Commit Graph
44 Commits
Author SHA1 Message Date
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
SYLAR 759aa4ffeb [Diffusion][Performance] Optimize MiniMax-H3 video output transfer (#6824)
Signed-off-by: lishunyang12 <lishunyang12@163.com>
2026-08-31 07:07:34 +08:00
HAAZZZEEEE c50b7de167 [NPU][Diffusion] MiniMax-H3 RainFusion end_step tail fallback (#6037)
Signed-off-by: HAAZZZEEEE <wang-taicheng@qq.com>
2026-08-29 18:36:05 +08:00
Wenjia LiandWeiQing Chen d9980c75e8 Perf/minimax h3 dit swiglu rope cache npu (#6410)
Signed-off-by: Wenjia Li <wjialish@gmail.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-08-29 09:14:52 +00:00
Zijun HuangandWeiQing Chen 08cdee8dc4 [Feature] Support MiniMax-H3 FlashGen native LoRA with the legacy manager (#6666)
Signed-off-by: Zijun Huang <zijunhua@usc.edu>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-08-29 06:52:19 +00:00
fan2956andWeiQing Chen 0dc8f45906 [Feat] Minimax H3 support ref and tgt video sparse attention on NPU (#6518)
Signed-off-by: fan2956 <zhoufan53@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-08-29 11:10:53 +08:00
Mu GuanLinandWeiQing Chen 9558fd2ea8 [Bugfix] Scope MiniMax-H3 cuDNN SDPA state (#6710)
Signed-off-by: mglyn <1203789601@qq.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-08-28 19:40:50 -07:00
Mu GuanLinandHongsheng Liu 04b97a5922 [Perf] MiniMax-H3 VAE Decoder Ops (#6607)
Signed-off-by: mglyn <1203789601@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-28 15:14:33 +08:00
b6a4baa659 [Feature] Support text encoder Disaggregation for H3 (#5885)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Signed-off-by: yuanwu <yuan.wu@intel.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: yuanwu <yuan.wu@intel.com>
2026-08-28 14:27:05 +08:00
Mu GuanLinandHongsheng Liu 59cf3add40 [Feature] Support MiniMax-H3 Turbo LoRA with DLO (#6550)
Signed-off-by: mglyn <1203789601@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-26 16:15:47 +08:00
XiongZhongwei 40dcfdbb43 [Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040)
Signed-off-by: MarkPoloChina <1228479724@qq.com>
Signed-off-by: XiongZhongwei <1228479724@qq.com>
2026-08-26 09:14:05 +08:00
Hongsheng Liu 5a8b81ebeb [Model] Optimize MiniMax-H3 DLO component lifecycle (#6526)
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>
2026-08-25 23:13:41 +08:00
Bo Li 51b7565f33 [perf] Add mask-free TRTLLM packed-padding path (#6542)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-08-25 07:45:21 +00:00
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
Mu GuanLinandHongsheng Liu 3d035bfa19 [Feature] Support MiniMax-H3 Turbo LoRA with the legacy manager (#6476)
Signed-off-by: mglyn <1203789601@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-24 06:21:42 +08:00
Hongsheng Liu 493fc64397 [Diffusion] Add final-layout BF16 Host Weight Runtime artifacts (#6445)
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-22 21:37:20 +08:00
R0CKSTAR 260db8bab5 [Bugfix][Diffusion] Fix MiniMax-H3 model-level CPU offload residency (#6072)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2026-08-21 10:30:53 +00:00
linzhenpl07andClaude Opus 5 38cf9adc38 [BugFix][Diffusion] Fix MiniMax-H3 VAE hang when decoder tiles are fewer than ranks (#6345)
Signed-off-by: linzhenpl07 <linzhenpl07@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-20 12:42:14 +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
Canlin Guo 14f2c16fb2 [Perf] Fuse MiniMax H3 modulation with FP32 accumulation (#6281)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
2026-08-18 20:13:54 -07:00
Canlin Guo 9683b7f4b4 [Perf] Fuse MiniMax H3 SwiGLU activation (#6283)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
2026-08-18 20:12:10 -07:00
Hongsheng Liu 9d2bb23ff6 [Diffusion] Add loader-owned host-weight plans for DLO (TP=1) (#6213)
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-16 11:02:38 +08:00
SYLARandHongsheng Liu d1e230c95b [Diffusion][Quantization] Enable MiniMax-H3 global FP8 with DLO (#5910)
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-15 23:01:26 +08:00
7b76b6446d [Model][Performance] Optimize MiniMax-H3 strict Ulysses boundaries (#6173)
Signed-off-by: mokashliu <mokashliu@tencent.com>
Co-authored-by: mokashliu <mokashliu@tencent.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-08-15 16:27:52 +08:00
R0CKSTAR 022d7a7695 [Perf][Diffusion] Avoid redundant MiniMax-H3 reference video scans (#6064)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2026-08-14 15:49:26 +08:00
596c16a550 [Kernel] Fuse Q/K RMSNorm and RoPE (#5990)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Signed-off-by: Mengjie Zhao <zmj0129@gmail.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-14 00:46:59 +00:00
Wenjia LiandHongsheng Liu 38a2500bdf [Perf] MiniMax H3 Qwen3-VL support fused RMSNorm on NPU (#5915)
Signed-off-by: Wenjia Li <wjialish@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-08-12 19:12:54 +08:00
Zijun HuangandWeiQing Chen 1a56953d7a [NPU][Model] Add distilled 4-step sigma schedule support for MiniMax H3 t2va (#5991)
Signed-off-by: Zijun Huang <zijunhua@usc.edu>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-08-11 13:46:10 +08:00
WeiQing Chen 1f65814fab [CI] Align MiniMax H3 Ref2VA inputs and add I2VA/Ref2VA accuracy coverage (#5978)
Signed-off-by: david6666666 <530634352@qq.com>
2026-08-11 13:36:37 +08:00
ooooooye 740f45abcd [Perf][Diffusion] MiniMax-H3: opt into packed varlen attention on NPU to eliminate quadratic mask materialization (#5891)
Signed-off-by: brandneway <gyuan4892@gmail.com>
2026-08-10 19:47:03 +08:00
R0CKSTAR 636d44e272 [Perf][MUSA] Restore MiniMax-H3 dynamic RoPE fusion (#5881)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2026-08-10 17:24:46 +08:00
Shenglei FuandClaude Opus 5 81b48e83ec [Model] Fail MiniMax H3 encoder load when a weight or fused shard is missing (#5824)
Signed-off-by: Shenglei Fu <sfu@confluent.io>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-08 13:14:00 +08:00
Mu GuanLin d8c35663b4 [Model][Feat] Support Minimax-H3 quality grading requests through dynamic loading/unloading with Cache-DiT (#5853)
Signed-off-by: mglyn <1203789601@qq.com>
2026-08-07 09:07:23 +00:00
48298030d4 [Diffusion] Add Minimax-H3 modular pipeline support (#5720)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Signed-off-by: David Chen <530634352@qq.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: David Chen <530634352@qq.com>
2026-08-06 11:43:23 +00:00
d219d93bbb [Attention] Refine TRTLLM attention support for MiniMax H3 (#5779)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
2026-08-06 09:38:17 +00:00
Zijun HuangandWeiQing Chen 93457f29ff [NPU][Quantization] Add RainFusion attention and INT8 online quantization for MiniMax H3 (#5706)
Signed-off-by: Zijun Huang <zijunhua@usc.edu>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-08-06 14:15:21 +08:00
ooooooye f879ad4983 fix(minimax-h3): pass device_type to fork_rng so VAE condition encode works on NPU devices (#5837)
Signed-off-by: brandneway <gyuan4892@gmail.com>
2026-08-06 03:56:55 +00:00
fan2956andFan f2e3d2e25b [Perf] Minimax-H3 support fused RMSNorm and RoPE opt (#5801)
Signed-off-by: Fan <fan@FandeMacBook-Air.local>
Co-authored-by: Fan <fan@FandeMacBook-Air.local>
2026-08-06 11:39:27 +08:00
SYLARandlishunyang12 1c2a81f6d8 feat(minimax-h3): enable 2x RTX 4090/5090 with DLO (#5764)
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
2026-08-06 09:02:29 +08:00
R0CKSTAR 2eada79b99 [Hardware][MUSA] Make MiniMax H3 conditioned VAE RNG device-aware (#5703)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2026-08-05 03:11:46 -07:00
WeiQing Chen ae7bee0c43 [Feature] Align MiniMax H3 official input matrix (#5752)
Signed-off-by: david6666666 <530634352@qq.com>
2026-08-05 07:12:01 +00:00
Mu GuanLin b9a51592f0 [Model][Feat] MiniMax H3 online FP8 support (#5737)
Signed-off-by: mglyn <1203789601@qq.com>
2026-08-04 11:35:01 +00:00
ooooooye a4ea67a21b [Model] Add soundfile fallback for MiniMax H3 audio loading (#5699)
Signed-off-by: brandneway <gyuan4892@gmail.com>
2026-08-03 16:24:50 +08:00
Isotr0py 24741961eb [Model] Add MiniMax H3 diffusion support (#5691) 2026-08-03 14:10:40 +08:00