Commit Graph
997 Commits
Author SHA1 Message Date
Canlin Guo 7bcd43f456 [Docs][skip ci] Fix omni and tts docs (#2130)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
2026-03-24 22:39:23 +08:00
Nick Cao 47ba887b93 [Feat] Support scalar types in AdditionalInformationEntry (#2105)
Signed-off-by: Nick Cao <ncao@redhat.com>
2026-03-24 10:29:38 -04:00
Didan Deng c7c1c3b04a [Fix CI] Reduce num gpus to prevent ci failure (#2131)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-03-24 11:25:57 +00:00
SYLAR 6b93459826 [Core] Unified quantization framework (#1764) 2026-03-24 18:56:55 +08:00
Alicia 2a630313ce [CI] Trigger nightly diffusion benchmark collects and html generates. (#1995)
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
2026-03-24 17:58:24 +08:00
Baoyuan Qi 8619321b90 [Enhancement] Custom chunk_size for mimo-audio model (#1964)
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
2026-03-24 02:14:50 -07:00
Alicia f8777d85bc [CI] Add conditions for L3 (tests after merging) and L4 (tests for nightly). (#1514)
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
2026-03-24 16:58:22 +08:00
Didan Deng c39225724d [Perf] Qwen-Image Nightly Performance CI Improvement (#2111)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-03-24 16:52:48 +08:00
5c14757ef0 [CI] [RL]: Add e2e test for custom pipeline (#2005)
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
2026-03-24 15:49:11 +08:00
Canlin Guo fb9f20a921 [API] Add layers and resolution parameters to /v1/images/edits endpoint (#2053)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
2026-03-24 15:47:41 +08:00
Canlin GuoSamitlishunyang lishunyang12@163.com
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
John Liu BUAA 93f1878229 [Test] L4 complete diffusion feature test for Qwen-Image-Layered models (#2085)
Signed-off-by: John Liu BUAA <liukecheng97@gmail.com>
2026-03-24 15:20:35 +08:00
dongbo910220andDidan Deng 50bd1961bf [Feature]: add Ulysses advanced_uaa mode (#1379)
Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: dongbo910220 <32610838+dongbo910220@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-03-24 14:55:54 +08:00
Lancerandgcanlin 4cfa9bf843 [Bugfix] fix offload and hsdp incompatibility (#1888)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
2026-03-24 14:50:57 +08:00
SamitandDidan Deng 9ead0d890d [Enhancement] Add force_refresh support for GLM-Image for cache-dit 1.3.0 upgrade (#1858)
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-03-24 14:32:18 +08:00
Alicia b2b061a9b3 [skip ci] Keep the latest version. (#2112)
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
2026-03-24 14:26:20 +08:00
rein yang 3cdf28828e [Feature] support to change the speaker of qwen3-omni (#1963)
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
2026-03-24 13:53:24 +08:00
Egor Chernobrovkin d16be833e1 [Bugfix] Support base64 input for --ref-audio in Qwen3-TTS client (#1389)
Signed-off-by: Egor Chernobrovkin <33jasooon33@gmail.com>
2026-03-23 22:36:36 -07:00
rongfu.leng b239bf0b7d [Feature] Add a extra body param in create video api (#1955)
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
2026-03-24 13:02:35 +08:00
akshatvishu ad5e4e5710 [feature] stable_audio_open_1 teacache support (#1314)
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
2026-03-24 01:00:45 -04:00
Chendi.Xue d71c9ae60f [BugFIX] enable Hunyuan image3 with stage selection among text_to_image/image_to_text (#1826)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
2026-03-24 13:00:21 +08:00
Yueqian Lin 4ac25287fd Add tool to configure gpu_memory_utilization for multi-stage pipelines (#1958)
Signed-off-by: linyueqian <linyueqian@outlook.com>
2026-03-24 12:55:26 +08:00
Yueqian Lin 8b102bdac1 [Feat][Qwen3-TTS] Better Qwen3-TTS online serving demo (#1857)
Signed-off-by: linyueqian <linyueqian@outlook.com>
2026-03-24 12:06:41 +08:00
LancerandDidan Deng c6b7597126 [Feat] support TP for GLM-Image (#1918)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-03-24 11:44:47 +08:00
Alicia b0efb6ede0 [Doc] Sync and fix. (#2110)
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
2026-03-24 03:20:50 +00:00
9bf8f8ce79 [model] support FLUX.1-Kontext-dev (#561)
Signed-off-by: Lancer <maruxiiang6688@gmail.com>
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Lancer <maruxiiang6688@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
2026-03-23 17:17:58 +00:00
Juan Pablo Zuluaga ec6ee1e336 [Bugfix][Chunk Transfer Adapter] deque mutated fix (#2102)
Signed-off-by: JuanPZuluaga <juanz9312@gmail.com>
2026-03-23 13:09:04 -04:00
Didan Deng 5aef6b9c71 [Bugfix] Fix Qwen-Image SP and TeaCache incompatibility (#2101)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-03-24 00:23:27 +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
Peiqi Yin df93b3a965 [Unit Test] add unit tests for AsyncOmni and Omni (#2034)
Signed-off-by: yinpe <11810305@mail.sustech.edu.cn>
2026-03-23 23:17:12 +08:00
Megha AgarwalandZhou Taichang 9eeac248f2 [Feat] Phase 1 foundation types for multimodal output decoupling (#1816)
Signed-off-by: Megha Agarwal <agarwalmegha1308@gmail.com>
Signed-off-by: Megha Agarwal <agarwalmegha@microsoft.com>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
2026-03-23 22:33:01 +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
WeiQing Chen d6b55b9196 [Quantization] feat: add qwen-image gguf adapter (#1755)
Signed-off-by: David Chen <530634352@qq.com>
2026-03-23 13:24:54 +00:00
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
wangyu 5a58a1aac0 [CI] Update Diffusion Model Test Configuration for Nightly Builds (#2086)
Signed-off-by: yenuo26 <410167048@qq.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
2026-03-23 19:29:44 +08:00
zhumingjue138 c14ab819e3 [Test] L5 Long-Term Stability Test and GPU Memory Monitoring Main L5 last (#1799) 2026-03-23 19:04:05 +08:00
knlnguyen1802 65d76a4127 [Feature][RL] Support batching for QwenImage in async mode (#1593)
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
2026-03-23 10:08:24 +00:00
Y. Fisher 560023d5d1 [Bugfix] Fix NPU Hunyuan fused MoE forward context after rebase to 0.18.0 (#2091)
Signed-off-by: KexiongYu <yukexiong1@huawei.com>
2026-03-23 09:22:06 +00:00
Zeyu Huang | 黃澤宇 8a58394379 [Docs][CI] doc update & L4 example test for text-to-image page (#1910)
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
2026-03-23 16:26:54 +08:00
WeiQing Chen 602f831068 [Bugfix] fix gguf TypeError: GGUFConfig.get_name() missing 1 required positional argument: 'self', test: add diffusion gguf unit coverage (#1865)
Signed-off-by: David Chen <530634352@qq.com>
2026-03-23 14:56:15 +08:00
zhou zhuoxinand汪志鹏 b147553d67 [Feature] add Tensor Parallelism to Omnigen2 (#2065)
Signed-off-by: zhou zhuoxin <zhouzhuoxin1508@outlook.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-03-23 11:46:58 +08:00
Lancer 0833470d41 [Feat] support TeaCache for Flux2 klein (#1234)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
2026-03-23 10:19:25 +08:00
Yupu cb6d012d91 [BugFix]: Fix OmniGen2 Model Loading (#1711)
Signed-off-by: Yupu <feng.yu.pu0330@gmail.com>
2026-03-22 23:13:13 +08:00
Salman Chishti f1ed949fcf Upgrade GitHub Actions for Node 24 compatibility (#2070)
Signed-off-by: Salman Muin Kayser Chishti <13schishti@gmail.com>
2026-03-22 22:49:48 +08:00
Alex Brooks a8f1394699 [Core] Simplify OmniModelConfig Initialization (#1768)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
2026-03-22 18:27:28 +08:00
LancerandHongsheng Liu d8b35035ec [Bugfix] Fix cache-dit for single-transformer Wan2.2 models(eg. Wan2.2-TI2V-5B) (#1392)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-03-22 17:57:28 +08:00
zJandSamit af9368d109 [Fix] Fix non-unique request IDs in /v1/images/edits endpoint (#2050)
Signed-off-by: zJ_ <19760191+zJuuu@users.noreply.github.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
2026-03-22 09:13:01 +00:00
Du Bin b4a96b0db4 [Bugfix] Restore chunk-waiting requests on OmniNewRequestData rewrap failure (#1691)
Signed-off-by: dubin555 <dubin555@gmail.com>
Signed-off-by: OSS Scout <scout@oss-scout.local>
2026-03-22 14:32:51 +08:00
Alex Brooks a5574a2fb0 [CI] Add Flux2 Klein Tests (#2027)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
2026-03-22 13:05:18 +08:00
Chendi.Xue 28aee51a59 [FP8] enable hunyuan-image-3 diffusion model with fp8 online quant (#1935)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
2026-03-22 13:02:16 +08:00