wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-04 09:38:12 +08:00
Code Issues Packages Projects Releases Wiki Activity
4,443 Commits 1 Branch 0 Tags
3b2005e1db79efe2ea4587035eb2e7ced6e258cb
Commit Graph

4443 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Rahul Tuli 3b2005e1db Add: Support for Sparse24Bitmask Compressed Models 2025-02-05 13:30:43 -08:00
Sanju C Sudhakaran af8486de49 [Hardware][Intel-Gaudi] Enable FusedSDPA support for Intel Gaudi (HPU) 2025-02-05 13:29:45 -08:00
Chen Zhang 4c3aac51e1 Merging PR #12536 
Merged via CLI script
 2025-02-05 13:24:26 -08:00
youkaichao bc1bdecebf [core][distributed] exact ray placement control (#12732) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-02-06 02:03:19 +08:00
Akash kaothalkar 022bcc701a [Bugfix] Fix 'ModuleNotFoundError: No module named 'intel_extension_for_pytorch'' for --tensor-parallel-size more than 1 (#12546) 2025-02-04 23:11:02 -08:00
Michael Goin c53dc466b1 [Doc] Remove performance warning for auto_awq.md (#12743) 2025-02-04 22:43:11 -08:00
Nick Hill 3d09e592a8 [V1][Misc] Shorten FinishReason enum and use constant strings (#12760) 2025-02-04 22:43:02 -08:00
Harry Mellor fcf2e3d7fc [Bugfix] Fix OpenVINO model runner (#12750) 2025-02-04 22:42:46 -08:00
Michael Goin 58b218d7ae [Doc] Update PR Reminder with link to Developer Slack (#12748) 2025-02-04 22:42:09 -08:00
Kyle Sayers 7ff7a638b6 [Model][Quant] Fix GLM, Fix fused module mappings for quantization (#12634) 
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
 2025-02-05 05:32:06 +00:00
Dipika Sikka 686006a220 [Misc] Bump the compressed-tensors version (#12736) 2025-02-04 20:44:48 -08:00
Isotr0py 98fd089fc9 [VLM] Add MLA with pure RoPE support for deepseek-vl2 models (#12729) 2025-02-04 20:44:26 -08:00
Harry Mellor 249824c3bf Refactor Linear handling in TransformersModel (#12727) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-02-05 04:31:12 +00:00
Aleksandr Malyshev 64862d106e [ROCM][AMD][TRITON] Halving warps number for fw_prefill to reduce spilling (#12713) 
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
 2025-02-05 03:58:22 +00:00
Aviv Keshet b3a0d01e45 [Core] add and implement VLLM_LOGITS_PROCESSOR_THREADS (#12368) 
Signed-off-by: Aviv Keshet <akeshet@scaledcognition.com>
 2025-02-04 18:46:26 -08:00
Lucas Wilkinson 75e94309e8 [Perf] Mem align KV caches for CUDA devices (MLA perf improvement) (#12676) 
Signed-off-by: simon-mo <xmo@berkeley.edu>
Signed-off-by: Lucas Wilkinson <lcwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
 2025-02-04 18:22:24 -08:00
Mark McLoughlin 233df6f5c4 [V1][Metrics] Add request_success_total counter, labelled with finish reason (#12579) 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
 2025-02-04 19:46:54 -05:00
Cyrus Leung 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
Sophie du Couédic 649550f27e [Build] update requirements of no-device for plugin usage (#12630) 
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
 2025-02-04 21:19:12 +08:00
Kero Liang 62467a834a Avoid unnecessary multi-modal input data copy when len(batch) == 1 (#12722) 
Signed-off-by: imkero <kerorek@outlook.com>
 2025-02-04 21:03:19 +08:00
Michael Greenbaum 6469038b14 [Bugfix] Fix loading of fine-tuned models based on Phi-3-Small (#12689) 
Signed-off-by: Michael Greenbaum <mgreenbaum@microsoft.com>
Co-authored-by: Michael Greenbaum <mgreenbaum@microsoft.com>
 2025-02-04 20:58:48 +08:00
Isotr0py 815079de8e [VLM] merged multimodal processor and V1 support for idefics3 (#12660) 
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2025-02-04 20:00:51 +08:00
Woosuk Kwon 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
Cyrus Leung 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
Jee Jee Li 96b23621c1 [Misc] Add BNB quantization for Whisper (#12381) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-02-04 16:27:36 +08:00
Hongxia Yang 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
Kyle Sayers 4896d0c2dd [Quant] Fix use_mla TypeError and support loading pure-sparsity Compressed Tensors configs (#12711) 2025-02-03 23:27:11 -08:00
Thomas Parnell 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
Michael Goin 5d98d56089 Support Pixtral-Large HF by using llava multimodal_projector_bias config (#12710) 
Signed-off-by: mgoin <michael@neuralmagic.com>
 2025-02-04 11:55:46 +08:00
Russell Bryant 73b35cca7f [Core] Improve hash collision avoidance in prefix caching (#12621) 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
 2025-02-03 16:28:20 -08:00
Cody Yu 5095e96606 [V1] Revert uncache_blocks and support recaching full blocks (#12415) 
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
 2025-02-03 15:04:53 -08:00
Cody Yu 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
kushanam 4797dad3ec [Model] Add Deepseek V3 fp8_w8a8 configs for B200 (#12707) 2025-02-03 13:30:39 -08:00
Kyle Sayers 6dd5e52823 Squelch MLA warning for Compressed-Tensors Models (#12704) 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
 2025-02-03 13:29:56 -08:00
Tyler Michael Smith c11de33dad [Bugfix][Kernel] Fix per-token/per-channel quantization for Hopper scaled mm (#12696) 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-02-03 13:04:59 -08:00
Russell Bryant 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
Arthur a1a2aaadb9 [Model]: Add transformers backend support (#11330) 
# Adds support for `transformers` as a backend

Following https://github.com/huggingface/transformers/pull/35235, a
bunch of models should already be supported, we are ramping up support
for more models.

Thanks @Isotr0py for the TP support, and @hmellor for his help as well!
This includes: 
- `trust_remote_code=True` support: any model on the hub, if it
implements attention the correct way can be natively supported!!
- tensor parallel support

---------

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <41363108+Isotr0py@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-02-03 21:30:38 +08:00
youkaichao 1298a400e8 [ci/build] fix gh200 test (#12681) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-02-03 15:59:49 +08:00
youkaichao ad4a9dc817 [cuda] manually import the correct pynvml module (#12679) 
fixes problems like https://github.com/vllm-project/vllm/pull/12635 and
https://github.com/vllm-project/vllm/pull/12636 and
https://github.com/vllm-project/vllm/pull/12565

---------

Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-02-03 15:58:21 +08:00
Srikanth Srinivas b9986454fe Fix for attention layers to remain unquantized during moe_wn16 quant (#12570) 
Fix to AWQ quant loading of the new R1 model

The new optimized MoE kernels for a large number of experts `moe_wn16`
uses AWQ quant which requires the attention layers to be in 16bit

The current merge has broken this, and the `get_quant_method` must
return None for it to work correctly again

---------

Signed-off-by: Srikanth Srinivas <srikanth@astrum.ai>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Beim <beim2015@outlook.com>
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: npanpaliya <nishidha.panpaliya@partner.ibm.com>
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: simon-mo <xmo@berkeley.edu>
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Ryan N <ryan.nguyen@centml.ai>
Signed-off-by: Brian Dellabetta <bdellabe@redhat.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Rahul Tuli <rahul@neuralmagic.com>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: Vicente Herrera <vicenteherrera@vicenteherrera.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Shawn Du <shawnd200@outlook.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Beim <805908499@qq.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Nishidha <nishidha.panpaliya@partner.ibm.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Aleksandr Malyshev <164964928+maleksan85@users.noreply.github.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
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: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Kevin H. Luu <kevin@anyscale.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Ryan Nguyen <96593302+xpbowler@users.noreply.github.com>
Co-authored-by: Brian Dellabetta <brian-dellabetta@users.noreply.github.com>
Co-authored-by: fade_away <1028552010@qq.com>
Co-authored-by: weilong.yu <weilong.yu@shopee.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Eldar Kurtic <eldarkurtic314@gmail.com>
Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Vicente Herrera <vicenteherrera@vicenteherrera.com>
Co-authored-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Shawn Du <shawnd200@outlook.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-02-03 13:46:19 +08:00
Eldar Kurtic c5932e5dac Properly check if all fused layers are in the list of targets (#12666) 
Thanks @kylesayrs for catching this!
 2025-02-03 13:42:18 +08:00
youkaichao 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
Yang Chen 95460fc513 [Kernel] port sgl moe_align_block_size kernels (#12574) 
sgl_moe_align_block_size is based on:


https://github.com/sgl-project/sglang/commit/ded9fcd09a43d5e7d5bb31a2bc3e9fc21bf65d2a

moe_align_block_size is based on:


https://github.com/sgl-project/sglang/commit/ba5112ff691d791a9e38c6c71f59324a5fcb49d0

Signed-off-by: Yang Chen <yangche@fb.com>
 2025-02-03 13:09:50 +08:00
Zhuohan Li 326fcc8b9f [Doc] Deprecate Discord (#12668) 2025-02-02 19:19:56 -08:00
youkaichao e64330910b [doc][misc] clarify VLLM_HOST_IP for multi-node inference (#12667) 
As more and more people are trying deepseek models with multi-node
inference, https://github.com/vllm-project/vllm/issues/7815 becomes more
frequent. Let's give clear message to users.

Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-02-03 09:32:18 +08:00
Russell Bryant 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
Kunshang Ji f256ebe4df [Hardware][Intel GPU] add XPU bf16 support (#12392) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-02-02 10:17:26 +00:00
Shawn Du 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
Woosuk Kwon abfcdcdf27 [V1][Minor] Avoid frequently creating ConstantList (#12653) 
A small optimization to avoid creating a new `ConstantList` every time `request.kv_block_hashes` is used.

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-02-01 23:43:20 -08:00
Russell Bryant e497f33491 [Core] Silence unnecessary deprecation warnings (#12620) 
I noticed during testing that I was getting a lot of these deprecation
warnings about `local_lora_path`:

```
DeprecationWarning: The 'lora_local_path' attribute is deprecated
     and will be removed in a future version.
     Please use 'lora_path' instead.
```

The check used for emitting this warning was always True, even when the
parameter was not actually specified. It will always be in
`__struct_fields__`. We should be checking for a non-None value,
instead.

Signed-off-by: Russell Bryant <rbryant@redhat.com>

Signed-off-by: Russell Bryant <rbryant@redhat.com>
 2025-02-02 15:35:50 +08:00