xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-16 12:55:02 +08:00
Code Issues Packages Projects Releases Wiki Activity
8,299 Commits 155 Branches 89 Tags
Commit Graph

8299 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
wxsm
f4135232b9
feat(distributed): add get_required_kvcache_layout class method to kv connector api (#20433) 
Signed-off-by: wxsm <wxsms@foxmail.com>
 2025-07-30 16:41:51 +00:00
Chenguang Zheng
4904e53c32
[Bugfix] SharedStorage Connector for V1 PD multimodal (#21611) 
Signed-off-by: fake0fan <645327136@qq.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
 2025-07-30 09:18:37 -07:00
Cyrus Leung
004203e953
[CI/Build] Fix registry tests (#21934) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-30 09:10:41 -07:00
633WHU
5c765aec65
[Bugfix] Fix TypeError in scheduler when comparing mixed request_id types (#21816) 
Signed-off-by: chiliu <chiliu@paypal.com>
Co-authored-by: chiliu <chiliu@paypal.com>
 2025-07-30 08:54:44 -07:00
Yong Hoon Shin
ad510309ee
Override attention metadata for fast prefill in some KV sharing setups (#21590) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-07-30 08:54:15 -07:00
Cyrus Leung
366f6b3a4d
[Bugfix] Fix multi-api server not working for text models (#21933) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-30 08:42:05 -07:00
Isotr0py
6e599eebe8
[Bugfix] Fix OOM tests in initialization test (#21921) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-07-30 07:35:47 -07:00
Harry Mellor
88edf5994c
[Docs] Reduce the size of the built docs (#21920) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-07-30 07:35:08 -07:00
Po-Han Huang (NVIDIA)
ff08e51940
[NVIDIA] Fix Llama4 Scout FP4 functionality issues (#21499) 
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
 2025-07-30 07:33:40 -07:00
Ruixiang Tan
8f4a1c9a04
[Misc] Improve code readability of KVCacheManager (#21673) 
Signed-off-by: tanruixiang <tanruixiang0104@gmail.com>
Signed-off-by: Ruixiang Tan <819464715@qq.com>
Signed-off-by: GitHub <noreply@github.com>
 2025-07-30 07:20:43 -07:00
Harry Mellor
36ede45989
Reduce time wasted in GitHub Actions using concurrency (#21919) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-07-30 07:18:02 -07:00
Cyrus Leung
0e40b26073
[CI/Build] Only run markdownlint in CI (#21892) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-07-30 07:17:14 -07:00
Wentao Ye
0271c2ff2f
[Test] Add Benchmark and Unit Test for per_token_group_quant (#21860) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-30 07:15:02 -07:00
youkaichao
e91d3c9cda
[misc] skip p2p check by default (#21904) 2025-07-30 22:05:04 +08:00
Yan Pashkovsky
bf668b5bf5
[Feature] Support multiple api keys in server (#18548) 
Signed-off-by: Yan Pashkovsky <yanp.bugz@gmail.com>
 2025-07-30 07:03:23 -07:00
rongfu.leng
da3e0bd6e5
[Bugfix] we should use metavar is not choices (#21902) 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
 2025-07-30 06:51:58 -07:00
Cyrus Leung
fcfd1eb9c5
[Doc] Remove vLLM prefix and add citation for PagedAttention (#21910) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-30 06:36:34 -07:00
aladerran
d979dd6beb
[Feature][EPLB] Add eplb support for Qwen3 (#20815) 
Signed-off-by: aladerran <aladerran@gmail.com>
 2025-07-30 06:27:57 -07:00
Eric Curtin
b876860c62
[Hardware][CPU] Build fix for ARM without BF16 (#21848) 
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
 2025-07-30 06:22:00 -07:00
Patrick von Platen
13986365a9
Add @patrickvonplaten as maintainer of mistral's related files. (#21928) 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2025-07-30 20:42:51 +08:00
Hongsheng Liu
5c8fe389d6
[Docs] Fix the example code of streaming chat completions in reasoning (#21825) 
Signed-off-by: wangzi <3220100013@zju.edu.cn>
Co-authored-by: wangzi <3220100013@zju.edu.cn>
Co-authored-by: Zi Wang <66560864+BruceW-07@users.noreply.github.com>
 2025-07-30 12:11:58 +00:00
Cyrus Leung
5bbaf492a6
[Doc] Update partial support (#21916) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-30 01:32:39 -07:00
Peter Pan
533db0935d
[benchmark] add max-concurrency in result table (#21095) 
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
 2025-07-30 01:15:43 -07:00
Jee Jee Li
fc91da5499
[Model] Remove DSV2 unused code (#21903) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-30 00:55:03 -07:00
Varun Vinayak Shenoy
547795232d
[Tests] Fixing bug inside MultiModalProfiler. (#21842) 
Signed-off-by: Varun Shenoy <varun.vinayak.shenoy@oracle.com>
 2025-07-30 00:44:15 -07:00
Kebe
30ef30ed5a
[CI] rollback lint-and-deploy pipeline using amd machine (#21912) 
Signed-off-by: Kebe <mail@kebe7jun.com>
 2025-07-30 00:37:59 -07:00
Jee Jee Li
02f82fe438
[Doc] Update Intern-S1 info (#21908) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-29 23:58:57 -07:00
Cyrus Leung
2ca5f82c2a
[Misc] Remove redundant config definitions (#21891) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-29 23:54:18 -07:00
Louie Tsai
6f8d261882
Update vLLM Benchmark Suite for Xeon based on 0.9.2 release (#21486) 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
 2025-07-30 05:57:03 +00:00
Ricardo Decal
4cd7fe6cea
[Docs] Expand introduction to Ray in Multi-node deployment section (#21584) 
Signed-off-by: Ricardo Decal <rdecal@anyscale.com>
 2025-07-29 22:07:28 -07:00
Cyrus Leung
16f3250527
[CI/Build] Fix pre-commit failure in docs (#21897) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-29 21:53:08 -07:00
Tao He
e3bc17ceea
Add @sighingnow as maintainer of qwen's related files. (#21895) 
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
 2025-07-29 21:30:44 -07:00
Kunshang Ji
05cbbe20c5
[XPU] use ZE_AFFINITY_MASK for device select on xpu (#21815) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-07-30 03:56:14 +00:00
wang.yuqi
65f311ce59
[Frontend] Add LLM.reward specific to reward models (#21720) 
Signed-off-by: wang.yuqi <noooop@126.com>
 2025-07-29 20:56:03 -07:00
Wentao Ye
1b0a155534
[Perf] Using __nv_fp8_e4m3 instead of c10::e4m3 for per_token_group_quant (#21867) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-29 21:50:46 -06:00
Cyrus Leung
44bc46da60
[Bugfix] Actually disable processing cache when API server is scaled out (#21839) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-29 20:36:04 -07:00
MingzhenHan
b7b23da4d2
[Bugfix] Fix comment typo of get_num_common_prefix_blocks() (#21827) 
Signed-off-by: MingzhenHan <hanmingzhen2002@outlook.com>
 2025-07-29 20:35:33 -07:00
Areeb Syed
fdde18229e
[Bugfix] Fix shape mismatch assertion error when loading Gemma3n model with BitsAndBytes quantization (#21808) 
Signed-off-by: sydarb <areebsyed237@gmail.com>
 2025-07-30 11:35:21 +08:00
Csrayz
b917da442b
Expose PyTorch profiler configuration to environment variables (#21803) 
Signed-off-by: Csrayz <33659823+Csrayz@users.noreply.github.com>
 2025-07-29 19:46:31 -07:00
Michael Goin
fb58e3a651
[Docs] Update docker.md with HF_TOKEN, new model, and podman fix (#21856) 2025-07-29 19:45:41 -07:00
Chen Zhang
76080cff79
[DOC] Fix path of v1 related figures (#21868) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-07-29 19:45:18 -07:00
Harry Mellor
ba5c5e5404
[Docs] Switch to better markdown linting pre-commit hook (#21851) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-07-29 19:45:08 -07:00
Chen Zhang
555e7225bc
[v1][attention] Support Hybrid Allocator + FlashInfer (#21412) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-07-30 01:45:29 +00:00
milesial
0e36abf993
[Bugfix] Correct max tokens for non-contiguous embeds (#21798) 
Signed-off-by: Alexandre Milesi <30204471+milesial@users.noreply.github.com>
Co-authored-by: Alexandre Milesi <30204471+milesial@users.noreply.github.com>
 2025-07-30 01:16:25 +00:00
Simon Mo
452b2a3180
[ci] mark blackwell test optional for now (#21878) 2025-07-29 18:03:27 -07:00
Simon Mo
0d0cc9e150
[ci] add b200 test placeholder (#21866) 
Signed-off-by: simon-mo <simon.mo@hey.com>
 2025-07-29 17:11:50 -07:00
Yong Hoon Shin
9266d98048
[BugFix] Fix interleaved sliding window not set for Gemma3n (#21863) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-07-29 16:34:19 -07:00
Gregory Shtrasberg
176bbce1db
Revert "[AMD][CI/Build] Fix the AMD issue caused by inappropriate of symbol exposure (#21647)" (#21850) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-07-29 21:56:29 +00:00
Doug Smith
a1873db23d
docker: docker-aware precompiled wheel support (#21127) 
Signed-off-by: dougbtv <dosmith@redhat.com>
 2025-07-29 14:45:19 -07:00
Michael Goin
a33ea28b1b
Add flashinfer_python to CUDA wheel requirements (#21389) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-07-29 12:51:58 -07:00