82 Commits
Author SHA1 Message Date
汪志鹏 5ca23106fd [Model] Add SheetSage2 preprocessing and YuE2 score handoff (#8371)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-10-05 11:09:37 +08:00
汪志鹏 b742f86136 [CI/Build] Restore streaming executor fixture contract (#8418)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-10-02 01:45:56 -07:00
汪志鹏 a038b38179 [Model] Add MiniMax-H3 latent super-resolution and hi-res refinement (#8322)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-10-01 14:24:40 +08:00
汪志鹏 f8a00b1491 [Misc] Add portable MiniMax H3 skills (#7923)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-09-22 11:10:42 +08:00
汪志鹏 139a47a578 [Model] Add MiniMax-H3 long-video latent continuation with driving audio (#7838)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-09-20 23:44:33 +08:00
汪志鹏 8e10c3ee07 [Bugfix] Avoid multimodal cache collisions in multistage image editing (#7817)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-09-20 11:27:06 +08:00
汪志鹏andClaude Opus 5 e8f45fcd89 [Frontend] Add ComfyUI FastH3 node, fix t2va aspect ratio and dropped audio (#7456)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-14 11:22:05 +08:00
汪志鹏 9b6a308914 [Perf][Diffusion] Keep LoRA weights resident across activation cycles (#7195)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-09-07 14:27:24 +00:00
汪志鹏 eeee257913 [Bugfix][Diffusion] Restore the TRTLLM attention default for the MiniMax-H3 modular alias (#7162)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-09-07 07:21:21 +08:00
汪志鹏andClaude Opus 5 af74a5a155 [Feature][MiniMax-H3] Support the full LightX2V Turbo LoRA matrix (#7062)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-06 20:23:36 +08:00
汪志鹏andClaude Opus 5 ae70479619 [Bugfix] Drop the removed diffusion_batch_size kwarg from the stage-init test (#7101)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-05 17:05:33 +00:00
汪志鹏 c59b48b47e [Feature][MiniMax-H3] Complete VSA and Ulysses support (#6909)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-09-02 07:19:21 -04:00
汪志鹏andHongsheng Liu 86b85c078b [Feature][MiniMax-H3] Fuse the FastH3 four-step adapter at load time (#6714)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-31 12:04:58 +08:00
d150a4fde7 [Feature][MiniMax-H3] Support diffusion continuous batching (#5810)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-24 21:08:53 +08:00
汪志鹏 dc72559d5d [BugFix]: CosyVoice3 STFT window device mismatch (#6454)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-08-21 19:45:46 +08:00
汪志鹏 fc163cd90f [Skills] Add vLLM-Omni simplification review skill (#6363)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-08-21 15:31:42 +08:00
汪志鹏 e9bc7fc06a [Refactor]: Mammothmoda2-dev use x_to_text.py in examples (#5454)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-27 14:11:49 +00:00
汪志鹏 88b7ca2ffa [Model] Support MammothModa2-Dev (#5411)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-27 17:01:54 +08:00
汪志鹏 ddc3c87547 [Refactor][Docs]: Remove stale BAGEL offline guide (#5429)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-27 09:46:11 +08:00
汪志鹏 ccdb2b51aa [Refactor]: Intrduce x_to_text.py in examples (#5384)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-07-26 16:33:17 +08:00
汪志鹏 a61d5c0fd8 [Refector] Remove mammothmodal2-preview example (#5335)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-07-24 07:29:55 +08:00
汪志鹏 f44649ffd0 [Refactor]: Remove sensenova examples (#5201)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-22 15:36:00 +00:00
汪志鹏 fb4dd41d79 [Refactor]: Remove unnecessary config getattr (#5199)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-22 03:48:05 -07:00
汪志鹏 14fad9835d [BugFix]: fix #3236 bug (#4877)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-05 17:26:09 +00:00
汪志鹏 862e0a2b27 [BugFix] Preserve diffusion extra_body params for out-of-process CFG Parallel (#4900)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-07-05 17:06:30 +00:00
汪志鹏 a10eac0f8c [Feature]: Migrate magi human example (#4572)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-06-22 15:17:00 +08:00
汪志鹏 950e66a44c [Feature]Migrate helios example (#4569)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-06-21 07:37:16 +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
汪志鹏 f195e44bc1 [BugFix]: Fix Bagel generate_image denoising schedule (#4509) 2026-06-18 02:02:38 +00:00
46e0b71423 [Enhancement] Introduce High-Performance MoT (Mixture-of-Tokens) Kernels: Triton Implementation (#3960)
Signed-off-by: Yufeng Zhu <yzhu802@gatech.edu>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Co-authored-by: Yufeng Zhu <yzhu802@gatech.edu>
Co-authored-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-16 03:08:02 +00:00
汪志鹏 c7178d89bb [Bugfix] UnspecifiedOmniPlatform.get_device_count returns 0 instead o… (#3636)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-05-15 05:28:40 +00:00
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
汪志鹏andHongsheng Liu e50a066548 [BugFix]: Fix async scheduer transfer exceed KV cache (#3318)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-05-03 20:02:22 +08:00
汪志鹏 2cd64cdccb [CI]Change pixels tolerance from 5 to 10 (#3289)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-05-01 15:06:37 +12:00
汪志鹏 77e1e5c01c [BugFix][Bagel]: Fix vLLM-Omni as rollout bug: number of trajectory_latents count less (#3258)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-05-01 00:15:16 +08:00
汪志鹏andSYLAR 37e5954acf [Config Refactor]: Remove bagel yaml (#2936)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
2026-04-24 21:21:30 +08:00
汪志鹏 e1cdd0c23b [BugFix][CI]: Fix test_omni_sleep_mode ci bug (#3010)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-04-22 12:36:20 +08:00
汪志鹏andHongsheng Liu 768931e6a4 [BugFix]: Fix multi-stage cfg bug (#2801)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-04-18 09:43:22 +00:00
汪志鹏 2c67c30550 [Bagel]: Support think mode in single stage deployment of Bagel (#2650)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-04-13 11:15:49 +00:00
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
汪志鹏 408365fa0d [Bagel]Fused gate_proj and up_proj (#2546)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-04-07 10:02:51 +00:00
汪志鹏 340cba7b04 [daVinci-MagiHuman][Doc][BugFix] Update model support for daVici-MagiHuman and fix media utils bug (#2542)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-04-07 17:16:12 +08:00
汪志鹏 8dd66ceb00 [BugFix] Continue decode if don't need transfer kv cache between two … (#2502)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-04-07 13:30:01 +12:00
汪志鹏 5b2c4f909d [BugFix] Add bagel text2text/img2text think mode support (#2503)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-04-07 13:29:26 +12:00
汪志鹏andDidan Deng 0059ec878c [Model Support]: Magihuman support (#2301)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-04-04 09:29:09 +00:00
汪志鹏 fa275fd1be [BAGEL] [Feature]: Add thinking mode in Bagel multi-stage serving (#2447) 2026-04-03 11:47:57 +08:00
汪志鹏 bf5bd0a4c0 [BugFix]: Fix bagel single-stage img2img fallback to text2img bug (#2397)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-04-01 02:29:02 -07:00
汪志鹏 369f301a1b [BugFix] Add BAGEL single-stage diffusion config and fix multiple <im_start><im_end> bug (#2381)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-04-01 09:19:13 +08:00
汪志鹏andDidan Deng 77d773ad47 [Bagel]: Support SP (#1903)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-03-23 21:52:50 +08:00
汪志鹏 1bd1d9d618 Remove mm_prefix_lm patch because vllm==0.18.0 already support (#2062)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-03-21 22:32:00 +08:00
汪志鹏 c2a5420d97 [CI] Change Bagel online test environment variable VLLM_TEST_CLEAN_GPU_MEMORY to 0 (#2032)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-03-20 12:13:21 +08:00
汪志鹏 81793f1918 [CI] Split BAGEL tests into dummy/real weight tiers (L2/L3) (#1998)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-03-19 15:32:48 +08:00
汪志鹏 61e170c69a [Feature]: Remove some useless hf_overrides in yaml (#1898)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-03-18 19:46:44 +08:00
汪志鹏 284575ab82 [CI]: Add/Fix bagel e2e online/offline test (#1895)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-03-15 18:27:07 +08:00
汪志鹏 e0b71056ba [BugFix]: Fix bagel online inference bug (#1804)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-03-13 08:58:44 +00:00
汪志鹏 a52867abde [BugFix]: Revert #1582 (#1842)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-03-12 19:19:57 +08:00
汪志鹏 11d9ca8f41 [Feature]: Enable directly use OmniLLM init AR model (#1821) 2026-03-12 04:24:10 +00:00
汪志鹏 7271116973 [Bagel]: Support multistage img2img (#1669)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-03-09 22:23:50 +08:00
汪志鹏andgcanlin f9ec07f0e2 [Model]: Helios support (#1604)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
2026-03-04 14:17:15 +08:00
汪志鹏andCursor e37a89ffcb [Feature]: Support cfg kv-cache transfer in multi-stage (#1422)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-03-02 05:06:28 +00:00
汪志鹏 3d9fa8d53f [BugFix]: fix a lot of bug (#1565)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-02-28 16:26:56 +08:00
汪志鹏 82e1bf2804 [Doc]: Add bagel single/multi node usage with mooncake document (#1450) 2026-02-24 15:54:57 +00:00
汪志鹏 630e84ef93 [BugFix]: Revert utils change (#1369)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-02-13 17:54:09 +08:00
汪志鹏 8228b5a8fe [Bagel]: Support TP (#1293)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-02-11 00:17:44 +13:00
汪志鹏andHongsheng Liu de0a8b057b [CI]: Bagel E2E Smoked Test (#1074)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-01-31 22:08:22 +13:00
汪志鹏andHongsheng Liu 0f0e94760c [TeaCache]: Add Coefficient Estimation (#940)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-01-31 22:06:17 +13:00
汪志鹏 741f7e2826 [Core]: KV Cache Transfer Encapsulation (#979)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-01-28 23:12:45 +08:00
汪志鹏 06c9d9b463 [Bagel] Support TeaCache (#848)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-01-25 14:52:27 +08:00
汪志鹏andwzliu 7f821be57b Support Bagel Model (#726)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: wzliu <wzliu@connect.hku.hk>
2026-01-22 23:09:55 +13:00
汪志鹏 36c28767cd [Core]Add GPU Diffusion Runner (#822)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-01-17 19:49:13 +08:00
汪志鹏 0888520875 [Bagel] Support Cache-Dit (#736)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-01-17 15:21:49 +08:00
汪志鹏 0ec2da08de [BugFix] Fix assuming all stage model have talker (#730)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-01-11 01:36:37 +13:00
汪志鹏 e7eeb54e08 [BugFix]Fix text_to_image bagel command error (#644)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-01-05 23:22:15 +13:00
汪志鹏 d430beef76 [Bagel]Add image edit (#588)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-01-05 12:18:04 +08:00
23bf317cc5 [New Model]Bagel model(Diffusion Only) (#319)
Signed-off-by: wzliu <wzliu@connect.hku.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: wzliu <wzliu@connect.hku.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2025-12-31 13:47:35 +08:00
汪志鹏 a97f979ec4 [CI]Wheel package compilation (#288)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2025-12-18 17:14:18 +08:00
汪志鹏 6c333161a4 [BugFix]Remove duplicate code (#309)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2025-12-15 01:42:55 +00:00
汪志鹏 71f9f9a9a7 [Bugfix] Remove debug code in AsyncOmni.del to fix resource leak (#260)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2025-12-09 23:23:01 +08:00
汪志鹏 08fb978c46 [Docs]Fix doc wrong link (#223)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2025-12-06 22:41:03 +13:00
汪志鹏 f3c69df419 [FixBug]online serving fails for high-resolution videos (#198)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
2025-12-05 02:29:01 +00:00
汪志鹏 522ce30a85 [Doc]Fixed some spelling errors (#199)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2025-12-04 08:43:28 -08:00
汪志鹏andZhipeng Wang 598d26580e [Doc] change vllm_omni to vllm-omni (#177)
Signed-off-by: Zhipeng Wang <zhipeng.wang@rakuten.com>
Co-authored-by: Zhipeng Wang <zhipeng.wang@rakuten.com>
2025-12-03 17:43:59 +08:00