iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
14,386 Commits 3 Branches 0 Tags
fa6a6be51978bd4b49ba0da17039e60f96dc5b13
Commit Graph
401 Commits
Author SHA1 Message Date
Jinzhen Lin d0feea31c7 [Kernel] optimize performance of gptq marlin kernel when n is small (#14138) 
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
 2025-03-07 11:53:38 -05:00
Tyler Michael Smith cc2f9b32c8 [Distributed] Add enable_expert_parallel arg (#14305) 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-03-06 18:54:45 +00:00
Serena 1b7624bf5c [misc] Add FlashMLA as a new option of VLLM_ATTENTION_BACKEND env (#14267) 2025-03-05 21:28:50 +00:00
Cody Yu f35f8e2242 [Build] Make sure local main branch is synced when VLLM_USE_PRECOMPILED=1 (#13921) 
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
 2025-03-03 16:43:14 +08:00
Harry Mellor cf069aa8aa Update deprecated Python 3.8 typing (#13971) 2025-03-02 17:34:51 -08:00
Rui Qiao c9944acbf9 [misc] Rename Ray ADAG to Compiled Graph (#13928) 2025-02-26 20:03:28 -08:00
Jongseok Park 781096e385 Expert Parallelism (EP) Support for DeepSeek V2 (#12583) 2025-02-24 07:33:20 -08:00
Kevin H. Luu 2c5e637b57 [ci] Use env var to control whether to use S3 bucket in CI (#13634) 2025-02-22 19:19:45 -08:00
Helena Kloosterman 382f66fb08 [Bugfix] Fix boolean conversion for OpenVINO env variable (#13615) 2025-02-22 08:04:12 -08:00
Gregory Shtrasberg c904fdddf6 [ROCm] Apply FP8 weights padding to values not divisible by 512 bytes on ROCm (#13231) 2025-02-22 05:54:38 -08:00
youkaichao 3e472d882a [core] set up data parallel communication (#13591) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-02-22 19:28:59 +08:00
Yu-ZhouandCody Yu d0a7a2769d [Hardware][Gaudi][Feature] Support Contiguous Cache Fetch (#12139) 
Signed-off-by: yuzhou <yuzhou@habana.ai>
Signed-off-by: zhouyu5 <yu.zhou@intel.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
 2025-02-18 19:40:19 -08:00
Roger Wang dd5ede4440 [V1] Consolidate MM cache size to vllm.envs (#13239) 2025-02-13 20:19:03 -08:00
Lu Fang 042c3419fa Introduce VLLM_CUDART_SO_PATH to allow users specify the .so path (#12998) 
Signed-off-by: Lu Fang <lufang@fb.com>
 2025-02-12 09:06:13 -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
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 Wilkinsonandsimon-mo 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
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
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
Lucas WilkinsonWoosuk Kwonsimon-moMichael GoinZhuohan LiTyler Michael SmithAlexander Matveev
 		baeded2569 [Attention] Deepseek v3 MLA support with FP8 compute (#12601) 
This PR implements the Deepseek V3 support by performing matrix absorption the fp8 weights 

---------

Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.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>
 2025-01-31 21:52:51 -08:00
Lucas WilkinsonWoosuk Kwonsimon-moMichael GoinZhuohan LiTyler Michael SmithAlexander Matveevsimon-mo
 		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
Gregory ShtrasbergandMicah Williamson 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
Lucas Wilkinson 978b45f399 [Kernel] Flash Attention 3 Support (#12093) 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
 2025-01-23 06:45:48 -08:00
Nick Hill aea94362c9 [Frontend][V1] Online serving performance improvements (#12287) 2025-01-22 22:22:12 +00:00
Cody Yu 7206ce4ce1 [Core] Support reset_prefix_cache (#12284) 2025-01-22 18:52:27 +00:00
Rui Qiao f218f9c24d [core] Turn off GPU communication overlap for Ray executor (#12051) 
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
 2025-01-15 05:19:55 +00:00
Woosuk Kwon 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
youkaichaoandTyler Michael Smith 88a412ed3d [torch.compile] fast inductor (#11108) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2024-12-16 16:15:22 -08:00
Russell Bryant 4863e5fba5 [Core] V1: Use multiprocessing by default (#11074) 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
 2024-12-13 16:27:32 -08:00
Rui QiaoandRui Qiao 72ff3a9686 [core] Bump ray to use _overlap_gpu_communication in compiled graph tests (#10410) 
Signed-off-by: Rui Qiao <ubuntu@ip-172-31-15-128.us-west-2.compute.internal>
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Co-authored-by: Rui Qiao <ubuntu@ip-172-31-15-128.us-west-2.compute.internal>
 2024-12-11 11:36:35 -08:00
youkaichao 75f89dc44c [torch.compile] add a flag to track batchsize statistics (#11059) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-12-10 12:40:52 -08:00
youkaichao 1b62745b1d [core][executor] simplify instance id (#10976) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-12-07 09:33:45 -08:00
Danieleandyoukaichao e4c34c23de [CI/Build] improve python-only dev setup (#9621) 
Signed-off-by: Daniele Trifirò <dtrifiro@redhat.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2024-12-04 21:48:13 +00:00
youkaichao 6e9ff050c8 [misc] do not read HOST_IP (#10644) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-11-25 17:04:50 -08:00
Cyrus Leung 3430857b64 [Misc] Increase default video fetch timeout (#10495) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2024-11-20 23:06:42 -08:00
youkaichao 803f37eaaa [6/N] torch.compile rollout to users (#10437) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-11-19 10:09:03 -08:00
youkaichao 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
Robert ShawNick HillVarun Sundar RabindranathNick HillTyler Michael Smith
 		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
Luka Govedičandyoukaichao 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
litianjianlitianjianDarkLight1337
 		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
youkaichao 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
Flex Wang 29061ed9df [Misc] Add an env var VLLM_LOGGING_PREFIX, if set, it will be prepend to all logging messages (#9590) 2024-10-23 11:17:28 +08:00
Woosuk Kwon 6c5af09b39 [V1] Implement vLLM V1 [1/N] (#9289) 2024-10-22 01:24:07 -07:00
Thomas ParnellChih-Chieh YangCody Yu
 		0c9a5258f9 [Kernel] Add env variable to force flashinfer backend to enable tensor cores (#9497) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Chih-Chieh Yang <chih.chieh.yang@ibm.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
 2024-10-18 17:55:48 -07:00
Luka Govedič 0f41fbe5a3 [torch.compile] Fine-grained CustomOp enabling mechanism (#9300) 2024-10-17 18:36:37 +00:00
Kuntai Du 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
Lucas Wilkinson e312e52b44 [Kernel] Add Exllama as a backend for compressed-tensors (#9395) 2024-10-17 09:48:26 -04:00
youkaichao e4d652ea3e [torch.compile] integration with compilation control (#9058) 2024-10-10 12:39:36 -07:00
sroy745 f3a507f1d3 [Core] Add an environment variable which needs to be set explicitly to allow BlockSpaceManagerV1 (#9149) 2024-10-10 14:17:17 +08:00
youkaichao c8627cd41b [ci][test] use load dummy for testing (#9165) 2024-10-09 00:38:40 -07:00