anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
2,394 Commits 235 Branches 31 Tags
bac3eafc18d2e5389f9db0f50a788e94969f73ea
Commit Graph
96 Commits
Author SHA1 Message Date
tzhouamandClaude Fable 5 bac3eafc18 review: scope KV receive consensus to the TP group, compare full KV state 
Address both P1 review comments:

- The exchange now runs on the stage's tensor-model-parallel group
  (vLLM parallel state) instead of pt.world. World also holds DP
  replicas and PP stages working on different requests, so the old
  group could mix verdicts across requests and — worse — deadlock if
  one replica skipped the exchange (dummy request) while another
  entered it. Within the TP group every skip guard is symmetric.

- Ranks now exchange (primary_received, sorted applied-KV roles)
  instead of a bare flag, using the same field enumeration as
  apply/broadcast, so partially-received CFG companion KV
  (cfg_text/cfg_img) diverging between ranks is caught too. Verdict is
  identical-state-everywhere: any divergence clears KV on every rank;
  symmetric absence is kept because it is consistent (Bagel's empty
  unconditional branch).

Local e2e rerun of test_bagel[tp_vae_patch_parallel_2] passed and the
new path fired on a real divergence (one rank primary+metadata, the
other only cfg_kv_request_ids) — both ranks fell back together.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-08-01 16:29:29 +08:00
tzhouamandClaude Fable 5 6d767a9a5b [BugFix] Make pure-TP KV receive fallback all-or-nothing across ranks 
Fixes the recurring Bagel tp_vae_patch_parallel_2 NCCL ALLREDUCE
timeout (#5627, previously #5487): in pure TP the transfer topology is
LOCAL on every rank — each rank fetches its own per-rank KV key with an
independent recv_timeout and distribute_kv_cache is a no-op. A receive
timeout returns silently, so a single rank that missed its shard fell
back alone into the pipeline's no-KV prefill (Bagel
forward_cache_update_text through the TP-sharded LM) and entered TP
allreduces its peers never joined. The hung [~20, 3584] allreduce
(NumelIn=71680) blocked 600s until the NCCL watchdog killed the worker,
after which every request failed with "DiffusionExecutor is closed".
PR #5482 fixed the orchestrator-level CFG bundle race but never touched
this lower KV-transfer layer, which is why the signature recurred at
its own merge commit.

After the per-rank receive, pure-TP ranks now exchange their receive
flags (rank 0 collects and broadcasts the verdict over the stage world
group's CPU object plane) and act on it together: if any rank missed,
ranks that did receive drop their applied KV — cleared symmetrically
with what apply/broadcast set — so every rank takes the identical no-KV
prefill path and the TP collective schedule can never diverge. The skip
guards (topology, need_recv_cache, dummy warmup id) depend only on
values identical across ranks, so ranks always agree on whether the
exchange happens; a rank whose connector failed to initialize still
participates and reports a miss instead of deadlocking the exchange.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-07-31 11:08:13 +08:00
Shenglei FuandClaude 3b0718f22e [Bugfix] Fix active_stream_window silently stalling audio generation (#5349) (#5373) 
Signed-off-by: Shenglei Fu <sfu@confluent.io>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-07-30 14:56:18 +00:00
Sy03andHongsheng Liu 0feb92bdfa [Bugfix][Minicpm] Support full-duplex three-stage serving (#5380) 
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-07-29 01:58:34 +08:00
Canlin Guo 61324e65d7 [Refactor] Make MOSS-TTS-Local stream session dynamic batch (#5235) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
 2026-07-28 21:38:24 +08:00
Yueqian Lin 8f115164c2 [Bugfix][Connectors] Flush processor tail on terminal async-chunk sends (#5414) 
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-07-27 16:04:08 +00:00
Zhou TaichangClaude Fable 5tzhouam
 		cbab1d4d8f [Rebase] Rebase to vllm 0.26.0 (#5443) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: tzhouam <tzhouam@gmail.com>
 2026-07-27 23:35:49 +08:00
Wallbreazzz e28e389a76 feat(qwen3-tts): add codec_chunk_ramp for gradual chunk size warmup (#5152) 
Signed-off-by: Wallbreazzz <110282866+Wallbreazzz@users.noreply.github.com>
 2026-07-27 04:15:43 +00:00
rein yangandSy03 ad3a162eb8 [perf] Minicpm o4.5 optimization (#5228) 
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Co-authored-by: Sy03 <1370724210@qq.com>
 2026-07-24 17:20:39 +08:00
Sy03lishunyang12Yueqian LinStormMelodyGao HanHongsheng Liu
 		05b794f29b [Full Duplex] Feat: Support Full-Duplex realtime runtime & add MiniCPM-o 4.5 demo (#3907) 
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: StormMelody <22371184@zju.edu.cn>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-07-23 16:45:18 +08:00
Zeyu Huang | 黃澤宇Copilot Autofix powered by AICursor
 		e39f4dddfb [Refactor]: clean up diffusion scheduler interfaces (#5216) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-22 14:05:49 +08:00
Bingyu (Spencer) Liu dcf8b07d39 [Core] Cleanup Omni connector runtime and transfer backends (#5096) 
Signed-off-by: spencerr221 <liubingyu62@gmail.com>
 2026-07-22 09:44:15 +08:00
Honghan Zhuzhuhh97Claude Opus 4.7Gao HanHongsheng Liu
 		f84f0e72fd [Bug Fix] Hunyuan image cfg bugfix (#4752) 
Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
Signed-off-by: dph97 <nenbaying@163.com>
Co-authored-by: zhuhh97 <z00806815@gmail.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-07-15 13:08:15 +08:00
Zhou Taichang a560ed184d [Rebase] Rebase to vllm v0.24.0 (#4709) 2026-06-30 19:41:06 +08:00
Honghan ZhuClaude Opus 4.7zhuhh97
 		5db89b41c4 [Core] hunyuan-image prefetch kv (#4448) 
Signed-off-by: z00806815 <zhuhonghan@huawei.com>
Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
Signed-off-by: dph97 <nenbaying@163.com>
Signed-off-by: zhh <zhh@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: zhuhh97 <zhuhh97@users.noreply.github.com>
 2026-06-25 21:31:49 +08:00
yangyonggit ccb5c53ea5 [Cleanup] Remove dead/stale modules with no repo references (fixes #4009) (#4044) 
Signed-off-by: leo.yang <leo.yang.engineer@gmail.com>
 2026-06-22 09:23:04 +08:00
Peiqi YinHongsheng LiuChenguang ZHENG
 		64a5bb92de [Refactor] Omni Stage Runtime and Distributed Replica Control Plane (#3855) 
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Chenguang ZHENG <645327136@qq.com>
 2026-06-17 14:13:20 +08:00
TJian 5cce797c03 [Bugfix] [CI] [ROCm] [CUDA] Fix voxtral test (#4380) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2026-06-16 16:39:23 +08:00
Zhou Taichang 7b837944a1 [Rebase] Rebase to vllm 0.23.0 (#4286) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-06-13 16:43:02 +00:00
Megha AgarwalCopilotHongsheng Liumeghaagr13Boao ShiTaichang ZhouCursor
 		8f869c8ea5 [Refactor] Output Processor Phase 2: separate multimodal output channel (#1601) (#2744) 
Signed-off-by: Megha Agarwal <agarwalmegha1308@gmail.com>
Signed-off-by: meghaagr13 <divyanshsinghvi@gmail.com>
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: meghaagr13 <divyanshsinghvi@gmail.com>
Co-authored-by: Boao Shi <aoibosh@connect.hku.hk>
Co-authored-by: Taichang Zhou <tzhouam@connect.ust.hk>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-12 15:19:14 +08:00
Sy03Yueqian LinHongsheng Liu
 		e27fd46ab9 [Perf] Optimize Higgs Audio v3 serving (#4204) 
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-11 13:29:31 -07:00
longguoandnpuichigo 73df8326d7 [Bugfix] purge chunk-transfer zombies on every schedule tick to keep engine-core alive on aborts (fixes #3736) (#3774) 
Signed-off-by: abinggo <107740309+abinggo@users.noreply.github.com>
Co-authored-by: npuichigo <11533479+npuichigo@users.noreply.github.com>
 2026-06-10 09:00:23 +08:00
inkcherryzejwangjunkang1991Zejian WangZejian WangCursor
 		e1b0b83238 add moriio transfer engine (#1742) 
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
Signed-off-by: zejwang  <zejwang@amd.com>
Signed-off-by: junkang1991 <junkangchow@gmail.com>
Signed-off-by: Zejian Wang <zejianwang@sjtu.edu.cn>
Co-authored-by: zejwang <zejwang@amd.com>
Co-authored-by: junkang1991 <junkangchow@gmail.com>
Co-authored-by: Zejian Wang <zejianwang@sjtu.edu.cn>
Co-authored-by: Zejian Wang <Zejian.Wang@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-10 08:37:33 +08:00
ChenWenjing 3842970a82 [bugfix] fix streaming input issue after rebase 0.22.0 (#4085) 
Signed-off-by: CHEN <116010019@link.cuhk.edu.cn>
 2026-06-03 16:07:41 +08:00
Yueqian LinandHongsheng Liu c067485030 [Perf][TTS] Bounded-K active-stream window for Stage 1 (RFC #3535) (#3592) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-01 21:59:10 +08:00
+1
Zhou TaichangClaude Opus 4.7skfZheng WengangHongsheng LiuWeiQing ChenSYLARYueqian Linnainiu258JasonYueqian Lin
 		f92d84fcf9 [Rebase] Rebase to vllm releases/v0.22.0 (#3891) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Signed-off-by: david6666666 <530634352@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: nainiu258 <cperfect02@163.com>
Signed-off-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Signed-off-by: JasonJ2021 <jasonj@zju.edu.cn>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: skf <54565339+skf-1999@users.noreply.github.com>
Co-authored-by: Zheng Wengang <zwg0606@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Co-authored-by: Jason <72191212+JasonJ2021@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-06-01 11:08:12 +08:00
ChenWenjing 5dfdf584dd [Feat]audio streaming input for async chunk (#3614) 
Signed-off-by: CHEN <116010019@link.cuhk.edu.cn>
 2026-05-31 17:39:25 +08:00
JiangJie Zhang 6fa9dbbe42 [Diffusion] Unify diffusion request identity on request_id (#3744) 
Signed-off-by: jader <yjader@foxmail.com>
 2026-05-28 14:56:56 +08:00
LancerandAlicia 5c3c81920b [Bugfix] Ensure stage and diffusion subprocesses exit when parent dies unexpectedly (#3751) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
 2026-05-28 08:22:04 +08:00
Sy03andYueqian Lin d37912b071 [TTS][Perf] Optimize Fish Speech S2 Pro high-concurrency serving (#3773) 
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-05-27 13:25:49 -05:00
yangsonglin13 1c530d984d Yuanrong TransferEngine Connector for NPU (#3180) 
Signed-off-by: yangsonglin13 <yangsonglin566@gmail.com>
 2026-05-20 14:51:33 +08:00
chickeytonandherotai214 e277feacaf [large-scale-serving] Integrate OmniCoordinator into stage engine pipeline (#3569) 
Signed-off-by: chickeyton <ngton2014@gmail.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
 2026-05-19 12:08:20 +08:00
amy-why-3459 e7ee5de09f [BugFix] Fix the issue of thinker requests being preempted, causing shape mismatch. (#3147) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-05-15 17:07:42 +08:00
NATUREandHongsheng Liu 82a0b3a467 [2/5] [core]refactor communication layer: PR 2 of 5 Qwen3 Omni non async (#2677) 
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-05-15 14:14:08 +08:00
dengyunyangand汪志鹏 94254e015f [BugFix] fix shm connector (#3583) 
Signed-off-by: dengyunyang <584797741@qq.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-05-14 20:07:12 +08:00
dsinghvi e40076e872 [Refactor] msgspec standardisation for data entry key names and improved type checks (#3149) 
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com>
 2026-05-12 14:30:13 +08:00
wuhang 3f27ffbd4d [Misc] Clean logs for image gen task (#3414) 
Signed-off-by: wuhang <wuhang6@huawei.com>
 2026-05-11 12:16:05 +00:00
dengyunyang 857356d5b7 [Feature] hunyuanimage support flash attn (#2981) 
Signed-off-by: dengyunyang <584797741@qq.com>
 2026-05-10 22:08:24 +08:00
Nick Cao e6466cf0e6 [Refactor] Replace and ban a few torch.cuda functions in favor of torch.accelerator replacements. (#3365) 
Signed-off-by: Nick Cao <ncao@redhat.com>
 2026-05-07 23:23:59 +08:00
Zhou TaichangandYuanheng Zhao 7f2b1e9386 [Rebase] Rebase to vllm 0.20.0 (#3232) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
 2026-04-30 09:56:59 +12:00
dsinghviZhou TaichangHongsheng Liu
 		2390350533 [Refactor] Standardize data entry key names to {type}.{qualifier} format (#1829) 
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-04-25 18:15:38 +08:00
NumberWan 678af19240 [Feature] Coordinator PUB mechanism optimization (#2442) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
 2026-04-24 15:09:23 +08:00
NumberWan b60a661b3f [Feature] Load Balancer - Add LeastQueueLengthBalancer RoundRobinBalancer (#2448) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
 2026-04-21 18:17:28 +00:00
SYLARreidliu41xiaohajiayouAlex BrooksHongsheng Liu
 		a3903810fe [Config Refactor][2/N] Pipeline + Deploy Config Schema (#2383) 
Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: xiaohajiayou <75477391+xiaohajiayou@users.noreply.github.com>
Co-authored-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-04-19 14:36:00 +12:00
amy-why-3459 b88d3ce75e [BugFix] Fixing occasional engine crashes caused by abort requests (#2871) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-04-17 09:15:35 +00:00
NATUREandHongsheng Liu 4d816ff1de [Feature] Bagel: Support tp+cfg parallel using mooncake transfer engine connector (#2705) 
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-04-16 16:25:13 +08:00
NATURE 6d01a8b506 [Omni Connector] Omni Transfer Engine Connector: Enable 1-receiver-to-N-senders to support Bagel TP/CFG parallel (#2731) 
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
 2026-04-14 16:06:37 +08:00
Jinhengahengljhnatureofnature
 		c3c736d488 [Feature] Port Bagel RDMA flow to latest main (#2000) 
Signed-off-by: Jinheng Li <ahengljh@gmail.com>
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Co-authored-by: ahengljh <ahengljh@users.noreply.github.com>
Co-authored-by: natureofnature <wzliu@connect.hku.hk>
 2026-04-08 14:55:35 +08:00
pikaxingeandAlicia c9dbc0955b [Bugfix] Prevent Silent Stage Dropouts: fix coordinator reconnect bug, close/update race, and heartbeat stall (#1899) 
Signed-off-by: pikaxinge <2392811793@qq.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
 2026-04-08 00:48:26 +08:00
indevnandlinyueqian 6fc38e0467 [Model][Core] Enable async_chunk streaming pipeline for CosyVoice3 (#1703) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: indevn <indevn@outlook.com>
Co-authored-by: linyueqian <linyueqian@outlook.com>
 2026-04-05 06:11:33 +00:00