Commit Graph
1042 Commits
Author SHA1 Message Date
Yukim1 633ebbd8a4 [Refactor] Migrate Step-Audio2 online test to deploy config (#5309)
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
2026-07-22 09:44:27 +00:00
wangyu 8fc9df4331 [CI][Bugfix] remove module-level skip_if_gated_repo_inaccessible in flux kontext e2e (#5250) (#5297)
Signed-off-by: wangyu <410167048@qq.com>
2026-07-22 17:29:59 +08:00
Zeyu Huang | 黃澤宇andHongsheng Liu 9479720f81 [Refactor]: clean up diffusion model runner surface (#5218)
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-22 17:07:36 +08:00
f43d761c26 [Refactor]: clean up diffusion worker interfaces (#5217)
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-22 17:07:09 +08:00
Mu GuanLin 39e83e27f0 [Bug][CI] Pin the LTX FP8 quality gate to its established sigma schedule (#5302)
Signed-off-by: mglyn <1203789601@qq.com>
2026-07-22 14:36:32 +08:00
Yifan TianandDidan Deng 24eb4ab89c [Model] Add Cache-DiT support for FLUX.1-Kontext-dev (#4205)
Signed-off-by: yifan <Yifan.Tian@colorado.edu>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
2026-07-22 14:06:12 +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
Yuekai ZhangandClaude Fable 5 e2115fb642 [Bugfix][CI] Relax higgs_audio_v2 PCM streaming HNR threshold (fixes #5045) (#5232)
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:26:00 +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
Zeyu Huang | 黃澤宇 2cf5f57b3e [Refactor]: clean up diffusion executor lifecycle (#5215)
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
2026-07-22 09:30:59 +08:00
ea34bde619 [Bugfix] MiniCPMo-4.5 bugfix (#5233)
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Co-authored-by: Guanzhe (Leo) Huang <116847811+leohuang257@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-07-22 09:23:03 +08:00
JaeandCursor ee33954dff [Model] Support Boogu/Boogu-Image-0.1-Base and Boogu/Boogu-Image-0.1-Edit (#4995)
Signed-off-by: zzehli <jaeli_ottawa@outlook.com>
Signed-off-by: jl <jaeli_ottawa@outlook.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-21 18:58:56 +00:00
akshatvishu d34b91722f [BugFix][Diffusion] Preserve image payloads with reasoning metadata (#5238)
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
2026-07-22 00:49:18 +08:00
wangyu 7b5b399210 [CI] skip test_audio_in_video_default_loader_sampling_regression (#5248) (#5280)
Signed-off-by: wangyu <410167048@qq.com>
2026-07-21 21:47:55 +08:00
Alicia 0034eaa9c3 Update perf baseline base on 7/5-7/11 7 days avg. (#5231)
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
2026-07-21 12:26:22 +00:00
wtz2333andhsliuustc0106 5a6a93dc5f [diffusion][model] Add LingBot Video dense and MoE support (#5035)
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>
Signed-off-by: wtz2333 <2955110911@qq.com>
Co-authored-by: hsliuustc0106 <liuhongsheng4@huawei.com>
2026-07-21 17:27:29 +08:00
bastefaniak 2f33df4678 [bugfix] Cosmos3 edge fix config use_k_norm_und_for_gen name (#5239)
Signed-off-by: Bartosz Stefaniak <bstefaniak@nvidia.com>
2026-07-21 07:56:31 +00:00
Hongshaorouandamy-why-3459 0576264dd1 [Bugfix] Fix MiniCPM-o 4.5 audio placeholder pool step (#5116)
Signed-off-by: a-kaa <siruhe666@gmail.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-07-21 15:44:05 +08:00
fatSheepandamy-why-3459 5d44868e91 [Hardware][Ascend] Keep HiFT vocoder on NPU (#5242)
Signed-off-by: fatSheep <tzh2005t@163.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-07-21 14:30:30 +08:00
Juan Pablo ZuluagaandYueqian Lin dacb8e6f10 [Bugfix][Perf] mimo_audio: fix per-request speech-code routing under continuous batching (#5070)
Signed-off-by: JuanPZuluaga <juanz9312@gmail.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
2026-07-20 17:22:45 +00:00
leo e24bddfb22 Fix Qwen3-Omni thinker fused MoE LoRA (#5191)
Signed-off-by: leo <yaoliu548926@gmail.com>
2026-07-20 08:52:21 -07:00
zhumingjue138 4d799997d3 [Bugfix] Fix issue 5205, add trust-remote-code (#5213)
Signed-off-by: zhumingjue <zhumingjue@huawei.com>
2026-07-20 15:20:53 +00:00
Yukim1 7d75095b84 [BugFix] Fix SoulX-Singer deploy pipeline registration (#5210)
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
2026-07-20 14:34:42 +00:00
Mu GuanLin a06664a243 [Refactor] Unify the LTX-2 and LTX-2.3 pipeline runtime (#5147)
Signed-off-by: mglyn <1203789601@qq.com>
2026-07-20 20:02:30 +08:00
Diya Penganddiyapeng 6cd1ff7e64 [Quantization] Add FLUX.2-dev Mistral TE online FP8 support (#5136)
Signed-off-by: diyapeng <50388704+diyapeng@users.noreply.github.com>
Co-authored-by: diyapeng <50388704+diyapeng@users.noreply.github.com>
2026-07-20 16:16:31 +08:00
Shenglei Fu 7b2edd6650 [Bugfix][Qwen3-TTS] Mode-aware ref_audio artifact readiness (fixes #5049) (#5157) 2026-07-20 00:38:07 -07:00
boatmanandYueqian Lin 32dddfcef4 [Cleanup]Migrate model validation to adapters and clean up serving_speech.py (#4833)
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
2026-07-19 23:03:32 -07:00
Wei 10d3a25916 [Feature] Support per-video audio masks for Qwen Omni (#4656)
Signed-off-by: hbhflw2000 <417911774@qq.com>
2026-07-20 11:39:59 +08:00
Lancer eef3bd5c4a [Feat] support CFG Parallel for FLUX kontext (#2281)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
2026-07-20 10:05:05 +08:00
Wang fuyin ffd4e1f97e [Bugfix] Fix stale pipeline resolver test call (#5193)
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
2026-07-18 23:38:35 -06:00
4fbbdfd250 [Refactor] Migrate Legacy Stage Configs to the Pipeline Registry (#5031)
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-18 09:34:33 +00:00
Yukim1andHongsheng Liu 793d3e9ab7 [Config] Return VllmOmniConfig from create_from_model (#4818)
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-18 09:21:07 +00:00
wangyu 907f932b72 [CI][Test] Tier diffusion offloader CI and reduce gpu_4_queue merge usage and fix #5182 (#5185)
Signed-off-by: wangyu <410167048@qq.com>
2026-07-18 17:15:17 +08:00
Nick Cao 1f0ed96fcd [Bugfix] Fix broken FrameSimilarityFilter threshold test (#4786)
Signed-off-by: Nick Cao <ncao@redhat.com>
2026-07-18 13:52:07 +08:00
Weiming Liaoandwangyu 7aa5c9a090 [CI][NPU]: Add nightly performance test for NPU - Qwen3-TTS on A3 (#5158)
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>
2026-07-17 17:32:48 +08:00
Alex Steiner ae949d129f [Bugfix][Quantization] Remap ModelOpt NVFP4 scale tensors (#5087)
Signed-off-by: Alex Steiner <asteiner@nvidia.com>
2026-07-16 12:33:57 -07:00
bastefaniak 85f7a5b374 Add Cosmos3 Edge and Distilled checkpoints support (#5001)
Signed-off-by: Bartosz Stefaniak <bstefaniak@nvidia.com>
2026-07-16 09:39:40 -07:00
zzh 0a9a5c231e Fix hunyuan ci (#5143)
Signed-off-by: zzh <943967662@qq.com>
2026-07-16 14:49:13 +00:00
wangyu 2a49b2b217 [CI][Perf] Add JSON mark support and paired parametrize for L4 perf, so as to further support performance‑case selection for NPU‑CI. (#5084)
Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
2026-07-16 14:45:00 +00:00
Ricardo Noriega 68a992060b [Bugfix] Fix audio.format parameter silently ignored in chat completions (#4718)
Signed-off-by: Ricardo Noriega De Soto <rnoriega@redhat.com>
2026-07-16 00:17:02 -06:00
zhumingjue138 238fc0a609 [Bugfix] fix issue 5065 (#5118) 2026-07-15 19:39:44 -07:00
Shi Boao Bowieandbjf-frz a432b8a325 [Refactor][OutputProcessor 1/8]: clean up multimodal payload accumulation and move payload logic into MultimodalPayload & directory refactor (#4980)
Signed-off-by: Boao Shi <aoibosh@connect.hku.hk>
Signed-off-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: bjf-frz <frz123db@gmail.com>
2026-07-15 15:50:19 +08:00
wangyu 795e4e0160 [CI] Add local job runner scripts for L2-L4 pytest execution (#4672)
Signed-off-by: wangyu <410167048@qq.com>
2026-07-15 14:18:58 +08:00
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
zyz111222andamy-why-3459 2d58070f60 [Hardware][Ascend][Model] Optimize Qwen3-TTS on 310P (#4841)
Signed-off-by: zouyizhou <zouyizhou@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-07-15 08:57:44 +08:00
wkutak a7b6a174bc Fix loading of ModelOpt FP8 checkpoints for Cosmos3 (#5076)
Signed-off-by: Wojciech Kutak <wkutak@nvidia.com>
2026-07-14 17:33:27 -07:00
bjf-frz b14ff23041 [PERF][CI]Add Cosmos3 diffusion perf config (#5010)
Signed-off-by: bjf-frz <frz123db@gmail.com>
2026-07-14 10:25:17 +00:00
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
Alex Steiner 4b9d09cb87 [Bugfix][Quantization] Support packed parameters with HSDP (#5088)
Signed-off-by: Alex Steiner <asteiner@nvidia.com>
2026-07-14 08:24:26 +00:00
wjsuijlenh 3589a676e2 [Bugfix] Accept kv_prefetch_jobs in ARDiffusionModelRunner.execute_model (#4941)
Signed-off-by: Wijnand Suijlen <wijnand.suijlen@huawei.com>
2026-07-14 08:22:40 +00:00