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
597 Commits
Author SHA1 Message Date
billishyahaoandZhai Feiyue 742369d35a [Frontend][Bugfix] support prefill decode disaggregation on deepseek (#14824) 
Signed-off-by: billishyahao <bill.he@amd.com>
Co-authored-by: Zhai Feiyue <80079571+ZhaiFeiyue@users.noreply.github.com>
 2025-03-20 00:00:33 -07:00
Alexander Matveev cfbca8a2f2 [V1] TPU - Tensor parallel MP support (#15059) 2025-03-20 00:55:18 +00:00
hoshi-hiyougaandyoukaichao 414919138b [Bugfix] torchrun compatibility (#14899) 
Signed-off-by: hiyouga <hiyouga@buaa.edu.cn>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-03-18 05:49:27 -07:00
Nick Hill b82662d952 [BugFix] Fix torch distributed stateless PG backend init (#14870) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-03-15 20:26:19 -07:00
yasu52 3fb17d26c8 [Doc] Fix typo in documentation (#14783) 
Signed-off-by: yasu52 <tsuguro4649@gmail.com>
 2025-03-13 20:33:09 -07:00
Mathis Felardos 1bd32bc8dd [Config][Disaggregated] Add timeout configuration for the torch.store and add KVTransferConfig.kv_connector_extra_config (#14367) 
Signed-off-by: Mathis Felardos <mathis@mistral.ai>
 2025-03-12 20:15:20 -07:00
gnovack d6123170d5 [Neuron] Add Neuron device communicator for vLLM v1 (#14085) 2025-03-10 18:37:04 -07:00
Jiayi Yao 6d7f037748 [Feat] Support chunked prefill for LMCache connector (#14505) 
Signed-off-by: YaoJiayi <120040070@link.cuhk.edu.cn>
 2025-03-08 19:30:06 -08:00
Mathis Felardos 980385f8c1 [Bugfix][Disaggregated] Add a check in send_kv_caches_and_hidden_states and fix the reshape of the KVCache (#14369) 
Signed-off-by: Mathis Felardos <mathis@mistral.ai>
 2025-03-07 22:39:31 -08:00
Kuntai Du 288ca110f6 [Security] Serialize using safetensors instead of pickle in Mooncake Pipe (#14228) 
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
 2025-03-04 21:10:32 +00:00
Mathis Felardos b9e41734c5 [Bugfix][Disaggregated] patch the inflight batching on the decode node in SimpleConnector to avoid hangs in SimpleBuffer (nccl based) (#13987) 
Signed-off-by: Mathis Felardos <mathis@mistral.ai>
 2025-02-28 07:53:45 +00:00
Harry Mellor 145944cb94 Improve pipeline partitioning (#13839) 2025-02-25 18:53:56 -08:00
Jiayi Yao 2f42a4888c [Feature] Support KV cache offloading and disagg prefill with LMCache connector. (#12953) 2025-02-25 00:38:42 -08:00
cjackal 51010a1807 [Misc] set single whitespace between log sentences (#13771) 
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
 2025-02-25 10:26:12 +08:00
Nick Hill 5a2ba16f5c [Core][Distributed] Use IPC (domain socket) ZMQ socket for local comms (#13688) 2025-02-23 02:54:29 -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
Isotr0py b2c3fc5d65 [Bugfix][CPU] Fix cpu all-reduce using native pytorch implementation (#13586) 2025-02-20 22:24:17 -08:00
Yan Ma 30513d1cb6 [Bugfix] fix xpu communicator (#13368) 
Signed-off-by: yan ma <yan.ma@intel.com>
 2025-02-17 20:59:18 +08:00
youkaichao a0231b7c25 [platform] add base class for communicators (#13208) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-02-16 22:14:22 +08:00
Lu Fang 009439caeb Simplify logic of locating CUDART so file path (#13203) 
Signed-off-by: Lu Fang <lufang@fb.com>
 2025-02-13 13:52:41 +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
Cyrus Leung 8a69e0e20e [CI/Build] Auto-fix Markdown files (#12941) 2025-02-08 04:25:15 -08:00
Lu Fang 45cbc4991d [Bugfix] Fix disagg hang caused by the prefill and decode communication issues (#12723) 
Signed-off-by: Lu Fang <lufang@fb.com>
 2025-02-07 16:39:50 -08:00
ZSL98andzhangshulai 433c4a4923 Make vllm compatible with verl (#12824) 
Co-authored-by: zhangshulai <zhangshulai@bytedance.com>
 2025-02-07 11:54:20 +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
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
Harry Mellor 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
Jani Monoses 9c485d9e25 [Core] Free CPU pinned memory on environment cleanup (#10477) 2025-01-21 11:56:41 -08:00
shangmingc df450aa567 [Bugfix] Fix num_heads value for simple connector when tp enabled (#12074) 
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
 2025-01-20 02:56:43 +00:00
youkaichao ad34c0df0f [core] platform agnostic executor via collective_rpc (#11256) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-01-15 13:45:21 +08:00
youkaichao 310aca88c9 [perf]fix current stream (#11870) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-01-09 07:18:21 +00:00
Harry Mellor 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
XiaobingZhang e512f76a89 fix init error for MessageQueue when n_local_reader is zero (#11768) 2025-01-07 06:12:48 +00:00
cennn 9e764e7b10 [distributed] remove pynccl's redundant change_state (#11749) 2025-01-06 09:05:48 +08:00
cennn 635b897246 [distributed] remove pynccl's redundant stream (#11744) 2025-01-05 23:09:11 +08:00
Yan Burman 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
youkaichao b12e87f942 [platforms] enable platform plugins (#11602) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-12-30 20:24:45 +08:00
Kuntai Du faef77c0d6 [Misc] KV cache transfer connector registry (#11481) 
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
 2024-12-29 16:08:09 +00:00
shangmingc d263bd9df7 [Core] Support disaggregated prefill with Mooncake Transfer Engine (#10884) 
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
 2024-12-15 21:28:18 +00:00
shangmingc db6c264a1e [Bugfix] Fix value unpack error of simple connector for KVCache transfer. (#11058) 
Signed-off-by: ShangmingCai <csmthu@gmail.com>
 2024-12-12 21:19:17 +00:00
youkaichao 62de37a38e [core][distributed] initialization from StatelessProcessGroup (#10986) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-12-12 09:04:19 +00:00
Tyler Michael Smith 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
youkaichao 21fe7b481a [core][distributed] add pynccl broadcast (#10843) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-12-03 04:53:23 +00:00
Kuntai Du 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
Sage Mooreandyoukaichao 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
Tyler Michael Smith 978b39744b [Misc] Add pynccl wrappers for all_gather and reduce_scatter (#9432) 2024-11-22 22:14:03 -05:00
youkaichao 0d4ea3fb5c [core][distributed] use tcp store directly (#10275) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-11-12 17:36:08 -08:00
youkaichao e6de9784d2 [core][distributed] add stateless process group (#10216) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-11-11 09:02:14 -08:00
Yan Ma f10797c0ce [Bugfix][XPU] Fix xpu tp by introducing XpuCommunicator (#10144) 
Signed-off-by: yan ma <yan.ma@intel.com>
 2024-11-08 09:41:03 +00:00
Hanzhi Zhou 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