anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
1,692 Commits 235 Branches 31 Tags
f0cec3ecd4e1991bd1cf9c0a6bbad9d0fe80480b
Commit Graph
298 Commits
Author SHA1 Message Date
SYLAR f0cec3ecd4 Merge branch 'main' into lance-model-support 2026-05-22 04:13:58 +08:00
lishunyang12 7b885f9d13 [Lance] Precision matching, recipe, and README cleanup 
- Precision matching across the Lance transformer and pipeline so vLLM-Omni
  outputs match the upstream reference end-to-end (text2img / img2img /
  text2video / video2video / image and video understanding).
- Add recipes/ByteDance/Lance.md covering all single-stage modalities for
  offline + online; register it in recipes/README.md.
- Offline README: document --height/--width and update the default
  resolution to 1024x1024 (matches the upstream inference_lance.sh).
- Gitignore lance_compare/ (local precision-matching dump scripts; not part
  of the repo).
- Remove LANCE_PR.md; the PR description lives on GitHub.

Signed-off-by: lishunyang12 <lishunyang12@163.com>
 2026-05-21 20:07:40 +00:00
Yuanheng Zhao 2bc9cb7f13 [Feat] Support online quantization (fp8/int8) for LTX-2 (#3700) 
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
 2026-05-21 19:52:21 +08:00
Liang Lvhxhhhlalalahyh_hh
 		8297570c2b [AutoRound] Support WAN2.2 W4A16 quantization model (#3353) 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: hyh_hh <huyinghong1@huawei.com>
Co-authored-by: hxhhhlalala <hyh_hh@163.com>
Co-authored-by: hyh_hh <huyinghong1@huawei.com>
 2026-05-21 17:54:41 +08:00
hxhhhlalalaandhyh_hh 9dd36e3afd [NPU][Quant] Add W4A4 MXFP4 online & MXFP4 dual-scale online/offline quantization support for Wan2.2 T2V / I2V inference on Ascend NPU (#3578) 
Signed-off-by: hyh_hh <huyinghong1@huawei.com>
Co-authored-by: hyh_hh <huyinghong1@huawei.com>
 2026-05-20 06:21:29 +00:00
Y. Fisherandzzh 29179599fc [Feat] Enable VAE parallel in HunyuanImage3 (#3091) 
Signed-off-by: KexiongYu <yukexiong1@huawei.com>
Signed-off-by: zzh <943967662@qq.com>
Co-authored-by: zzh <943967662@qq.com>
 2026-05-20 09:55:33 +08:00
LuandSYLAR 14e5baceaf [Qwen-Image] Drop unused vision tower from text encoder (#3608) 
Signed-off-by: lulugoodcoder <luludachiever@gmail.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-05-19 19:19:58 +08:00
JiaHong ca9fd0b71c Reject non-positive Flux2 Klein inference steps (#3717) 
Signed-off-by: MmMaiIIi <2360655509@qq.com>
 2026-05-19 11:52:41 +08:00
JiaHongandWeiQing Chen 3ac739817f [Bugfix] Reject empty prompts in Flux2 Klein diffusion pipeline (#3711) 
Signed-off-by: MmMaiIIi <2360655509@qq.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
 2026-05-19 11:30:54 +08:00
Rustam Khadipash 89f8819525 [Feature] Add support for Pipeline Parallel and integrate it into Wan 2.2 (#2322) 
Signed-off-by: Rustam Khadipash <16683750+hadipash@users.noreply.github.com>
 2026-05-19 09:42:17 +08:00
lishunyang 69bcc6416d [New Model] Lance (ByteDance) — unified AR+diffusion multimodal (#3697) 
Adds Lance (bytedance-research/Lance), a 3B unified AR+diffusion
multimodal model on a Qwen2.5-VL backbone. Lance is BAGEL-lineage:
it reuses vLLM-Omni's BAGEL Mixture-of-Transformers core verbatim and
specializes only the ViT (Qwen2.5-VL vision), the VAE (Wan2.2) and the
checkpoint layout.

All six single-stage Lance modalities verified end-to-end on 1x B300:
t2i, t2v, image_edit, video_edit, x2t_image (image understanding) and
x2t_video (video understanding). 3-D mRoPE is wired through
BagelRotaryEmbedding for the x2t / video / edit paths. Includes the
upstream gap-analysis quality fixes (task-specific system prompts, full
Qwen chat template, upstream inference defaults and aspect-ratio
buckets).

Ships an offline example (examples/offline_inference/lance/), an
OpenAI-compatible online-serving example
(examples/online_serving/lance/) and an e2e test
(tests/e2e/online_serving/test_lance.py).

See LANCE_PR.md for the architecture rationale, per-modality status and
the two remaining follow-ups (two-stage AR+DiT, video_edit polish).

Closes #3697.

Signed-off-by: lishunyang <lishunyang03@gmail.com>
 2026-05-18 22:09:14 +00:00
lyj-jjjandCursor 821286794f [HY-Imgae3.0] support hunyuan image3 dit fa-fp8 on npu (#3540) 
Signed-off-by: lyj-jjj <liuyingjun5@huawei.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-18 09:35:30 -07:00
Ding Zuhaoandnussejzz f4115bd771 [Bugfix] Fix SenseNova U1 broken import after SupportsModuleOffload (#3691) 
Signed-off-by: nussejzz <nussejzz@users.noreply.github.com>
Co-authored-by: nussejzz <nussejzz@users.noreply.github.com>
 2026-05-18 21:12:46 +08:00
Yuanheng Zhao 220db62b3f [Bugfix] Adapt LTX-2 connector arg with diffusers 0.38.0 (#3661) 
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
 2026-05-17 21:58:44 +08:00
Yuanheng Zhao a64ebf103b [Refactor] Migrate and clean up TTS configs: CosyVoice3, OmniVoice, VoxCPM (#3338) 
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
 2026-05-17 07:32:34 +08:00
TaffyOfficialTaffyOfficialTaffyOfficialskf1999
 		3f63aaf982 [Feature] HunyuanImage-3.0 IT2I: multi-image input + prompt API cleanup (#3444) 
Signed-off-by: TaffyOfficial <2324465096@qq.com>
Signed-off-by: TaffyOfficial <wu15922848573@outlook.com>
Signed-off-by: skf1999 <13234016272@163.com>
Signed-off-by: zuiho <2324465096@qq.com>
Signed-off-by: Claude Code <noreply@anthropic.com>
Signed-off-by: zuiho <wu15922848573@outlook.com>
Signed-off-by: TaffyOfficial <2587297563@qq.com>
Co-authored-by: TaffyOfficial <2324465096@qq.com>
Co-authored-by: TaffyOfficial <wu15922848573@outlook.com>
Co-authored-by: skf1999 <13234016272@163.com>
 2026-05-14 16:58:40 +08:00
vraitiandClaude Opus 4.6 9de9d1f7b5 [Model] Add TP-aware MistralEncoder for FLUX.2-dev TP (#2465) 
Signed-off-by: vraiti <vraiti@redhat.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-13 12:33:55 -07:00
dengyunyang efd955674b [Bugfix][HunyuanImage3.0] Fix KV reuse compatibility in SP scenarios (#3546) 
Signed-off-by: dengyunyang <584797741@qq.com>
 2026-05-13 22:40:18 +08:00
Zeng Chuang 16a84b29d5 [Bugfix] Add bot_task option of think_recaption for hunyuanimage3 it2i (#3551) 
Signed-off-by: zengchuang <zengchuang3@huawei.com>
 2026-05-13 22:10:35 +08:00
hxhhhlalalaandhyh_hh a715abd447 [NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU (#3140) 
Signed-off-by: hyh_hh <huyinghong1@huawei.com>
Co-authored-by: hyh_hh <huyinghong1@huawei.com>
 2026-05-13 17:14:42 +08:00
lyj-jjjCursorgcanlin
 		56ca7dd612 support online FP8 quantization for FA on NPU #2236 (#2640) 
Signed-off-by: lyj-jjj <liuyingjun5@huawei.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
 2026-05-13 11:46:00 +08:00
dengyunyangandHongsheng Liu 0d91fbbbb7 [Bugfix] Align the AR and DiT prompt formatting across both online and offline modes. (#3516) 
Signed-off-by: dengyunyang <584797741@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-05-12 12:13:30 +08:00
Lancer 955fcff828 [Chore] explicit .float() conversion in Helios's optimized_scale function (#3529) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
 2026-05-12 02:08:28 +00:00
Y. Fisher a33e2eb588 [Config] Add HunyuanImage3 deploy configs (#3172) 
Signed-off-by: KexiongYu <yukexiong1@huawei.com>
Signed-off-by: Y. Fisher <yukexiong1@huawei.com>
 2026-05-11 22:49:19 +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
Canlin Guo 5e263b6929 [BugFix] Rename attention_config to diffusion_attention_config (#3489) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-05-11 11:27:35 +08:00
dengyunyang 857356d5b7 [Feature] hunyuanimage support flash attn (#2981) 
Signed-off-by: dengyunyang <584797741@qq.com>
 2026-05-10 22:08:24 +08:00
Canlin GuoandHongsheng Liu 11c4c7f0ff [Diffusion][Attention] Support per-role attention backend via CLI (#2681) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-05-10 11:59:05 +08:00
baonudesifeizhaiandroG0d c4a0990044 （Phase 1）Add ModelOpt FP8 auto-detect support for diffusion checkpoints #2709 (#2913) 
Signed-off-by: roG0d <rodgarcas98@gmail.com>
Signed-off-by: roG0d <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Co-authored-by: roG0d <rodgarcas98@gmail.com>
 2026-05-09 16:55:05 +08:00
Lancer de3a291710 [Bugfix] fix OmniGen2 offload and dtype mismatch (#2560) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
 2026-05-09 09:13:37 +08:00
Yueqian Lin c2a624bec4 [Bugfix][StableAudio] Pass model_class_name to Omni() and declare audio class attrs (#3405) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-05-09 06:40:43 +08:00
Nick CaoandClaude 65bc968465 [Refactor] Rename SupportsModuleOffload to SupportsComponentDiscovery (#3354) 
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-05-08 14:16:49 +00:00
Ayush AgarwalandHongsheng Liu b968373c88 enhancement: extend to dmd2 to image generation + add flux, qwen image pipelines (#2974) 
Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: Ayush Agarwal <ayushag@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-05-08 21:37:57 +08:00
zdobaanddaixinning c83cd45069 [Feat] Add Sequence Parallelism (USP) support for HunyuanVideo 1.5 transformer (#2444) 
Signed-off-by: daixinning <daixinning@163.com>
Co-authored-by: daixinning <daixinning@163.com>
 2026-05-08 21:20:03 +08:00
dengyunyang 5b61e7f1f1 [Feature][Hunyuan image 3.0] AR + DIT with kv reuse. (#3346) 
Signed-off-by: dengyunyang <584797741@qq.com>
 2026-05-08 20:51:46 +08:00
Alex BrooksandGao Han ce8a7dfd2d [Bugfix] Fix Dtype Crashes in SD3 (#2526) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-05-08 16:05:38 +08:00
lsyyyyyand汪志鹏 32663f21d5 [Feat] support hsdp for Bagel (#3150) 
Signed-off-by: siyuan.lei <siyuanlei37@gmail.com>
Signed-off-by: lsyyyyy <siyuanlei37@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-05-08 15:20:42 +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
Canlin Guo 4a24a517ab [BugFix] Probe __dict__ instead of hasattr when patching WanRMS_norm (#3400) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-05-07 11:54:16 +08:00
dengyunyang 3c85ca5536 [bugfix][hunyuaniamge] Fix parameter issue introduced during PR #3107 rebase (#3395) 
Signed-off-by: dengyunyang <584797741@qq.com>
 2026-05-07 02:03:21 +00:00
Yueqian Lin 687a44e5c8 [Bugfix][OmniVoice] Read voice-cloning fields from OmniTextPrompt in offline path (#3392) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-05-07 06:17:57 +08:00
Isotr0pyHongsheng LiuSYLAR
 		0a8204cb81 [Quantization] Redo Z-Image text encoder FP8 online quantization (#3279) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-05-06 16:37:36 +00:00
skfTaffyOfficialdengyunyangJohn Liu BUAA
 		576afb6f53 [Feature] HunyuanImage-3.0 IT2I (image editing) support (#3107) 
Signed-off-by: TaffyOfficial <2324465096@qq.com>
Signed-off-by: zuiho <2324465096@qq.com>
Signed-off-by: skf1999 <13234016272@163.com>
Co-authored-by: TaffyOfficial <2324465096@qq.com>
Co-authored-by: dengyunyang <584797741@qq.com>
Co-authored-by: John Liu BUAA <liukecheng97@gmail.com>
 2026-05-06 22:37:39 +08:00
dengyunyang 369a47d5a1 [Hunyuanimage-3.0] Accuracy fix (#3373) 
Signed-off-by: dengyunyang <584797741@qq.com>
 2026-05-06 07:31:11 +00:00
fywc 9f81a0a4b0 [Feat] support HSDP for DreamID-Omni (#3138) 
Signed-off-by: hanzheli <hanzheli@kuaishou.com>
Signed-off-by: fywc <hanzheli@kuaishou.com>
 2026-05-06 13:09:39 +08:00
Chendi.XueandHongsheng Liu 4e41b7bc23 Enable Wan2.2-S2V modeling to vLLM-omni (#2751) 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-05-06 08:03:48 +08:00
Ting FUasukaqaq-sjaderHongsheng LiuGao Han
 		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
TaffyOfficialTaffyOfficialzuiho-kai
 		44cde33eb5 [Bugfix][HunyuanImage3] Fix offline AR garbage output by switching to Instruct chat template (#3243) 
Signed-off-by: zuiho <wu15922848573@outlook.com>
Signed-off-by: TaffyOfficial <2324465096@qq.com>
Signed-off-by: zuiho-kai <31877877+zuiho-kai@users.noreply.github.com>
Signed-off-by: zuiho <2324465096@qq.com>
Co-authored-by: TaffyOfficial <2324465096@qq.com>
Co-authored-by: zuiho-kai <31877877+zuiho-kai@users.noreply.github.com>
 2026-05-06 00:31:02 +08:00
Juan Pablo ZuluagaandJuanPZuluaga b64ab05d09 [TTS][SpeakerCacheManager] A global speaker cache manager for Voice Cloning (#2630) 
Signed-off-by: JuanPZuluaga <juanz9312@gmal.com>
Co-authored-by: JuanPZuluaga <juanz9312@gmal.com>
 2026-05-05 10:53:45 -04:00