Commit Graph
60 Commits
Author SHA1 Message Date
Anjie HouandClaude Sonnet 5 ecdd762ff5 [2/N] Add a minimal temporal chunk callback for MiniMax-H3 (#7017)
Signed-off-by: specture724 <specture724@gmail.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-09 16:40:32 +08:00
6942a5b600 [1/N] Stream Wan VAE chunks to the media consumer (#7016)
Signed-off-by: specture724 <specture724@gmail.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-09-08 07:41:13 +08:00
Hongsheng Liu d4096e01fe [Model] Add native MAGI-2 Preview diffusion support (#5918)
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>
2026-09-05 15:32:30 +08:00
hurukawa 8f284b343a [Feature][Diffusion]: CFG parallelism support for Boogu-Image (#6786)
Signed-off-by: nagisa <1434936049@qq.com>
Signed-off-by: nagisa-kun <1434936049@qq.com>
2026-09-03 10:37:21 +08:00
Bo Li 6f16f9546d [Bugfix][Kernel] Stage strided Ulysses QKV with copy engine (#6814)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-08-31 17:28:49 +08:00
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
baonudesifeizhai 8be601ed7f [Diffusion] Add native SymmMem Fast Ulysses transport (#6340)
Signed-off-by: roG0d <baonudesifeizhai@gmail.com>
2026-08-30 04:14:21 +00:00
Hongsheng Liuandhsliuustc0106 8bfad23f98 [Core] Restore topology-aware diffusion worker titles (#6722)
Signed-off-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>
Co-authored-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>
2026-08-29 08:45:57 +08:00
wangyuandCursor aeb348d8f8 [CI]Remove DreamID-Omni and MagiHuman support (#6357)
Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: [Your Name] <your.email@example.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-26 01:31:12 +00:00
WeiQing Chen 53df9fe62b [Bugfix] Use dedicated WORLD group for distributed VAE communication (#6401)
Signed-off-by: david6666666 <530634352@qq.com>
2026-08-20 16:13:34 +08:00
bjf-frzandHongsheng Liu 14bd8f8772 [REFACT]Refactor diffusion parallel state (#5531)
Signed-off-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-19 11:23:10 +08:00
Rahul SteigerandRahul Steiger 854bff7fe5 [Bugfix] Fix Wan spatial reshard boundary (#6062)
Signed-off-by: Rahul Steiger <rsteiger@nvl72d106-T18.cm.cluster>
Co-authored-by: Rahul Steiger <rsteiger@nvl72d106-T18.cm.cluster>
2026-08-12 11:36:24 +08:00
Zhou TaichangandClaude Opus 5 2ce15ab7a0 [Rebase] Rebase to vllm 0.27.0 (#5976)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-11 15:23:46 +00:00
e108cbb510 [NPU][HunyuanImage3] Adapt diffusion FusedMoE for vLLM >= 0.24.0 (#5167)
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Signed-off-by: jiangmengyu18 <56633611+jiangmengyu18@users.noreply.github.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-27 22:41:34 +08:00
84bbd57e4d [Feature] Add AllGather-KV sequence-parallel attention str… (#4968)
Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
Signed-off-by: dph97 <nenbaying@163.com>
Signed-off-by: zhuhh97 <zhh@unknown>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: dengyunyang <584797741@qq.com>
2026-07-24 14:45:26 +00:00
Diya Peng acf941da4d [Diffusion] Add VAE patch parallel support for FLUX.2-dev (#5292)
Signed-off-by: dpeng123 <diyapeng123@gmail.com>
2026-07-24 07:00:57 +00:00
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
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
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
TaffyOfficialandzuiho 66ec3a2aff [Bugfix] Fix HunyuanImage3 MoE groups for vLLM 0.24 (#4893)
Signed-off-by: zuiho <2324465096@qq.com>
Co-authored-by: zuiho <2324465096@qq.com>
2026-07-05 15:37:42 +00:00
Jiaqian Liu a25636d780 [NPU] Fix HunyuanImage3 MoE EP+SP parallel mapping (#4344)
Signed-off-by: Celeste-jq <591998922@qq.com>
2026-07-02 04:14:12 +00:00
dd3a4d0a29 [Feat] Support CFG-Parallel For Sensenova-U1-8B-MoT (#4188)
Signed-off-by: sphinxkkkbc <binchengkang8@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: sphinxkkkbc <binchengkang8@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-06-30 08:03:26 +00:00
Rahul SteigerandHongsheng Liu 327e9dcaf2 [Feature] Spatially-sharded (SP) decode for the Wan VAE (#4620)
Signed-off-by: Rahul Steiger <rsteiger@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-27 09:01:25 +08:00
bmengkeandHongsheng Liu 329c98ff9d Wan2.2: Fix the bug of using cache-dit with ulysses in t2v and i2v (#3927)
Signed-off-by: Mengkejiergeli Ba <mengkejiergeli.ba@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-06-25 15:15:59 +00:00
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
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
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
WeiQing Chen a3456752c5 [Diffusion] Support USP and VAE patch parallel for HunyuanVideo 1.5 (#3979)
Signed-off-by: david6666666 <530634352@qq.com>
2026-05-30 14:40:42 +08:00
Huanyu Yang 3457758114 [Bugfix] Fix IndexError in DistributedVaeExecutor when vae_patch_parallel_size < world_size (#3928)
Signed-off-by: QingZhou-YangHY <3868850350@qq.com>
2026-05-29 03:17:34 -07:00
Chenguang ZhengandCanlin Guo 7d8816b46b [Bugfix] Fix Hunyuan worker device context (#3768)
Signed-off-by: Chenguang ZHENG <645327136@qq.com>
Signed-off-by: Canlin Guo <961750412@qq.com>
Co-authored-by: Canlin Guo <961750412@qq.com>
2026-05-22 02:17:59 +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
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
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
Hongsheng Liu 7fc528f7a9 Revert "[Quantization] Enable FP8 online quantization for Z-image text encoder" (#3272) 2026-04-30 15:08:17 +08:00
Isotr0py ac66282746 [Quantization] Enable FP8 online quantization for Z-image text encoder (#1338)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2026-04-30 14:12:01 +08:00
fan2956 c2578f7131 [Bugfix] Fix VAE parallelism dist.gather performance bottleneck on NPU (#2969)
Signed-off-by: fan2956 <zhoufan53@huawei.com>
2026-04-21 20:35:02 +08:00
NATUREandHongsheng Liu 4d816ff1de [Feature] Bagel: Support tp+cfg parallel using mooncake transfer engine connector (#2705)
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-04-16 16:25:13 +08:00
zhou zhuoxin 16041ab550 [Refactor] Extend CFG Parallel to support 3 or 4 branch dispatch across M GPUs (#2423) 2026-04-12 22:06:49 +08:00
Y. FisherandCanlin Guo ec082add35 [Perf] Wan2.2 I2V optimization: convert datatype from FP32 to BF16 in vae (#2391)
Signed-off-by: KexiongYu <yukexiong1@huawei.com>
Signed-off-by: Canlin Guo <961750412@qq.com>
Co-authored-by: Canlin Guo <961750412@qq.com>
2026-04-08 03:26:39 +00:00
Canlin GuoandHongsheng Liu e771842781 [Feature] Support vae tiling parallel encode (#2368)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-04-06 14:47:45 +00:00
Lancer 70a62651b9 [Feat] support HSDP for Qwen-image series, Z-Image, GLM-Image (#2029)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
2026-04-01 20:01:09 +08:00
zdobaanddaixinning 08cb436d4e Fix: ensure input tensor is contiguous in GroupCoordinator.all_gather (#2367)
Signed-off-by: daixinning <daixinning@163.com>
Co-authored-by: daixinning <daixinning@163.com>
2026-04-01 16:41:25 +08:00
Yangshen DengandClaude Opus 4.6 837679dbaa [Diffusion] Refactor CFG parallel for extensibility and performance (#2063)
Signed-off-by: Yangshen Deng <yangshen.d@outlook.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 16:48:58 +00:00
Wu JIAZHEN da7a8f8014 reafator pipeline stage/step pipeline (#1368)
Signed-off-by: asukaqaq-s <1311722138@qq.com>
2026-03-20 19:21:50 +08:00
Ting FU 6ac85d4607 [Feat] Enable expert parallel for diffusion MoE layers (#1323)
Signed-off-by: Semmer2 <semmer@live.cn>
2026-03-11 10:45:36 +08:00
Canlin Guo 29357027b0 [Bugfix] Allow to enable HSDP alone (#1567)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
2026-03-09 06:36:13 +00:00
dengyunyang d275c0c993 [FEATURE] Tile/Patch parallelism refactor for easily support other models (#1366)
Signed-off-by: dengyunyang <584797741@qq.com>
2026-03-03 15:48:51 +08:00
Canlin GuoandHongsheng Liu f53152d340 [Feature] Support HSDP for diffusion models (#1339)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-02-26 21:31:10 +08:00
Dong WandHongsheng Liu 1eebb374f1 [Model]Add new nextstep_1(Diffusion) model(only T2I) (#612)
Signed-off-by: Dong Wang <dongw2019@gmail.com>
Signed-off-by: sniper35 <dongw2019@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-02-26 00:09:11 +08:00
dongbo910220andhsliuustc0106 43e8747c00 [Feat]: support VAE patch parallelism (#756)
Signed-off-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: hsliuustc0106 <liuhongsheng4@huawei.com>
2026-02-10 17:36:10 +08:00