourashis Roy <sroy@roblox.com>
2024-11-08 15:56:18 +00:00
b489fc3c91
[CI/Build] Update CPU tests to include all "standard" tests ( #5481 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-08 23:30:04 +08:00
1ff4aed5bd
[Model] Expose size to Idefics3 as mm_processor_kwargs ( #10146 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-11-08 09:56:58 +00:00
201fc07730
[V1] Prefix caching (take 2) ( #9972 )
...
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
2024-11-07 17:34:44 -08:00
28b2877d30
Online video support for VLMs ( #10020 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: litianjian <litianjian@bytedance.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-07 20:25:59 +00:00
3be5b26a76
[CI/Build] Add shell script linting using shellcheck ( #7925 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2024-11-07 18:17:29 +00:00
9d43afcc53
[Feature] [Spec decode]: Combine chunked prefill with speculative decoding ( #9291 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2024-11-07 08:15:14 -08:00
ae62fd17c0
[Frontend] Tool calling parser for Granite 3.0 models ( #9027 )
...
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
2024-11-07 07:09:02 -08:00
aa9078fa03
Adds method to read the pooling types from model's files ( #9506 )
...
Signed-off-by: Flavia Beo <flavia.beo@ibm.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
2024-11-07 08:42:40 +00:00
6192e9b8fe
[Core][Distributed] Refactor ipc buffer init in CustomAllreduce ( #10030 )
...
Signed-off-by: Hanzhi Zhou <hanzhi713@gmail.com>
2024-11-06 23:50:47 -08:00
db7db4aab9
[Misc] Consolidate ModelConfig code related to HF config ( #10104 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-07 06:00:21 +00:00
a4b3e0c1e9
[Hardware][CPU] Update torch 2.5 ( #9911 )
...
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2024-11-07 04:43:08 +00:00
719c1ca468
[core][distributed] add stateless_init_process_group ( #10072 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-06 16:42:09 -08:00
d58268c56a
[V1] Make v1 more testable ( #9888 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-11-06 11:57:35 -08:00
a5bba7d234
[Model] Add Idefics3 support ( #9767 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: B-201 <Joy25810@foxmail.com>
Co-authored-by: B-201 <Joy25810@foxmail.com>
2024-11-06 11:41:17 +00:00
a5fda50a10
[CI/Build] Fix large_gpu_mark reason ( #10070 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-11-06 08:50:37 +00:00
21063c11c7
[CI/Build] drop support for Python 3.8 EOL ( #8464 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2024-11-06 07:11:55 +00:00
4be3a45158
[distributed] add function to create ipc buffers directly ( #10064 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-05 22:35:03 -08:00
2bcbae704c
[Bugfix] Fix edge-case crash when using chat with the Mistral Tekken Tokenizer ( #10051 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-11-06 04:28:29 +00:00
0c63c34f72
[Bugfix][SpecDecode] kv corruption with bonus tokens in spec decode ( #9730 )
...
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2024-11-06 01:45:45 +00:00
966e31697b
[Bugfix] Fix pickle of input when async output processing is on ( #9931 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com>
2024-11-06 00:39:26 +00:00
ca9844b340
[bugfix] fix weak ref in piecewise cudagraph and tractable test ( #10048 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-05 14:49:20 -08:00
235366fe2e
[CI] Prune back the number of tests in tests/kernels/* ( #9932 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-05 16:02:32 -05:00
02462465ea
[CI] Prune tests/models/decoder_only/language/* tests ( #9940 )
...
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-05 16:02:23 -05:00
bbc3619dc8
[Core] Make encoder-decoder inputs a nested structure to be more composable ( #9604 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-05 10:07:31 +08:00
ac04a97a9f
[Frontend] Add max_tokens prometheus metric ( #9881 )
...
Signed-off-by: Tomer Asida <tomera@ai21.com>
2024-11-04 22:53:24 +00:00
5208dc7a20
[Bugfix][CI/Build][Hardware][AMD] Shard ID parameters in AMD tests running parallel jobs ( #9279 )
...
Signed-off-by: Hissu Hyvarinen <hissu.hyvarinen@amd.com>
2024-11-04 11:37:46 -08:00
1c45f4c385
[CI] Basic Integration Test For TPU ( #9968 )
...
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
2024-11-04 11:34:26 -08:00
ac6b8f19b9
[Frontend] Multi-Modality Support for Loading Local Image Files ( #9915 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2024-11-04 15:34:57 +00:00
54597724f4
[Model] Add support for H2OVL-Mississippi models ( #9747 )
...
Signed-off-by: Shanshan Wang <shanshan.wang@h2o.ai>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-11-04 00:15:36 +00:00
cea808f325
[3/N] model runner pass the whole config to model ( #9958 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-02 12:08:49 -07:00
e893795443
[2/N] executor pass the complete config to worker/modelrunner ( #9938 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2024-11-02 07:35:05 -07:00
a78dd3303e
[Encoder Decoder] Add flash_attn kernel support for encoder-decoder models ( #9559 )
2024-11-01 23:22:49 -07:00
6c0b7f548d
[Core][VLM] Add precise multi-modal placeholder tracking ( #8346 )
...
Signed-off-by: Peter Salas <peter@fixie.ai>
2024-11-01 16:21:10 -07:00
598b6d7b07
[Bugfix/Core] Flashinfer k_scale and v_scale ( #9861 )
2024-11-01 12:15:05 -07:00
1dd4cb2935
[Bugfix] Fix edge cases for MistralTokenizer ( #9625 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2024-11-01 10:33:15 -07:00
ba0d892074
[Frontend] Use a proper chat template for VLM2Vec ( #9912 )
2024-11-01 14:09:07 +00:00
30a2e80742
[CI/Build] Add Model Tests for PixtralHF ( #9813 )
2024-11-01 07:55:29 -06:00
06386a64dd
[Frontend] Chat-based Embeddings API ( #9759 )
2024-11-01 08:13:35 +00:00
2b5bf20988
[torch.compile] Adding torch compile annotations to some models ( #9876 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2024-11-01 00:25:47 -07:00
566cd27797
[torch.compile] rework test plans ( #9866 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-10-31 22:20:17 -07:00
96e0c9cbbd
[torch.compile] directly register custom op ( #9896 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-10-31 21:56:09 -07:00
031a7995f3
[Bugfix][Frontend] Reject guided decoding in multistep mode ( #9892 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-11-01 01:09:46 +00:00
9fb12f7848
[BugFix][Kernel] Fix Illegal memory access in causal_conv1d in H100 ( #9838 )
...
Signed-off-by: mzusman <mor.zusmann@gmail.com>
2024-10-31 20:06:25 +00:00
55650c83a0
[Bugfix] Fix `illegal memory access` error with chunked prefill, prefix caching, block manager v2 and xformers enabled together ( #9532 )
...
Signed-off-by: sasha0552 <admin@sasha0552.org>
2024-10-31 11:46:36 -07:00
16b8f7a86f
[CI/Build] Add Model Tests for Qwen2-VL ( #9846 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-31 09:10:52 -07:00
abbfb6134d
[Misc][OpenAI] deprecate max_tokens in favor of new max_completion_tokens field for chat completion endpoint ( #9837 )
2024-10-30 18:15:56 -07:00
64384bbcdf
[torch.compile] upgrade tests ( #9858 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-10-30 16:34:22 -07:00
00d91c8a2c
[CI/Build] Simplify exception trace in api server tests ( #9787 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2024-10-30 14:52:05 -07:00
3b3f1e7436
[Bugfix][core] replace heartbeat with pid check ( #9818 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-10-30 09:34:07 -07:00
9ff4511e43
[Misc] Add chunked-prefill support on FlashInfer. ( #9781 )
2024-10-30 09:33:53 -07:00
cc98f1e079
[CI/Build] VLM Test Consolidation ( #9372 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-10-30 09:32:17 -07:00
ff5ed6e1bc
[torch.compile] rework compile control with piecewise cudagraph ( #9715 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-10-29 23:03:49 -07:00
882a1ad0de
[Model] tool calling support for ibm-granite/granite-20b-functioncalling ( #8339 )
...
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Maximilien de Bayser <maxdebayser@gmail.com>
2024-10-29 15:07:37 -07:00
67bdf8e523
[Bugfix][Frontend] Guard against bad token ids ( #9634 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-10-29 14:13:20 -07:00
ab6f981671
[CI][Bugfix] Skip chameleon for transformers 4.46.1 ( #9808 )
2024-10-29 11:12:43 -07:00
622b7ab955
[Hardware] using current_platform.seed_everything ( #9785 )
...
Signed-off-by: wangshuai09 <391746016@qq.com>
2024-10-29 14:47:44 +00:00
ef7865b4f9
[Frontend] re-enable multi-modality input in the new beam search implementation ( #9427 )
...
Signed-off-by: Qishuai Ferdinandzhong@gmail.com
2024-10-29 11:49:47 +00:00
5f8d8075f9
[Model][VLM] Add multi-video support for LLaVA-Onevision ( #8905 )
...
Co-authored-by: litianjian <litianjian@bytedance.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-28 18:04:10 +00:00
32176fee73
[torch.compile] support moe models ( #9632 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-10-27 21:58:04 -07:00
4e2d95e372
[Hardware][ROCM] using current_platform.is_rocm ( #9642 )
...
Signed-off-by: wangshuai09 <391746016@qq.com>
2024-10-28 04:07:00 +00:00
34a9941620
[Bugfix] Fix load config when using bools ( #9533 )
2024-10-27 13:46:41 -04:00
3cb07a36a2
[Misc] Upgrade to pytorch 2.5 ( #9588 )
...
Signed-off-by: Bill Nell <bill@neuralmagic.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2024-10-27 09:44:24 +00:00
6650e6a930
[Model] Add classification Task with Qwen2ForSequenceClassification ( #9704 )
...
Signed-off-by: Kevin-Yang <ykcha9@gmail.com>
Co-authored-by: Kevin-Yang <ykcha9@gmail.com>
2024-10-26 17:53:35 +00:00
07e981fdf4
[Frontend] Bad words sampling parameter ( #9717 )
...
Signed-off-by: Vasily Alexeev <alvasian@yandex.ru>
2024-10-26 16:29:38 +00:00
5cbdccd151
[Hardware][openvino] is_openvino --> current_platform.is_openvino ( #9716 )
2024-10-26 10:59:06 +00:00
9f7b4ba865
[ci/Build] Skip Chameleon for transformers 4.46.0 on broadcast test #9675 ( #9676 )
2024-10-24 20:59:00 -07:00
59449095ab
[Performance][Kernel] Fused_moe Performance Improvement ( #9384 )
...
Signed-off-by: charlifu <charlifu@amd.com>
2024-10-24 15:37:52 -07:00
722d46edb9
[Model] Compute Llava Next Max Tokens / Dummy Data From Gridpoints ( #9650 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-10-24 10:42:24 -07:00
c866e0079d
[CI/Build] Fix VLM test failures when using transformers v4.46 ( #9666 )
2024-10-25 01:40:40 +08:00
d27cfbf791
[torch.compile] Adding torch compile annotations to some models ( #9641 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2024-10-24 09:31:42 -07:00
295a061fb3
[Kernel] add kernel for FATReLU ( #9610 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-10-24 16:18:27 +08:00
8a02cd045a
[torch.compile] Adding torch compile annotations to some models ( #9639 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2024-10-24 00:54:57 -07:00
4fdc581f9e
[core] simplify seq group code ( #9569 )
...
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-10-24 00:16:44 -07:00
836e8ef6ee
[Bugfix] Fix PP for ChatGLM and Molmo ( #9422 )
2024-10-24 06:12:05 +00:00
33bab41060
[Bugfix]: Make chat content text allow type content ( #9358 )
...
Signed-off-by: Vinay Damodaran <vrdn@hey.com>
2024-10-24 05:05:49 +00:00
fc6c274626
[Model] Add Qwen2-Audio model support ( #9248 )
...
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-23 17:54:22 +00:00
150b779081
[Frontend] Enable Online Multi-image Support for MLlama ( #9393 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-10-23 17:28:57 +00:00
31a08f5bd2
[Model] Add min_pixels / max_pixels to Qwen2VL as mm_processor_kwargs ( #9612 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-10-23 14:05:18 +00:00
3ff57ebfca
[Model] Initialize Florence-2 language backbone support ( #9555 )
2024-10-23 10:42:47 +00:00
831540cf04
[Model] Support E5-V ( #9576 )
2024-10-23 11:35:29 +08:00
b17046e298
[BugFix] Fix metrics error for --num-scheduler-steps > 1 ( #8234 )
2024-10-22 15:43:03 -07:00
cd5601ac37
[BugFix] Prevent exporting duplicate OpenTelemetry spans ( #9017 )
2024-10-22 11:11:53 -07:00
bb392ea2d2
[Model][VLM] Initialize support for Mono-InternVL model ( #9528 )
2024-10-22 16:01:46 +00:00
a48e3ec052
[CI/Build][LoRA] Temporarily fix long context failure issue ( #9579 )
2024-10-22 11:32:51 +00:00
3ddbe25502
[Hardware][CPU] using current_platform.is_cpu ( #9536 )
2024-10-22 00:50:43 -07:00
c0292211ce
[CI/Build] Replaced some models on tests for smaller ones ( #9570 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com>
2024-10-22 04:52:14 +00:00
f085995a7b
[CI/Build] Remove unnecessary `fork_new_process` ( #9484 )
2024-10-21 19:47:29 -07:00
b729901139
[Bugfix]: serialize config by value for --trust-remote-code ( #6751 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-10-21 19:46:24 -07:00
76a5e13270
[core] move parallel sampling out from vllm core ( #9302 )
2024-10-22 00:31:44 +00:00
ef7faad1b8
🐛 Fixup more test failures from memory profiling ( #9563 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-10-21 17:10:56 -07:00
711f3a7806
[Frontend] Don't log duplicate error stacktrace for every request in the batch ( #9023 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com>
2024-10-21 14:49:41 -07:00
f6b97293aa
[Model] FalconMamba Support ( #9325 )
2024-10-21 12:50:16 -04:00
696b01af8f
[CI/Build] Split up decoder-only LM tests ( #9488 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-10-20 21:27:50 -07:00
4fa3e33349
[Kernel] Support sliding window in flash attention backend ( #9403 )
2024-10-20 10:57:52 -07:00
5b59fe0f08
[Bugfix] Pass json-schema to GuidedDecodingParams and make test stronger ( #9530 )
2024-10-20 00:05:02 +00:00
c5eea3c8ba
[Frontend] Support simpler image input format ( #9478 )
2024-10-18 23:17:07 -07:00
380e18639f
🐛 fix torch memory profiling ( #9516 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-10-18 21:25:19 -04:00
337ed76671
[Bugfix] Fix offline mode when using `mistral_common` ( #9457 )
2024-10-18 18:12:32 -07:00
d11bf435a0
[MISC] Consolidate cleanup() and refactor offline_inference_with_prefix.py ( #9510 )
2024-10-18 14:30:55 -07:00
051eaf6db3
[Model] Add user-configurable task for models that support both generation and embedding ( #9424 )
2024-10-18 11:31:58 -07:00
d2b1bf55ec
[Frontend][Feature] Add jamba tool parser ( #9154 )
2024-10-18 10:27:48 +00:00
de4008e2ab
[Bugfix][Core] Use torch.cuda.memory_stats() to profile peak memory usage ( #9352 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-10-17 22:47:27 -04:00
343f8e0905
Support `BERTModel` (first `encoder-only` embedding model) ( #9056 )
...
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Andrew Feldman <afeldman@neuralmagic.com>
Co-authored-by: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: laishzh <laishengzhang@gmail.com>
Co-authored-by: Max de Bayser <maxdebayser@gmail.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2024-10-17 23:21:01 +00:00
eca2c5f7c0
[Bugfix] Fix support for dimension like integers and ScalarType ( #9299 )
2024-10-17 19:08:34 +00:00
0f41fbe5a3
[torch.compile] Fine-grained CustomOp enabling mechanism ( #9300 )
2024-10-17 18:36:37 +00:00
81ede99ca4
[Core] Deprecating block manager v1 and make block manager v2 default ( #8704 )
...
Removing the block manager v1. This is the initial piece of prefix-caching-centric design. In order to achieve prefix-caching-centric design, we need to simplify the code path so that we only use v2 block manager (which has much higher performance on prefix caching).
2024-10-17 11:38:15 -05:00
fb60ae9b91
[Kernel][Model] Improve continuous batching for Jamba and Mamba ( #9189 )
2024-10-16 12:12:43 -04:00
cee711fdbb
[Core] Rename input data types ( #8688 )
2024-10-16 10:49:37 +00:00
7abba39ee6
[Model] VLM2Vec, the first multimodal embedding model in vLLM ( #9303 )
2024-10-16 14:31:00 +08:00
7e7eae338d
[Misc] Standardize RoPE handling for Qwen2-VL ( #9250 )
2024-10-16 13:56:17 +08:00
ba30942240
[Bugfix] Fix vLLM UsageInfo and logprobs None AssertionError with empty token_ids ( #9034 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-10-15 15:40:43 -07:00
22f8a69549
[Misc] Directly use compressed-tensors for checkpoint definitions ( #8909 )
...
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-15 15:40:25 -07:00
e9d517f276
[BugFix] Fix chat API continuous usage stats ( #9357 )
2024-10-14 23:19:48 -07:00
f0fe4fe86d
[Model] Make llama3.2 support multiple and interleaved images ( #9095 )
2024-10-14 15:24:26 -07:00
89feb4c84d
[SpecDec] Remove Batch Expansion (2/3) ( #9298 )
2024-10-12 05:13:37 +00:00
6cf1167c1a
[Model] Add GLM-4v support and meet vllm==0.6.2 ( #9242 )
2024-10-11 17:36:13 +00:00
7342a7d7f8
[Model] Support Mamba ( #6484 )
2024-10-11 15:40:06 +00:00
36ea79079b
[Misc][LoRA] Support loading LoRA weights for target_modules in reg format ( #9275 )
2024-10-11 12:31:21 +00:00
cbc2ef5529
[misc] hide best_of from engine ( #9261 )
...
Co-authored-by: Brendan Wong <bjwpokemon@gmail.com>
2024-10-10 21:30:44 -07:00
e4d652ea3e
[torch.compile] integration with compilation control ( #9058 )
2024-10-10 12:39:36 -07:00
f3a507f1d3
[Core] Add an environment variable which needs to be set explicitly to allow BlockSpaceManagerV1 ( #9149 )
2024-10-10 14:17:17 +08:00
a64e7b9407
[Bugfix] Machete garbage results for some models (large K dim) ( #9212 )
2024-10-10 14:16:17 +08:00
ce00231a8b
[Bugfix] Fix Weight Loading Multiple GPU Test - Large Models ( #9213 )
2024-10-10 14:15:40 +08:00
ca77dd7a44
[Hardware][CPU] Support AWQ for CPU backend ( #7515 )
2024-10-09 10:28:08 -06:00
c8627cd41b
[ci][test] use load dummy for testing ( #9165 )
2024-10-09 00:38:40 -07:00
2f4117c38e
support bitsandbytes quantization with more models ( #9148 )
2024-10-08 19:52:19 -06:00
bd37b9fbe2
[Bugfix] Try to handle older versions of pytorch ( #9086 )
2024-10-08 14:28:12 -07:00
9a94ca4a5d
[Bugfix] fix OpenAI API server startup with --disable-frontend-multiprocessing ( #8537 )
2024-10-08 09:38:40 -07:00
069d3bd8d0
[Frontend] Add Early Validation For Chat Template / Tool Call Parser ( #9151 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-10-08 14:31:26 +00:00
a3691b6b5e
[Core][Frontend] Add Support for Inference Time mm_processor_kwargs ( #9131 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-10-08 14:12:56 +00:00
8c746226c9
[Frontend] API support for beam search for MQLLMEngine ( #9117 )
2024-10-08 05:51:43 +00:00
04c12f8157
[misc] update utils to support comparing multiple settings ( #9140 )
2024-10-08 02:51:49 +00:00
f19da64871
[Core] Refactor GGUF parameters packing and forwarding ( #8859 )
2024-10-07 10:01:46 +00:00
4f95ffee6f
[Hardware][CPU] Cross-attention and Encoder-Decoder models support on CPU backend ( #9089 )
2024-10-07 06:50:35 +00:00
8c6de96ea1
[Model] Explicit interface for vLLM models and support OOT embedding models ( #9108 )
2024-10-07 06:10:35 +00:00
18b296fdb2
[core] remove beam search from the core ( #9105 )
2024-10-07 05:47:04 +00:00
cb3b2b9ba4
[Bugfix] Fix incorrect updates to num_computed_tokens in multi-step scheduling ( #9038 )
...
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-10-06 12:48:11 -07:00
b22b798471
[Model] PP support for embedding models and update docs ( #9090 )
...
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-10-06 16:35:27 +08:00
168cab6bbf
[Frontend] API support for beam search ( #9087 )
...
Co-authored-by: youkaichao <youkaichao@126.com>
2024-10-05 23:39:03 -07:00
5df1834895
[Bugfix] Fix order of arguments matters in config.yaml ( #8960 )
2024-10-05 17:35:11 +00:00
cfadb9c687
[Bugfix] Deprecate registration of custom configs to huggingface ( #9083 )
2024-10-05 21:56:40 +08:00
15986f598c
[Model] Support Gemma2 embedding model ( #9004 )
2024-10-05 06:57:05 +00:00
05d686432f
[Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE ( #8973 )
...
Co-authored-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>
2024-10-04 12:34:44 -06:00
0dcc8cbe5a
Adds truncate_prompt_tokens param for embeddings creation ( #8999 )
...
Signed-off-by: Flavia Beo <flavia.beo@ibm.com>
2024-10-04 18:31:40 +00:00
26aa325f4f
[Core][VLM] Test registration for OOT multimodal models ( #8717 )
...
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-04 10:38:25 -07:00
9ade8bbc8d
[Model] add a bunch of supported lora modules for mixtral ( #9008 )
...
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
2024-10-04 16:24:40 +00:00
0e36fd4909
[Misc] Move registry to its own file ( #9064 )
2024-10-04 10:01:37 +00:00
0f6d7a9a34
[Models] Add remaining model PP support ( #7168 )
...
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Signed-off-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-04 10:56:58 +08:00
3dbb215b38
[Frontend][Feature] support tool calling for internlm/internlm2_5-7b-chat model ( #8405 )
2024-10-04 10:36:39 +08:00
91add85ec4
Fix failing spec decode test ( #9054 )
2024-10-03 23:07:29 +00:00
9aaf14c62e
[misc] add forward context for attention ( #9029 )
2024-10-03 12:09:42 -07:00
63e39937f9
[Frontend] [Neuron] Parse literals out of override-neuron-config ( #8959 )
...
Co-authored-by: Jerzy Zagorski <jzagorsk@amazon.com>
2024-10-03 18:02:07 +00:00
83caf35e08
[BugFix] Enforce Mistral ToolCall id constraint when using the Mistral tool call parser ( #9020 )
2024-10-03 16:44:52 +08:00
19f0d25796
[Model] Adding Granite MoE. ( #8206 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-10-03 09:33:57 +08:00
563649aafe
[Core] Combined support for multi-step scheduling, chunked prefill & prefix caching ( #8804 )
...
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
2024-10-02 07:52:20 +00:00
1570203864
[Spec Decode] (1/2) Remove batch expansion ( #8839 )
2024-10-01 16:04:42 -07:00
bc4eb65b54
[Bugfix] Fix Fuyu tensor parallel inference ( #8986 )
2024-10-01 17:51:41 +08:00
062c89e7c9
[Frontend][Core] Move guided decoding params into sampling params ( #8252 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-10-01 09:34:25 +08:00
bce324487a
[CI][SpecDecode] Fix spec decode tests, use flash attention backend for spec decode CI tests. ( #8975 )
2024-10-01 00:51:40 +00:00
f13a07b1f8
[Kernel][Model] Varlen prefill + Prefill chunking support for mamba kernels and Jamba model ( #8533 )
2024-09-29 17:35:58 -04:00
6c9ba48fde
[Frontend] Added support for HF's new `continue_final_message` parameter ( #8942 )
2024-09-29 17:59:47 +00:00
3d49776bbb
[Model][LoRA]LoRA support added for MiniCPMV2.5 ( #7199 )
2024-09-29 06:59:45 +00:00
26a68d5d7e
[CI/Build] Add test decorator for minimum GPU memory ( #8925 )
2024-09-29 02:50:51 +00:00
d081da0064
[Bugfix] Fix Marlin MoE act order when is_k_full == False ( #8741 )
...
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-09-28 18:19:40 -07:00
5bf8789b2a
[Bugfix] Block manager v2 with preemption and lookahead slots ( #8824 )
2024-09-29 09:17:45 +08:00
e1a3f5e831
[CI/Build] Update models tests & examples ( #8874 )
...
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-09-28 09:54:35 -07:00
19d02ff938
[Bugfix] Fix PP for Multi-Step ( #8887 )
2024-09-28 08:52:46 -07:00
c2ec430ab5
[Core] Multi-Step + Single Step Prefills via Chunked Prefill code path ( #8378 )
...
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-09-27 13:32:07 -07:00
172d1cd276
[Kernel] AQ AZP 4/4: Integrate asymmetric quantization to linear method ( #7271 )
2024-09-27 14:25:10 -04:00
a9b15c606f
[torch.compile] use empty tensor instead of None for profiling ( #8875 )
2024-09-27 08:11:32 -07:00
6d792d2f31
[Bugfix][VLM] Fix Fuyu batching inference with `max_num_seqs>1` ( #8892 )
2024-09-27 01:15:58 -07:00
3b00b9c26c
[Core] rename`PromptInputs` and `inputs` ( #8876 )
2024-09-26 20:35:15 -07:00
344cd2b6f4
[Feature] Add support for Llama 3.1 and 3.2 tool use ( #8343 )
...
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
2024-09-26 17:01:42 -07:00
4b377d6feb
[BugFix] Fix test breakages from transformers 4.45 upgrade ( #8829 )
2024-09-26 16:46:43 -07:00
ee2da3e9ef
fix validation: Only set tool_choice `auto` if at least one tool is provided ( #8568 )
2024-09-26 16:23:17 -07:00
770ec6024f
[Model] Add support for the multi-modal Llama 3.2 model ( #8811 )
...
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chang Su <chang.s.su@oracle.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-09-25 13:29:32 -07:00
4f1ba0844b
Revert "rename PromptInputs and inputs with backward compatibility ( #8760 ) ( #8810 )
2024-09-25 10:36:26 -07:00
873edda6cf
[Misc] Support FP8 MoE for compressed-tensors ( #8588 )
2024-09-25 09:43:36 -07:00
28e1299e60
rename PromptInputs and inputs with backward compatibility ( #8760 )
2024-09-25 09:36:47 -07:00
300da09177
[Kernel] Fullgraph and opcheck tests ( #8479 )
2024-09-25 08:35:52 -06:00
fc3afc20df
Fix tests in test_chunked_prefill_scheduler which fail with BlockManager V2 ( #8752 )
2024-09-24 21:26:36 -07:00
ee777d9c30
Fix test_schedule_swapped_simple in test_scheduler.py ( #8780 )
2024-09-24 21:26:18 -07:00
6e0c9d6bd0
[Bugfix] Use heartbeats instead of health checks ( #8583 )
2024-09-24 20:37:38 -07:00
01b6f9e1f0
[Core][Bugfix] Support prompt_logprobs returned with speculative decoding ( #8047 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-09-24 17:29:56 -07:00
13f9f7a3d0
[[Misc]Upgrade bitsandbytes to the latest version 0.44.0 ( #8768 )
2024-09-24 17:08:55 -07:00
2529d09b5a
[Frontend] Batch inference for llm.chat() API ( #8648 )
...
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-09-24 09:44:11 -07:00
8ff7ced996
[Model] Expose Phi3v num_crops as a mm_processor_kwarg ( #8658 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-09-24 07:36:46 +00:00
3185fb0cca
Revert "[Core] Rename `PromptInputs` to `PromptType`, and `inputs` to `prompt`" ( #8750 )
2024-09-24 05:45:20 +00:00
0250dd68c5
re-implement beam search on top of vllm core ( #8726 )
...
Co-authored-by: Brendan Wong <bjwpokemon@gmail.com>
2024-09-23 22:08:12 -07:00
88577ac928
Fix tests in test_scheduler.py that fail with BlockManager V2 ( #8728 )
2024-09-24 04:43:13 +00:00
1a2aef3e59
Add output streaming support to multi-step + async while ensuring RequestOutput obj reuse ( #8335 )
2024-09-23 15:38:04 -07:00
5f7bb58427
Fix typical acceptance sampler with correct recovered token ids ( #8562 )
2024-09-23 12:32:27 -07:00
9b0e3ec970
[Kernel][LoRA] Add assertion for punica sgmv kernels ( #7585 )
2024-09-23 18:57:42 +00:00
86e9c8df29
[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin ( #7701 )
...
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-09-23 13:46:26 -04:00
ee5f34b1c2
[CI/Build] use setuptools-scm to set __version__ ( #4738 )
...
Co-authored-by: youkaichao <youkaichao@126.com>
2024-09-23 09:44:26 -07:00
a79e522984
[Model] Support pp for qwen2-vl ( #8696 )
2024-09-23 13:46:59 +00:00
9b8c8ba119
[Core][Frontend] Support Passing Multimodal Processor Kwargs ( #8657 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-09-23 07:44:48 +00:00
c6bd70d772
[SpecDec][Misc] Cleanup, remove bonus token logic. ( #8701 )
2024-09-22 12:34:14 -07:00
5b59532760
[Model][VLM] Add LLaVA-Onevision model support ( #8486 )
...
Co-authored-by: litianjian <litianjian@bytedance.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-09-22 10:51:44 -07:00
0faab90eb0
[beam search] add output for manually checking the correctness ( #8684 )
2024-09-20 19:55:33 -07:00
0455c46ed4
[Core] Factor out common code in `SequenceData` and `Sequence` ( #8675 )
2024-09-21 02:30:39 +00:00
0057894ef7
[Core] Rename `PromptInputs` and `inputs`( #8673 )
2024-09-20 19:00:54 -07:00
b4e4eda92e
[Bugfix][Core] Fix tekken edge case for mistral tokenizer ( #8640 )
2024-09-20 14:33:03 -07:00
260d40b5ea
[Core] Support Lora lineage and base model metadata management ( #6315 )
2024-09-20 06:20:56 +00:00
9cc373f390
[Kernel][Amd] Add fp8 kv cache support for rocm custom paged attention ( #8577 )
2024-09-19 17:37:57 +00:00
3118f63385
[Bugfix] [Encoder-Decoder] Bugfix for encoder specific metadata construction during decode of encoder-decoder models. ( #8545 )
2024-09-19 02:24:15 +00:00
db9120cded
[Kernel] Change interface to Mamba selective_state_update for continuous batching ( #8039 )
2024-09-18 20:05:06 +00:00
a8c1d161a7
[Core] *Prompt* logprobs support in Multi-step ( #8199 )
2024-09-18 08:38:43 -07:00
7c7714d856
[Core][Bugfix][Perf] Introduce `MQLLMEngine` to avoid `asyncio` OH ( #8157 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
2024-09-18 13:56:58 +00:00
9d104b5beb
[CI/Build] Update Ruff version ( #8469 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-09-18 11:00:56 +00:00
6ffa3f314c
[CI/Build] Avoid CUDA initialization ( #8534 )
2024-09-18 10:38:11 +00:00
8110e44529
[Kernel] Change interface to Mamba causal_conv1d_update for continuous batching ( #8012 )
2024-09-17 23:44:27 +00:00
fa0c114fad
[doc] improve installation doc ( #8550 )
...
Co-authored-by: Andy Dai <76841985+Imss27@users.noreply.github.com>
2024-09-17 16:24:06 -07:00
a54ed80249
[Model] Add mistral function calling format to all models loaded with "mistral" format ( #8515 )
...
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-09-17 17:50:37 +00:00
9855b99502
[Feature][kernel] tensor parallelism with bitsandbytes quantization ( #8434 )
2024-09-17 08:09:12 -07:00
1009e93c5d
[Encoder decoder] Add cuda graph support during decoding for encoder-decoder models ( #7631 )
2024-09-17 07:35:01 -07:00
99aa4eddaf
[torch.compile] register allreduce operations as custom ops ( #8526 )
2024-09-16 22:57:57 -07:00
1c1bb388e0
[Frontend] Improve Nullable kv Arg Parsing ( #8525 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-09-17 04:17:32 +00:00
546034b466
[refactor] remove triton based sampler ( #8524 )
2024-09-16 20:04:48 -07:00
5d73ae49d6
[Kernel] AQ AZP 3/4: Asymmetric quantization kernels ( #7270 )
2024-09-16 11:52:40 -07:00
acd5511b6d
[BugFix] Fix clean shutdown issues ( #8492 )
2024-09-16 09:33:46 -07:00
a091e2da3e
[Kernel] Enable 8-bit weights in Fused Marlin MoE ( #8032 )
...
Co-authored-by: Dipika <dipikasikka1@gmail.com>
2024-09-16 09:47:19 -06:00
fc990f9795
[Bugfix][Kernel] Add `IQ1_M` quantization implementation to GGUF kernel ( #8357 )
2024-09-15 16:51:44 -06:00
47790f3e32
[torch.compile] add a flag to disable custom op ( #8488 )
2024-09-14 13:07:16 -07:00
a36e070dad
[torch.compile] fix functionalization ( #8480 )
2024-09-14 09:46:04 -07:00
8a0cf1ddc3
[Model] support minicpm3 ( #8297 )
...
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-09-14 14:50:26 +00:00
1ef0d2efd0
[Kernel][Hardware][Amd]Custom paged attention kernel for rocm ( #8310 )
2024-09-13 17:01:11 -07:00
18e9e1f7b3
[HotFix] Fix final output truncation with stop string + streaming ( #8468 )
2024-09-13 11:31:12 -07:00
a84e598e21
[CI/Build] Reorganize models tests ( #7820 )
2024-09-13 10:20:06 -07:00
a2469127db
[misc][ci] fix quant test ( #8449 )
2024-09-13 17:20:14 +08:00
9b4a3b235e
[CI/Build] Enable InternVL2 PP test only on single node ( #8437 )
2024-09-13 06:35:20 +00:00
6821020109
[Bugfix] Fix async log stats ( #8417 )
2024-09-12 20:48:59 -07:00
8427550488
[CI/Build] Update pixtral tests to use JSON ( #8436 )
2024-09-13 03:47:52 +00:00
40c396533d
[Bugfix] Mapping physical device indices for e2e test utils ( #8290 )
2024-09-13 11:06:28 +08:00
5ec9c0fb3c
[Core] Factor out input preprocessing to a separate class ( #7329 )
2024-09-13 02:56:13 +00:00
d31174a4e1
[Hotfix][Pixtral] Fix multiple images bugs ( #8415 )
2024-09-12 15:21:51 -07:00
b61bd98f90
[CI/Build] Disable multi-node test for InternVL2 ( #8428 )
2024-09-12 15:05:35 -07:00
551ce01078
[Core] Add engine option to return only deltas or final output ( #7381 )
2024-09-12 12:02:00 -07:00
a6c0f3658d
[multi-step] add flashinfer backend ( #7928 )
2024-09-12 11:16:22 -07:00
f2e263b801
[Bugfix] Offline mode fix ( #8376 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-09-12 11:11:57 -07:00
c6202daeed
[Model] Support multiple images for qwen-vl ( #8247 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-09-12 10:10:54 -07:00
e56bf27741
[Bugfix] Fix InternVL2 inference with various num_patches ( #8375 )
...
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-09-12 10:10:35 -07:00
7de49aa86c
[torch.compile] hide slicing under custom op for inductor ( #8384 )
2024-09-12 00:11:55 -07:00
f842a7aff1
[misc] remove engine_use_ray ( #8126 )
2024-09-11 18:23:36 -07:00
a65cb16067
[MISC] Dump model runner inputs when crashing ( #8305 )
2024-09-12 01:12:25 +00:00
d394787e52
Pixtral ( #8377 )
...
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-09-11 14:41:55 -07:00
775f00f81e
[Speculative Decoding] Test refactor ( #8317 )
...
Co-authored-by: youkaichao <youkaichao@126.com>
2024-09-11 14:07:34 -07:00
73202dbe77
[Kernel][Misc] register ops to prevent graph breaks ( #6917 )
...
Co-authored-by: Sage Moore <sage@neuralmagic.com>
2024-09-11 12:52:19 -07:00
0b952af458
[Hardware][Intel] Support compressed-tensor W8A8 for CPU backend ( #7257 )
2024-09-11 09:46:46 -07:00
3b7fea770f
[Model][VLM] Add Qwen2-VL model support ( #7905 )
...
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-09-11 09:31:19 -07:00
cea95dfb94
[Frontend] Create ErrorResponse instead of raising exceptions in run_batch ( #8347 )
2024-09-11 05:30:11 +00:00
6a512a00df
[model] Support for Llava-Next-Video model ( #7559 )
...
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-09-10 22:21:36 -07:00
efcf946a15
[Hardware][NV] Add support for ModelOpt static scaling checkpoints. ( #6112 )
2024-09-11 00:38:40 -04:00
1230263e16
[Bugfix] Fix InternVL2 vision embeddings process with pipeline parallel ( #8299 )
2024-09-11 10:11:01 +08:00
8c054b7a62
[Frontend] Clean up type annotations for mistral tokenizer ( #8314 )
2024-09-10 16:49:11 +00:00
6cd5e5b07e
[Misc] Fused MoE Marlin support for GPTQ ( #8217 )
2024-09-09 23:02:52 -04:00
c7cb5c3335
[Misc] GPTQ Activation Ordering ( #8135 )
2024-09-09 16:27:26 -04:00
08287ef675
[Bugfix] Streamed tool calls now more strictly follow OpenAI's format; ensures Vercel AI SDK compatibility ( #8272 )
2024-09-09 10:45:11 -04:00
cfe712bf1a
[CI/Build] Use python 3.12 in cuda image ( #8133 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-09-07 13:03:16 -07:00
e807125936
[Model][VLM] Support multi-images inputs for InternVL2 models ( #8201 )
2024-09-07 16:38:23 +08:00
9f68e00d27
[Bugfix] Fix broken OpenAI tensorizer test ( #8258 )
2024-09-07 08:02:39 +00:00
ce2702a923
[tpu][misc] fix typo ( #8260 )
2024-09-06 22:40:46 -07:00
2f707fcb35
[Model] Multi-input support for LLaVA ( #8238 )
2024-09-07 02:57:24 +00:00
29f49cd6e3
[Model] Allow loading from original Mistral format ( #8168 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-09-06 17:02:05 -06:00
1447c97e75
[CI/Build] Increasing timeout for multiproc worker tests ( #8203 )
2024-09-06 11:51:03 -07:00
e5cab71531
[Frontend] Add --logprobs argument to `benchmark_serving.py` ( #8191 )
2024-09-06 09:01:14 -07:00
db3bf7c991
[Core] Support load and unload LoRA in api server ( #6566 )
...
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2024-09-05 18:10:33 -07:00
9da25a88aa
[MODEL] Qwen Multimodal Support (Qwen-VL / Qwen-VL-Chat) ( #8029 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-09-05 12:48:10 +00:00
8685ba1a1e
Inclusion of InternVLChatModel In PP_SUPPORTED_MODELS(Pipeline Parallelism) ( #7860 )
2024-09-05 11:33:37 +00:00
e39ebf5cf5
[Core/Bugfix] Add query dtype as per FlashInfer API requirements. ( #8173 )
2024-09-05 05:12:26 +00:00
e02ce498be
[Feature] OpenAI-Compatible Tools API + Streaming for Hermes & Mistral models ( #5649 )
...
Co-authored-by: constellate <constellate@1-ai-appserver-staging.codereach.com>
Co-authored-by: Kyle Mistele <kyle@constellate.ai>
2024-09-04 13:18:13 -07:00
561d6f8077
[CI] Change test input in Gemma LoRA test ( #8163 )
2024-09-04 13:05:50 -07:00
d1dec64243
[CI/Build][ROCm] Enabling LoRA tests on ROCm ( #7369 )
...
Co-authored-by: Simon Mo <simon.mo@hey.com>
2024-09-04 11:57:54 -07:00
2ad2e5608e
[MISC] Consolidate FP8 kv-cache tests ( #8131 )
2024-09-04 18:53:25 +00:00
855c262a6b
[Frontend] Multimodal support in offline chat ( #8098 )
2024-09-04 05:22:17 +00:00
2be8ec6e71
[Model] Add Ultravox support for multiple audio chunks ( #7963 )
2024-09-04 04:38:21 +00:00
2188a60c7e
[Misc] Update `GPTQ` to use `vLLMParameters` ( #7976 )
2024-09-03 17:21:44 -04:00
6d646d08a2
[Core] Optimize Async + Multi-step ( #8050 )
2024-09-03 18:50:29 +00:00
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
e6a26ed037
[SpecDecode][Kernel] Flashinfer Rejection Sampling ( #7244 )
2024-09-01 21:23:29 -07:00
f8d60145b4
[Model] Add Granite model ( #7436 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-09-01 18:37:18 -07:00
5b86b19954
[Misc] Optional installation of audio related packages ( #8063 )
2024-09-01 14:46:57 -07:00
5231f0898e
[Frontend][VLM] Add support for multiple multi-modal items ( #8049 )
2024-08-31 16:35:53 -07:00
622f8abff8
[Bugfix] bugfix and add model test for flashinfer fp8 kv cache. ( #8013 )
2024-08-30 22:18:50 -07:00
1248e8506a
[Model] Adding support for MSFT Phi-3.5-MoE ( #7729 )
...
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Zeqi Lin <zelin@microsoft.com>
Co-authored-by: Zeqi Lin <Zeqi.Lin@microsoft.com>
2024-08-30 13:42:57 -06:00
058344f89a
[Frontend]-config-cli-args ( #7737 )
...
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Kaunil Dhruv <kaunil_dhruv@intuit.com>
2024-08-30 08:21:02 -07:00
f97be32d1d
[VLM][Model] TP support for ViTs ( #7186 )
...
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-08-30 08:19:27 -07:00
428dd1445e
[Core] Logprobs support in Multi-step ( #7652 )
2024-08-29 19:19:08 -07:00
4abed65c58
[VLM] Disallow overflowing `max_model_len` for multimodal models ( #7998 )
2024-08-29 17:49:04 -07:00
4664ceaad6
support bitsandbytes 8-bit and FP4 quantized models ( #7445 )
2024-08-29 19:09:08 -04:00
6b3421567d
[Core][Kernels] Enable FP8 KV Cache with Flashinfer backend. + BugFix for kv_cache_dtype=auto ( #7985 )
...
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2024-08-29 14:53:11 -04:00
3f60f2244e
[Core] Combine async postprocessor and multi-step ( #7921 )
2024-08-29 11:18:26 -07:00
f205c09854
[Bugfix] Unify rank computation across regular decoding and speculative decoding ( #7899 )
2024-08-28 22:18:13 -07:00
ef99a78760
Revert "[Core][Kernels] Use FlashInfer backend for FP8 KV Cache when available." ( #7982 )
2024-08-28 21:27:06 -07:00
74d5543ec5
[VLM][Core] Fix exceptions on ragged NestedTensors ( #7974 )
2024-08-29 03:24:31 +00:00
a7f65c2be9
[torch.compile] remove reset ( #7975 )
2024-08-28 17:32:26 -07:00
ce6bf3a2cf
[torch.compile] avoid Dynamo guard evaluation overhead ( #7898 )
...
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-08-28 16:10:12 -07:00
fdd9daafa3
[Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM ( #7651 )
2024-08-28 15:06:52 -07:00
e5697d161c
[Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and awq_gemm to support AWQ ( #7386 )
2024-08-28 15:37:47 -04:00
b98cc28f91
[Core][Kernels] Use FlashInfer backend for FP8 KV Cache when available. ( #7798 )
...
Co-authored-by: Simon Mo <simon.mo@hey.com>
2024-08-28 10:01:22 -07:00
e3580537a4
[Performance] Enable chunked prefill and prefix caching together ( #7753 )
2024-08-28 00:36:31 -07:00
51f86bf487
[mypy][CI/Build] Fix mypy errors ( #7929 )
2024-08-27 23:47:44 -07:00
fab5f53e2d
[Core][VLM] Stack multimodal tensors to represent multiple images within each prompt ( #7902 )
2024-08-28 01:53:56 +00:00
5340a2dccf
[Model] Add multi-image input support for LLaVA-Next offline inference ( #7230 )
2024-08-28 07:09:02 +08:00
fc911880cc
[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel ( #7766 )
...
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
2024-08-27 15:07:09 -07:00
9db642138b
[CI/Build][VLM] Cleanup multiple images inputs model test ( #7897 )
2024-08-27 15:28:30 +00:00
6fc4e6e07a
[Model] Add Mistral Tokenization to improve robustness and chat encoding ( #7739 )
2024-08-27 12:40:02 +00:00
64cc644425
[core][torch.compile] discard the compile for profiling ( #7796 )
2024-08-26 21:33:58 -07:00
39178c7fbc
[Tests] Disable retries and use context manager for openai client ( #7565 )
2024-08-26 21:33:17 -07:00
2eedede875
[Core] Asynchronous Output Processor ( #7049 )
...
Co-authored-by: Alexander Matveev <alexm@neuralmagic.com>
2024-08-26 20:53:20 -07:00
665304092d
[Misc] Update `qqq` to use vLLMParameters ( #7805 )
2024-08-26 13:16:15 -06:00
2deb029d11
[Performance][BlockManagerV2] Mark prefix cache block as computed after schedule ( #7822 )
2024-08-26 11:24:53 -07:00
029c71de11
[CI/Build] Avoid downloading all HF files in `RemoteOpenAIServer` ( #7836 )
2024-08-26 05:31:10 +00:00
0b769992ec
[Bugfix]: Use float32 for base64 embedding ( #7855 )
...
Signed-off-by: Hollow Man <hollowman@opensuse.org>
2024-08-26 03:16:38 +00:00
1856aff4d6
[Spec Decoding] Streamline batch expansion tensor manipulation ( #7851 )
2024-08-25 15:45:14 -07:00
2059b8d9ca
[Misc] Remove snapshot_download usage in InternVL2 test ( #7835 )
2024-08-25 15:53:09 +00:00
8aaf3d5347
[Model][VLM] Support multi-images inputs for Phi-3-vision models ( #7783 )
2024-08-25 11:51:20 +00:00
80162c44b1
[Bugfix] Fix Phi-3v crash when input images are of certain sizes ( #7840 )
2024-08-24 18:16:24 -07:00
aab0fcdb63
[ci][test] fix RemoteOpenAIServer ( #7838 )
2024-08-24 17:31:28 +00:00
ea9fa160e3
[ci][test] exclude model download time in server start time ( #7834 )
2024-08-24 01:03:27 -07:00
7d9ffa2ae1
[misc][core] lazy import outlines ( #7831 )
2024-08-24 00:51:38 -07:00
d81abefd2e
[Frontend] add json_schema support from OpenAI protocol ( #7654 )
2024-08-23 23:07:24 -07:00
8da48e4d95
[Frontend] Publish Prometheus metrics in run_batch API ( #7641 )
2024-08-23 23:04:22 -07:00
9db93de20c
[Core] Add multi-step support to LLMEngine ( #7789 )
2024-08-23 12:45:53 -07:00
f1df5dbfd6
[Misc] Update `marlin` to use vLLMParameters ( #7803 )
2024-08-23 14:30:52 -04:00
e25fee57c2
[BugFix] Fix server crash on empty prompt ( #7746 )
...
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
2024-08-23 13:12:44 +00:00
c01a6cb231
[Ray backend] Better error when pg topology is bad. ( #7584 )
...
Co-authored-by: youkaichao <youkaichao@126.com>
2024-08-22 17:44:25 -07:00
b903e1ba7f
[Frontend] error suppression cleanup ( #7786 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-08-22 21:50:21 +00:00
cc0eaf12b1
[Bugfix] spec decode handle None entries in topk args in create_sequence_group_output ( #7232 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-08-22 09:33:48 -04:00
955b5191c9
[Misc] update fp8 to use `vLLMParameter` ( #7437 )
2024-08-22 08:36:18 -04:00
a3fce56b88
[Speculative Decoding] EAGLE Implementation with Top-1 proposer ( #6830 )
2024-08-22 02:42:24 -07:00
aae74ef95c
Revert "[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel ( #7527 )" ( #7764 )
2024-08-22 03:42:14 +00:00
cde9183b40
[Bug][Frontend] Improve ZMQ client robustness ( #7443 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-08-22 02:18:11 +00:00
df1a21131d
[Model] Fix Phi-3.5-vision-instruct 'num_crops' issue ( #7710 )
2024-08-22 09:36:24 +08:00
7937009a7e
[Kernel] Replaced `blockReduce[...]` functions with `cub::BlockReduce` ( #7233 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-08-21 20:18:00 -04:00
8678a69ab5
[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel ( #7527 )
...
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
2024-08-21 16:17:10 -07:00
1ca0d4f86b
[Model] Add UltravoxModel and UltravoxConfig ( #7615 )
2024-08-21 22:49:39 +00:00
970dfdc01d
[Frontend] Improve Startup Failure UX ( #7716 )
2024-08-21 19:53:01 +00:00
f7e3b0c5aa
[Bugfix][Frontend] Fix Issues Under High Load With `zeromq` Frontend ( #7394 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-08-21 13:34:14 -04:00
53328d7536
[BUG] fix crash on flashinfer backend with cudagraph disabled, when attention group_size not in [1,2,4,8] ( #7509 )
2024-08-21 08:54:31 -07:00
c75363fbc0
[BugFix] Avoid premature async generator exit and raise all exception variations ( #7698 )
2024-08-21 11:45:55 -04:00
baaedfdb2d
[mypy] Enable following imports for entrypoints ( #7248 )
...
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Fei <dfdfcai4@gmail.com>
2024-08-20 23:28:21 -07:00
12e1c65bc9
[Model] Add AWQ quantization support for InternVL2 model ( #7187 )
2024-08-20 23:18:57 -07:00
9e51b6a626
[ci][test] adjust max wait time for cpu offloading test ( #7709 )
2024-08-20 17:12:44 -07:00
3b682179dd
[Core] Add `AttentionState` abstraction ( #7663 )
2024-08-20 18:50:45 +00:00
aae6927be0
[VLM][Model] Add test for InternViT vision encoder ( #7409 )
2024-08-20 23:10:20 +08:00
5288c06aa0
[Kernel] (1/N) Machete - Hopper Optimized Mixed Precision Linear Kernel ( #7174 )
2024-08-20 07:09:33 -06:00
312f761232
[Speculative Decoding] Fixing hidden states handling in batch expansion ( #7508 )
2024-08-19 17:58:14 -07:00
7601cb044d
[Core] Support tensor parallelism for GGUF quantization ( #7520 )
2024-08-19 17:30:14 -04:00
47b65a5508
[core] Multi Step Scheduling ( #7000 )
...
Co-authored-by: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com>
2024-08-19 13:52:13 -07:00
3ac50b47d0
[MISC] Add prefix cache hit rate to metrics ( #7606 )
2024-08-19 11:52:07 -07:00
f710fb5265
[Core] Use flashinfer sampling kernel when available ( #7137 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-08-19 03:24:03 +00:00
ff7ec82c4d
[Core] Optimize SPMD architecture with delta + serialization optimization ( #7109 )
2024-08-18 17:57:20 -07:00
40e1360bb6
[CI/Build] Add text-only test for Qwen models ( #7475 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-08-19 07:43:46 +08:00
e3b318216d
[ Bugfix ] Fix Prometheus Metrics With `zeromq` Frontend ( #7279 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-08-18 20:19:48 +00:00
bbf55c4805
[VLM] Refactor `MultiModalConfig` initialization and profiling ( #7530 )
2024-08-17 13:30:55 -07:00
832163b875
[ci][test] allow longer wait time for api server ( #7629 )
2024-08-17 11:26:38 -07:00
5bf45db7df
[ci][test] fix engine/logger test ( #7621 )
2024-08-16 23:00:59 -07:00
4706eb628e
[aDAG] Unflake aDAG + PP tests ( #7600 )
2024-08-16 20:49:30 -07:00
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
7fc23be81c
[Kernel] W8A16 Int8 inside FusedMoE ( #7415 )
2024-08-16 10:06:51 -07:00
e837b624f2
[Feature][Hardware][Amd] Add fp8 Linear Layer for Rocm ( #7210 )
2024-08-16 10:06:30 -07:00
54bd9a03c4
register custom op for flash attn and use from torch.ops ( #7536 )
2024-08-15 22:38:56 -07:00
50b8d08dbd
[Misc/Testing] Use `torch.testing.assert_close` ( #7324 )
2024-08-16 04:24:04 +00:00
e165528778
[CI] Move quantization cpu offload tests out of fastcheck ( #7574 )
2024-08-15 21:16:20 -07:00
3b19e39dc5
Chat method for offline llm ( #5049 )
...
Co-authored-by: nunjunj <ray@g-3ff9f30f2ed650001.c.vllm-405802.internal>
Co-authored-by: nunjunj <ray@g-1df6075697c3f0001.c.vllm-405802.internal>
Co-authored-by: nunjunj <ray@g-c5a2c23abc49e0001.c.vllm-405802.internal>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-08-15 19:41:34 -07:00
4cd7d47fed
[ci/test] rearrange tests and make adag test soft fail ( #7572 )
2024-08-15 19:39:04 -07:00
f878c8feb0
[Feature]: Add OpenAI server prompt_logprobs support #6508 ( #7453 )
2024-08-16 02:38:08 +00:00
b67ae00cdb
[Misc] Add quantization config support for speculative model. ( #7343 )
2024-08-15 19:34:28 -07:00
f55a9aea45
[Misc] Revert `compressed-tensors` code reuse ( #7521 )
2024-08-14 15:07:37 -07:00
3f674a49b5
[VLM][Core] Support profiling with multiple multi-modal inputs per prompt ( #7126 )
2024-08-14 17:55:42 +00:00
70b746efcf
[Misc] Deprecation Warning when setting --engine-use-ray ( #7424 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: youkaichao <youkaichao@126.com>
2024-08-14 09:44:27 -07:00
ea49e6a3c8
[misc][ci] fix cpu test with plugins ( #7489 )
2024-08-13 19:27:46 -07:00
97992802f3
[CI/Build]Reduce the time consumption for LoRA tests ( #7396 )
2024-08-13 17:27:29 -07:00
16422ea76f
[misc][plugin] add plugin system implementation ( #7426 )
2024-08-13 16:24:17 -07:00
373538f973
[Misc] `compressed-tensors` code reuse ( #7277 )
2024-08-13 19:05:15 -04:00
33e5d7e6b6
[frontend] spawn engine process from api server process ( #7484 )
2024-08-13 15:40:17 -07:00
b1e5afc3e7
[Misc] Update `awq` and `awq_marlin` to use `vLLMParameters` ( #7422 )
2024-08-13 17:08:20 -04:00
fb377d7e74
[Misc] Update `gptq_marlin` to use new vLLMParameters ( #7281 )
2024-08-13 14:30:11 -04:00
00c3d68e45
[Frontend][Core] Add plumbing to support audio language models ( #7446 )
2024-08-13 17:39:33 +00:00
7025b11d94
[Bugfix] Fix weight loading for Chameleon when TP>1 ( #7410 )
2024-08-13 05:33:41 +00:00
97a6be95ba
[Misc] improve logits processors logging message ( #7435 )
2024-08-13 02:29:34 +00:00
9ba85bc152
[mypy] Misc. typing improvements ( #7417 )
2024-08-13 09:20:20 +08:00
198d6a2898
[Core] Shut down aDAG workers with clean async llm engine exit ( #7224 )
...
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2024-08-12 17:57:16 -07:00
a046f86397
[Core/Bugfix] Add FP8 K/V Scale and dtype conversion for prefix/prefill Triton Kernel ( #7208 )
...
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2024-08-12 22:47:41 +00:00
e6e42e4b17
[Core][VLM] Support image embeddings as input ( #6613 )
2024-08-12 16:16:06 +08:00
4c5d8e8ea9
[Bugfix] Fix phi3v batch inference when images have different aspect ratio ( #7392 )
2024-08-10 16:19:33 +00:00
baa240252e
[Core] Fix edge case in chunked prefill + block manager v2 ( #7380 )
2024-08-09 23:48:49 +00:00
933790c209
[Core] Add span metrics for model_forward, scheduler and sampler time ( #7089 )
2024-08-09 13:55:13 -07:00
249b88228d
[Frontend] Support embeddings in the run_batch API ( #7132 )
...
Co-authored-by: Simon Mo <simon.mo@hey.com>
2024-08-09 09:48:21 -07:00
b4e9528f95
[Core] Streamline stream termination in `AsyncLLMEngine` ( #7336 )
2024-08-09 07:06:36 +00:00
57b7be0e1c
[Speculative decoding] [Multi-Step] decouple should_modify_greedy_probs_inplace ( #6971 )
2024-08-09 05:42:45 +00:00
99b4cf5f23
[Bugfix] Fix speculative decoding with MLPSpeculator with padded vocabulary ( #7218 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-08-08 22:08:46 -07:00
7eb4a51c5f
[Core] Support serving encoder/decoder models ( #7258 )
2024-08-09 10:39:41 +08:00
782e53ab59
[Bugfix][fast] Fix the get_num_blocks_touched logic ( #6849 )
2024-08-08 10:43:30 -07:00
21b9c49aa3
[Frontend] Kill the server on engine death ( #6594 )
...
Signed-off-by: Joe Runde <joe@joerun.de>
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2024-08-08 09:47:48 -07:00
5fb4a3f678
[Bugfix][Kernel] Increased atol to fix failing tests ( #7305 )
2024-08-08 12:16:13 -04:00
Yannick Schnider
Nick Hill
Lucia Fang
Alex Brooks
Kevin H. Luu
Murali Andoorveedu
Liangfu Chen
Michael Goin
Isotr0py
Woosuk Kwon
Tyler Michael Smith
shangmingc
Cyrus Leung
youkaichao
wchen61
Lily Liu
Cody Yu
Mark McLoughlin
Aoyu
Joe Runde
Lu Fang
Alexander Matveev
Kero Liang
Varun Sundar Rabindranath
Harry Mellor
Nicolò Lucchesi
Vaibhav Jain
Rui Qiao
LikeSundayLikeRain
Kaixi Hou
Qubitium-ModelCloud
Jee Jee Li
Rafael Vasquez
Lingfan Yu
Christian Pinto
Keyun Tong
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
மனோஜ்குமார் பழனிச்சாமி
Ce Gao
Florian Greinacher
Farzad Abdolhosseini
TJian
afeldman-nm
Maximilien de Bayser
Yu Chin Fabian Lim
Dipika Sikka
Sumit Vij
Roger Wang
Rahul Tuli
Lucas Wilkinson
Hongxia Yang
Thomas Parnell
Russell Bryant
Arthur
Shawn Du
Chen Zhang
Jinzhen Lin
Yanyi Liu
Alphi
Travis Johnson
Ce Gao
Gabriel Marinho
Nicolò Lucchesi
Bowen Wang
Pooya Davoodi
Kyle Mistele
Matthew Hendrey
Nick Hill
Gregory Shtrasberg
rasmith
Adrian Cole
Andy Lo
Ricky Xu
Martin Gleize
yancong
Wallas Henrique
kewang-xlnx
RunningLeon
wangxiyuan
Elfie Guo
Yangcheng Li
Robert Shaw
Avshalom Manevich
Akshat Tripathi
Li, Jiang
cennn
Yan Burman
xcnick
Aurick Qiao
sakunkun
John Giorgi
ErezSC42
sroy745
Jiaxin Shan
Jason T. Greene
omer-dayan
Yehoshua Cohen
kYLe
Jani Monoses
Brad Hilton
Sungjae Lee
Luka Govedič
Alexander Matveev
Mor Zusman
zhou fan
Xin Yang
Aaron Pham
Kuntai Du
sixgod
Ricky Xu
tomeras91
shunxing12345
jeongin601
Chendi.Xue
Sage Moore
Shane A
Chauncey
Varun Vinayak Shenoy
Isotr0py
Pavani Majety
Guillaume Calmettes
ElizaWszola
Mengqing Cao
Yan Ma
lkchen
Patrick von Platen
Mike Depinet
HoangCongDuc
Austin Veselka
Umesh
zifeitong
Krishna Mandal
bnellnm
Florian Zimmermeister
litianjian
Flávia Béo
Hanzhi Zhou
hissu-hyvarinen
shanshan wang
Peter Salas
Yongzao
sasha0552
Will Eaton
wangshuai09
Zhong Qishuai
madt2709
kakao-kevin-us
Vasiliy Alekseev
Charlie Fu
Vinay R Damodaran
Yunfei Chu
yulei
Ronen Schaffer
Dhia Eddine Rhaiem
Yue Zhang
Chang Su
Xiang Xu
chenqianfzh
Daniele
Brendan Wong
Andy Dai
Prashant Gupta
代君
xendo
Guillaume Calmettes
Shawn Tan
danieljannai21
Chirag Jain
Simon Mo
Andy
jiqing-feng
ywfang
Charlie Fu
shangmingc
William Lin
Yang Fan
Yangshen⚡Deng
Pavani Majety
Kyle Sayers
Alexey Kondratiev(AMD)
manikandan.tm@zucisystems.com
wang.yuqi
Wenxiang
Kaunil Dhruv
Jungho Christopher Cho
Jonas M. Kübler
Megha Agarwal
Tyler Rockwood
SangBin Cho
Abhinav Goyal
LI MOU
Antoni Baum
Abhinav Goyal
Peng Guanwen
Mahesh Keralapura
jon-chuang
nunjunj
Grant Pinkert
Peter Salas
Andrew Wang
Cade Daniel
Pooya Davoodi
Zach Zheng