Commit Graph
578 Commits
Author SHA1 Message Date
bjf-frz 2447740308 [Perf]perf: skip unused Cosmos3 I2V conditioning latents (#4614)
Signed-off-by: bjf-frz <frz123db@gmail.com>
2026-06-22 09:51:47 +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
WeiQing ChenandHongsheng Liu f0d7fe18f2 [Perf][Cosmos3] Optimize I2V conditioning transfer (8.63% faster x-inference) (#4467)
Signed-off-by: david6666666 <530634352@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-22 01:59:03 +00:00
Alex Brooksand汪志鹏 7ff11d8d0f [Perf/Fix] Reimplement Batched CFG Forward for Bagel (#4098)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-06-22 07:37:21 +08:00
MaciejBalaNVandHongsheng Liu fc32d9fe6f Improve Cosmos3 v2v quality (#4514)
Signed-off-by: Maciej Bala <mbala@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-21 22:20:30 +08:00
Shin 1292c47804 [BugFix]Fix diffusion profile RPC None results (#4372)
Signed-off-by: yixiaoer <shin@yixiaoer.sg>
2026-06-21 17:14:21 +08:00
MaciejBalaNV a1e1ac0155 Cosmos3 transfer (#4379)
Signed-off-by: Maciej Bala <mbala@nvidia.com>
Signed-off-by: MaciejBalaNV <mbala@nvidia.com>
2026-06-21 09:59:18 +08:00
Zhengyuan Su (苏政渊)andClaude Opus 4.8 2d0b1d8a29 [Diffusion] add GR00T-N1.7 pipeline with OpenPI serving (#3798)
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 11:45:26 +08:00
TJian e70822ed54 [ROCm] [CI] Fix diffusion test (#4574)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2026-06-20 08:31:39 +08:00
Alex Brooks 6ff246bf3c [Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
2026-06-20 08:30:44 +08:00
Kwokho TsuiandKwokho Tsui 7e152ca64b [Bugfix] Fix HSDP + FP8 online quantization compatibility (#4494)
Signed-off-by: Kwokho Tsui <kh_tsui@163.com>
Co-authored-by: Kwokho Tsui <kh_tsui@163.com>
2026-06-19 15:06:27 +08:00
amy-why-3459 f05e03aea8 [Perf][DreamZero]dreamzero supports CUDA graph, torch.compile, and DiT Caching. (#4213)
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-06-19 14:24:37 +08:00
yangyonggit 37a442447e [Cleanup] Remove duplicate HiDreamI1ImagePipeline (fixes #4009) (#4045)
Signed-off-by: leo.yang <leo.yang.engineer@gmail.com>
2026-06-19 06:32:18 +08:00
Honghan Zhu 8f28b969e9 [Feat] DreamZero fix tp & cross attn cache (#4154) 2026-06-18 10:57:04 +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
bjf-frz 14d70d9870 [Perf]Enable regional compile for Cosmos3 HSDP blocks (#4485)
Signed-off-by: bjf-frz <frz123db@gmail.com>
2026-06-18 16:54:05 +08:00
汪志鹏 f195e44bc1 [BugFix]: Fix Bagel generate_image denoising schedule (#4509) 2026-06-18 02:02:38 +00:00
Nick CaoandClaude e957d16f8d [Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076)
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-06-17 21:33:06 +08:00
KristofferandHongsheng Liu 890803ca06 [Wan2.2] Fix "uninitialized nn.Module of type RotaryEmbeddingWan" graph-break (#4053)
Signed-off-by: Kristoffer Torp <kristoffer.torp@amd.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-17 15:48:22 +08:00
64a5bb92de [Refactor] Omni Stage Runtime and Distributed Replica Control Plane (#3855)
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Chenguang ZHENG <645327136@qq.com>
2026-06-17 14:13:20 +08:00
KristofferandHongsheng Liu e3621ec633 [Perf][qwen-image-edit] Skip attention-mask to avoid varlen path (#4293)
Signed-off-by: kTorp <Kristoffer.Torp@amd.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-16 22:52:04 +08:00
Chendi.XueandHongsheng Liu e7f0db1067 [SDXL] SDXL model enabling (#4331)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-16 22:51:11 +08:00
Samit 5f5b77aa9c [BugFix][Qwen-Image] align txt_seq_lens RoPE width with padded embeds (#4474)
Signed-off-by: samithuang <285365963@qq.com>
2026-06-16 19:09:25 +08:00
Kwokho TsuiandKwokho 3bce5e2e3a [Bugfix] Cosmos3: fix HSDP dtype mismatch on time_embedder via _hsdp_ignored_modules (#4452)
Signed-off-by: Kwokho <kh_tsui@163.com>
Co-authored-by: Kwokho <kh_tsui@163.com>
2026-06-16 04:06:14 +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
dengyunyang a86c333c7e [Perf][HunyuanImage] remove sync logic (#4401)
Signed-off-by: dengyunyang <584797741@qq.com>
2026-06-16 05:28:51 +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
ae937320ff [Feature] Add HunyuanImage3 DiT grouped step batching (#4041)
Signed-off-by: TaffyOfficial <2324465096@qq.com>
Signed-off-by: zuiho <2324465096@qq.com>
Co-authored-by: TaffyOfficial <2324465096@qq.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-15 20:36:41 +08:00
Mu GuanLin 11829ccd75 [Bugfix] Fix LTX-2.3 tensor-parallel gated attention (#4439)
Signed-off-by: mglyn <1203789601@qq.com>
2026-06-15 11:40:06 +00:00
Ting FU 6c6fde3e6d [BugFix] Fix HunyuanImage3 size match issue (#4416)
Signed-off-by: Semmer <semmer@live.cn>
2026-06-15 09:36:39 +08:00
Zhou Taichang 7b837944a1 [Rebase] Rebase to vllm 0.23.0 (#4286)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-06-13 16:43:02 +00:00
Chendi.Xue a9ee92ddec [XPU] update Dreamzero to support any HW (#4399)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
2026-06-13 15:32:39 +00:00
Hongsheng Liu fa94f41807 [Bugfix] Surface all-rank diffusion RPC failures (#4403)
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>
2026-06-13 15:42:16 +08:00
Joni JuvonenandHongsheng Liu 20b7a67b0d [Perf][Wan2.2] Skip attention mask for zero-padded SP sequences to avoid varlen path (#3763)
Signed-off-by: jjuvonen-amd <joni.juvonen@amd.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-13 07:50:39 +08:00
Ting FU 1be1a71156 [Model] Add more resolution support for HunyuanImage3.0 (#4004)
Signed-off-by: Semmer <semmer@live.cn>
2026-06-12 14:44:00 +08:00
Chendi.Xue 3fe3aa359b [XPU][COSMOS3] removing cuda hardcode and make VLLM_VIDEO_SYNC_TIMEOUT a tunable config (#4360)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
2026-06-12 04:55:07 +00:00
MaciejBalaNVandHongsheng 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
dengyunyang eb964dcec5 [HunyuanImage][Perf] opt prepare_attention_mask for e2e latency 6% reduction (#4333)
Signed-off-by: dengyunyang <584797741@qq.com>
2026-06-11 19:06:22 +08:00
Chendi.XueandHongsheng Liu 5414f78e5f [WAN2.2-S2V] Add server API for image + audio (#3394)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-11 18:50:03 +08:00
WeiQing ChenandHongsheng Liu f3d40b5402 [Bugfix] Add Cosmos3-Nano baselines and fix USP gather (#4301)
Signed-off-by: david6666666 <530634352@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-11 18:36:26 +08:00
Kushanam 74b5ae5ebe [Bugfix] Fix SP denoise indentation bug on BAGEL (#4328)
Signed-off-by: Kushan A. <kahmadian@nvidia.com>
2026-06-11 03:32:22 +00:00
3753b21c3d [Feature] LoRA support for SenseNova-U1 (#3971)
Signed-off-by: leohuang257 <masugchds@gmail.com>
Signed-off-by: Guanzhe (Leo) Huang <116847811+leohuang257@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
2026-06-09 14:36:35 +00:00
Mu GuanLin bf03413c36 [Feat] Add vae-decode-parallel for LTX-2.3 (#4277)
Signed-off-by: mglyn <1203789601@qq.com>
2026-06-09 13:14:16 +00:00
Chendi.Xue f174ee54b0 [XPU] Add sage_attn backend (#3785)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
2026-06-09 19:28:18 +08:00
Mu GuanLin 02eb7a4ecb [Bugfix] Register LTX RMSNorm identity weight as buffer (#4278)
Signed-off-by: mglyn <1203789601@qq.com>
2026-06-09 09:09:39 +00:00
yangjianjuan cb1c5a0c39 [Perf] lance perf optimize (t2i & i2i) (#4214)
Signed-off-by: yangjianjuan <510818155@qq.com>
2026-06-09 08:31:57 +00:00
weizhoublue 1b85df0510 fix: Propagate Quantization Configuration to HunyuanVideo-1.5 I2V Transformer to Enable FP8 Layers (#4245)
Signed-off-by: weizhoublue <weizhou.lan@daocloud.io>
2026-06-09 15:28:32 +08:00
Alex Brooks 7dcbeaea03 [Core] Cleanup DiffusersPipelineLoader (#1932)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
2026-06-09 11:55:32 +08:00
b8f68174ad [Refactor] Remove dead legacy pipeline.yaml loader and duplicate diff… (#4023)
Signed-off-by: dph97 <nenbaying@163.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: zhuhonghan <z00806815@china.huawei.com>
2026-06-09 07:34:35 +08:00