hsliuustc0106
33297bdb9d
[Model] Fold the DLO warmup recipe into _make_dummy_request
...
One request builder instead of two: when the generic dummy run opts out
(num_frames <= 0), _make_dummy_request itself falls back to the model's
declared dlo_dummy_run_recipe under distributed layerwise offload, and
_dummy_run keeps its original shape. The recipe request is text-only even
for image-capable models — the recipe names its own task, and t2va rejects
image conditions; caught by a boot smoke after folding (the standalone
builder had built the prompt fresh) and pinned by a regression test.
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-08-26 15:35:13 +08:00
hsliuustc0106
f4394f1d3d
[Model] Prime DLO cache retention with a startup warmup
...
Models whose request geometry opts out of the generic dummy run (H3: t2va
needs an explicit aspect ratio and a bounded duration) can declare a
dlo_dummy_run_recipe. Under distributed layerwise offload the engine's
startup warmup runs it, so the learned cache-retention budget is primed
before real traffic instead of on the first request.
H3 declares a maximum-duration t2va generation: duration is the only
workload variable at the fixed 768 short edge, so the learned peak
dominates every production request and no real request re-learns. Validated
on L20X: all cold-start releases happen during the startup warmup, zero
during requests; first request 15.91 s vs 16.7 s unwarmed, steady 14.9 s;
startup gains one max-length generation (~10-20 s). Non-DLO deployments
keep the opted-out generic warmup unchanged.
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-08-26 15:06:08 +08:00
ivanusto and Hongsheng Liu
f09bdcbc7d
[Bugfix] Make the async-output wait bound configurable and default it higher ( #6255 )
...
Signed-off-by: ivanusto <ivanusto@gmail.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-22 22:10:30 +08:00
Wang fuyin and Hongsheng Liu
72ee535fcd
[Diffusion] Add native paged KV backend for diffusion workers ( #6102 )
...
Signed-off-by: Acerak01-fy <wfy2003324@163.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-22 21:45:45 +08:00
Yukim1 and zwhzzz0821
0a1846aa45
[Diffusion] Add native KV cache initialization and Scheduler-managed block allocation ( #6094 )
...
Signed-off-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com >
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com >
2026-08-18 07:00:24 +00:00
Samit
136cb27b05
[Bugfix] Fix lost async diffusion outputs in request-level batching ( #6023 )
...
Signed-off-by: samithuang <285365963@qq.com >
2026-08-15 18:27:51 +08:00
Wang fuyin and Hongsheng Liu
af3faa6c1e
[Diffusion] Add Worker contracts and RPC plumbing for Scheduler-managed paged KV cache ( #5550 )
...
Signed-off-by: Acerak01-fy <wfy2003324@163.com >
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-11 14:55:42 +08:00
Zeyu Huang | 黃澤宇 and Hongsheng Liu
33dd9a5a3e
[Core][Refactor][Diffusion] refactor request scheduler's admission wait policy ( #5843 )
...
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-10 15:06:27 +08:00
6ae7ff7846
[Diffusion] Prepare HunyuanImage3 for Scheduler-managed paged KV cache ( #5541 )
...
Signed-off-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com >
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-08-10 08:48:56 +08:00
SYLAR
44e38d7b38
[Diffusion] Fix DLO DP concurrent request execution ( #5864 )
...
Signed-off-by: lishunyang12 <lishunyang12@163.com >
2026-08-08 08:24:42 +08:00
SYLAR and lishunyang12
1c2a81f6d8
feat(minimax-h3): enable 2x RTX 4090/5090 with DLO ( #5764 )
...
Signed-off-by: lishunyang12 <lishunyang03@gmail.com >
Signed-off-by: lishunyang12 <lishunyang12@163.com >
Co-authored-by: lishunyang12 <lishunyang03@gmail.com >
2026-08-06 09:02:29 +08:00
evanchueng and david6666666
744c65b730
[Feature] Distributed layerwise offload with DP multi-concurrency + mmap weight… ( #5397 )
...
Signed-off-by: evanchueng <evanchueng@outlook.com >
Signed-off-by: david6666666 <530634352@qq.com >
Co-authored-by: david6666666 <530634352@qq.com >
2026-07-30 13:35:38 +00:00
zzh and dengyunyang
dba05c3517
Enable Diffusion Image models asynchronous output ( #4981 )
...
Signed-off-by: zzh <943967662@qq.com >
Co-authored-by: dengyunyang <584797741@qq.com >
2026-07-29 17:21:55 +00:00
bjf-frz and Hongsheng Liu
be667a8067
[Refact] Refactor diffusion output streaming ( #5166 )
...
Signed-off-by: bjf-frz <frz123db@gmail.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-07-23 10:06:08 +08:00
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
bjf-frz
1a4a042a83
[REFACT]Refactor diffusion outputs to payload metadata ( #4922 )
...
Signed-off-by: bjf-frz <frz123db@gmail.com >
2026-07-14 17:24:03 +08:00
Zhou Taichang
86bdcaf3d5
[BDE] Phase 1: engine-level KV cache management for DreamZero (RFC #4366 ) ( #4534 )
2026-07-05 07:17:58 +08:00
JiangJie Zhang and Samit
c45ac74d43
[Core][Frontend] Support request-level batching for diffusion pipelines ( #4079 )
...
Signed-off-by: jader <yjader@foxmail.com >
Co-authored-by: Samit <285365963@qq.com >
2026-06-29 18:09:19 +02:00
3901ad8165
[feat] Streaming diffusion video generation output ( #3737 )
...
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 >
2026-06-23 09:57:53 +00:00
f75c437a60
[Refactor]Base class for dit pipelines with unified parameter declaration[1/N] ( #4225 )
...
Signed-off-by: princepride <wangzhipeng628@gmail.com >
Co-authored-by: Cursor <cursoragent@cursor.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-06-18 17:14:18 +08:00
Hongsheng Liu
aff0af9754
[Refactor] Extract diffusion output formatting boundary ( #4407 )
...
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com >
2026-06-15 22:50:50 +08:00
Yuzhu Dong
e2e79177db
Support DROID policy server for Cosmos3 OpenPI ( #4282 )
...
Signed-off-by: yuzhud <yuzhudong@gmail.com >
2026-06-15 21:22:59 +08:00
MaciejBalaNV and Hongsheng Liu
03cc888485
[refactor] Refactor guardrail error handling - add 400 error code ( #4297 )
...
Signed-off-by: Maciej Bala <mbala@nvidia.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-06-11 21:09:24 +00:00
Chendi.Xue and Mengkejiergeli Ba
31f882935d
[XPU][S2V] Optimize Wan2.2 S2V: RoPE refactor + cache_dit enabling ( #4062 )
...
Signed-off-by: Chendi Xue <chendi.xue@intel.com >
Co-authored-by: Mengkejiergeli Ba <mengkejiergeli.ba@intel.com >
2026-06-05 06:20:16 +08:00
bdfc77147d
[Diffusion] DreamZero world model integration with CFG parallel + OpenPI serving ( #2162 )
...
Signed-off-by: Meng <meng_chen99@163.com >
Signed-off-by: Yangshen Deng <yangshen.d@outlook.com >
Signed-off-by: Suli Wang <50828270+wsl2000@users.noreply.github.com >
Co-authored-by: Meng <meng_chen99@163.com >
Co-authored-by: Suli Wang <50828270+wsl2000@users.noreply.github.com >
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com >
2026-06-02 19:50:20 +00:00
bc794e625f
Add Cosmos3 model support ( #3454 )
...
Signed-off-by: Maciej Bala <mbala@nvidia.com >
Signed-off-by: MaciejBalaNV <mbala@nvidia.com >
Signed-off-by: lishunyang12 <lishunyang12@163.com >
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com >
Co-authored-by: lishunyang12 <lishunyang12@163.com >
2026-06-02 04:04:31 +08:00
+1
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
WeiQing Chen
67bb9b4a12
[CI][Bugfix] Fix LTX audio-video warmup output typing ( #3964 )
...
Signed-off-by: david6666666 <530634352@qq.com >
2026-05-29 07:46:02 +00:00
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
373d3c7476
[Blackwell] Add CUDNN_ATTN and FLASHINFER_ATTN backends for diffusion (auto-route) ( #3079 )
...
Signed-off-by: lishunyang <lishunyang12@163.com >
Signed-off-by: Zhang <jianmusings@gmail.com >
Signed-off-by: Zhang Jian <jianmusings@gmail.com >
Co-authored-by: frauttauteffasu <247219357+frauttauteffasu@users.noreply.github.com >
Co-authored-by: Zhang Jian <jianmusings@gmail.com >
2026-05-28 11:09:25 +08:00
wuhang and Hongsheng Liu
4ba8e14981
Fix diffusion engine cleanup lifecycle ( #3494 )
...
Signed-off-by: wuhang <wuhang6@huawei.com >
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
2026-05-18 08:54:57 +08:00
knlnguyen1802 and Samit
aa1184d737
[bugfix, rl] Fix race condition bug on async running for diffusion model ( #3379 )
...
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com >
Co-authored-by: Samit <285365963@qq.com >
2026-05-12 14:55:30 +08:00
汪志鹏
c9a8556c24
[New Model]: Add sensenova u1 support ( #3319 )
...
Signed-off-by: princepride <wangzhipeng628@gmail.com >
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com >
2026-05-11 22:19:00 +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
e49fbd8a2d
[Feat] DiffusionEngine Support async batch infer ( #2729 )
...
Signed-off-by: Semmer <semmer@live.cn >
Signed-off-by: jader <yjader@foxmail.com >
Signed-off-by: asukaqaq-s <1311722138@qq.com >
Co-authored-by: asukaqaq-s <1311722138@qq.com >
Co-authored-by: jader <yjader@foxmail.com >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk >
2026-05-06 09:47:13 +12:00
Zeyu Huang | 黃澤宇 and Copilot Autofix powered by AI
f19891e4f1
[bugfix][CI] Diffusers backend update ( #3096 )
...
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 >
2026-05-05 20:54:39 +08:00
c708aecb18
[Diffusion] [Model] Support AudioX ( #2077 )
...
Signed-off-by: Zhang Jian <jianmusings@gmail.com >
Signed-off-by: Zhang <jianmusings@gmail.com >
Signed-off-by: Zhang <zhang.jian@u.nus.edu >
Signed-off-by: Zhang Jian <e0322744@u.nus.edu >
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com >
Co-authored-by: Zhang Jian <e0322744@u.nus.edu >
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com >
2026-05-04 10:24:35 -04:00
539fa57006
fix(diffusion): correct metric keys, remove duplication, minor cleanup ( #2692 )
...
Signed-off-by: willamhou <willamhou@ceresman.com >
Co-authored-by: Claude <noreply@anthropic.com >
Co-authored-by: Happy <yesreply@happy.engineering >
2026-04-27 21:40:31 +08:00
52b53367ef
[Enhancement] Engine runtime errors ( #2426 )
...
Signed-off-by: Daniel Huang <daniel1.huang@intel.com >
Signed-off-by: Daniel Huang <pilotflyer824@gmail.com >
Signed-off-by: bjf-frz <frz123db@gmail.com >
Co-authored-by: Chenguang Zheng <645327136@qq.com >
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk >
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com >
Co-authored-by: bjf-frz <frz123db@gmail.com >
2026-04-21 14:46:05 +08:00
WeiQing Chen
6c6551dff8
[Feature] feat: add video frame interpolation postprocess ( #2555 )
...
Signed-off-by: David Chen <530634352@qq.com >
2026-04-15 11:52:20 +08:00
78bef62f82
[Profiler] Add Nsight Systems support for serving ( #1098 )
...
Signed-off-by: Jinheng Li <ahengljh@gmail.com >
Signed-off-by: Canlin Guo <961750412@qq.com >
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com >
Co-authored-by: Canlin Guo <961750412@qq.com >
2026-04-10 18:13:12 +08:00
Samit
956f53b278
[Refactor] Use trajectory_* fields for Qwen-Image structured RL outputs ( #2513 )
...
Signed-off-by: samithuang <285365963@qq.com >
2026-04-09 03:06:40 -07:00
汪志鹏
9d87229a30
[MagiHuman] Fix audio sample rate and fps propagation for online serving ( #2554 )
...
Signed-off-by: princepride <wangzhipeng628@gmail.com >
2026-04-09 06:52:12 +00:00
cb6a8739c1
[Feature] Add trajectory recording to BAGEL denoising loop ( #2483 )
...
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu >
Signed-off-by: Zhengyuan Su (苏政渊) <su.zhengyuan@u.nus.edu >
Co-authored-by: Claude <noreply@anthropic.com >
Co-authored-by: Samit <285365963@qq.com >
2026-04-08 10:43:01 +08:00
Zhou Taichang
2804a85e58
[Rebase] Rebase to vllm v0.19.0 ( #2475 )
2026-04-04 15:03:32 +08:00
Lidang Jiang and Claude Opus 4.6
515d15ef87
[Cleanup] Replace bare print() with logger and use specific exception types ( #2228 )
...
Signed-off-by: Lidang Jiang <lidangjiang@gmail.com >
Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com >
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-04-03 23:59:07 +08:00
Wu JIAZHEN and jader
3fd4a4dc27
[Feat] Support step-boundary abort in diffusion ( #1769 )
...
Signed-off-by: jader <yjader@foxmail.com >
Signed-off-by: asukaqaq-s <1311722138@qq.com >
Co-authored-by: jader <yjader@foxmail.com >
2026-04-01 17:25:02 +08:00
7217557950
[Refactor] Unify torch profiler for omni and diffusion models ( #2099 )
...
Signed-off-by: gcanlin <canlinguosdu@gmail.com >
Signed-off-by: Samit <285365963@qq.com >
Co-authored-by: Samit <285365963@qq.com >
Co-authored-by: lishunyang lishunyang12@163.com
2026-03-24 15:25:52 +08:00
Didan Deng
1f5eca5686
[Perf] Qwen-Image Performance Nightly CI test ( #1805 )
...
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com >
2026-03-24 00:19:20 +08:00
61cd532cff
[Refactor] Refactor Diffusion Scheduler/Executor Boundaries and Request State Flow ( #1625 )
...
Signed-off-by: jader <yjader@foxmail.com >
Signed-off-by: JiangJie Zhang <76905040+yJader@users.noreply.github.com >
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com >
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com >
2026-03-23 20:25:32 +08:00