Commit Graph
64 Commits
Author SHA1 Message Date
LittleNyimaandMick Qian 5727f08932 [diffusion] feat: add configurable reference image resizing for MiniMax H3 Ref2VA (#35839)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-10-13 19:48:18 +08:00
97bfa5cc53 [diffusion] fix: select VSA-H3 for FastH3 when no transformer backend is given (#43690)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 23:05:25 +08:00
72657f7ca5 [diffusion] perf: pipeline every USPAttention Ulysses path's exchange over the copy engine (#43521)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 21:34:18 +08:00
d8c5eca3ac [diffusion] fix: keep a LoRA unmerged under merge_mode auto when merging would round its update away (#43385)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 15:02:03 +08:00
ccae3b3639 [diffusion] perf: pipeline MiniMax-H3's Ulysses exchange against cuDNN SDPA on Blackwell (#43373)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 12:58:30 +08:00
bookinstockandMick Qian 32f34e898b [diffusion] fix: honor requested inference step count for MiniMax H3(#38671)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-10-10 09:02:57 +08:00
bd7c7971ba [diffusion] perf: move MiniMax-H3's pipelined Ulysses copies off the SMs (#43361)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 08:58:07 +08:00
121aa8dcc7 [diffusion] perf: fuse MiniMax-H3's RMSNorm and indexed AdaLN under quality lossless (#43327)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 22:39:11 +08:00
1203eb9181 [diffusion] perf: pipeline MiniMax-H3's Ulysses exchange against attention over the copy engine (#43164)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 22:04:29 +08:00
4f320fb85a [diffusion] perf: FastH3 8-Step V2 native support, native Blackwell VSA and batched H3 VAE decode (#37662)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: mickqian <mickqian@users.noreply.github.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-10-08 14:35:27 +08:00
7a4d6dfd2f [diffusion] feat: name the quality tiers after what they guarantee (#42370)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-10-07 09:49:30 +08:00
WenhaoZhangandMick Qian f048d5aa4b [diffusion] feat: add community LoRA recipes and Kohya mapping (#35857)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-10-05 18:22:56 +08:00
Alex O. P.andPo-Han Huang e667ab10d5 [diffusion] quantization: ConvRot INT8 online W8A8 for DiTs (sgl-kernel + convrot_int8_customkernel) (#38040)
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
2026-10-02 23:26:28 +08:00
MickandMick Qian 2ab1b537f8 [diffusion] docs: recommend docker for gpu deployments (#41966)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-10-01 09:52:31 +08:00
WenhaoZhang f1e62e3a2e [diffusion] feat: add MiniMax-H3 to ComfyUI integrated mode (#35990) 2026-09-27 17:58:54 +08:00
WenhaoZhang ae47bcd4da [diffusion] feat: minimax-h3 spectrum skip-step + fused RMSNorm/AdaLN (#35684) 2026-09-27 17:56:13 +08:00
973fb44471 [Diffusion] Support MiniMax-H3 PDD(Parallel Decoding Distillation) inference (#40568)
Co-authored-by: Forrest Lin <forrestl@nvidia.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 12:57:26 +08:00
50ec9702d0 [diffusion] docs: update ComfyUI sections, trimmed examples, and the RTX 5090 DiT-resident recipe (1.42x) for Qwen-Image-2.1 cookbook (#40573)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-21 21:23:11 +08:00
MickandMick Qian 9784d5f979 [diffusion] doc: sync CFG and tracing documentation (#39883)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-18 18:03:40 +08:00
a25f213bc4 [diffusion] docs: give the RTX 5090 its own H3 recipe, measured on a physical desktop (#39373)
Co-authored-by: Mick Qian <mickqian@radixark.ai>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-15 09:15:13 +08:00
42b5af8c62 [diffusion] docs: refresh the VDN-H3 on b200 numbers in cookbook (#39244)
Co-authored-by: haochengxi <xihc@berkeley.edu>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
2026-09-14 11:50:40 +08:00
ff1ce11348 [diffusion] model: support VDN-H3 with a hybrid_window_attn_h3 backend (#37903)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Haocheng Xi <xihc@berkeley.edu>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-09-12 11:36:32 +08:00
MickandMick Qian c9c26d56b2 [diffusion] docs: sync snapshot and minimax-h3 subblock features (#38784)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-10 17:23:43 +08:00
MickandMick Qian a8e45f16cc [diffusion] feat: support mixed INT8 embeddings and Comfy NVFP4 encoders for minimax-h3 (#38506)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-09 08:36:43 +08:00
MickandMick Qian 65400bb420 [diffusion] model: support MiniMax-H3 singularity hybrid checkpoints (#38455)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-09 08:35:39 +08:00
Mick ba6d3df69a [diffusion] doc: document verified GB300 and derived GB200 H3 recipes (#38296) 2026-09-07 16:32:29 +08:00
MickandClaude Fable 5 ade1da017f [diffusion] docs: verify the DGX Spark H3 recipe (#37456)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-09-06 23:10:27 +08:00
triple-muandmickqian bf71035d39 [diffusion] MiniMax-H3: tiered AdaLN plan cache (pinned-host tier + per-plan LRU) (#37266)
Co-authored-by: mickqian <mickqian@users.noreply.github.com>
2026-09-03 22:09:21 +08:00
Kevin MiandClaude Fable 5 f586654518 [diffusion] feat: support FastH3 (4-step VSA-distilled MiniMax-H3) with a VSA-H3 attention backend (#37480)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-09-02 21:39:54 +08:00
4b329482e8 [diffusion] feat: support cube sparse attention for minimax h3 (#34893)
Co-authored-by: zhenaozhenfu <zhenaozhenfu@minimaxi.com>
Co-authored-by: Reynor <reynor@minimaxi.com>
2026-09-02 15:21:33 +08:00
Xiaoyu Zhang 1aa8299d1d [Diffusion] Add cumulative extra-high quality tier (#37422) 2026-09-02 10:26:13 +08:00
WenhaoZhang e9a7157615 [diffusion] feat: allow cache-dit with dit layerwise offload (#35858) 2026-08-30 20:55:41 +08:00
Mick c3c529c28e [diffusion] docs: distinguish MiniMax H3 checkpoint variants (#36412) 2026-08-26 15:16:18 +08:00
Mick 054f485d38 [diffusion] docs: add MiniMax H3 checkpoint format table (#36028) 2026-08-26 09:18:07 +08:00
MickandClaude Fable 5 c3947eeada [diffusion] docs: desktop-safe 24 GB recipe and the DGX Spark tier (#36169)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-25 20:25:17 +08:00
Mick 191244b3f6 [diffusion] feat: support loading Comfy NVFP4-AWQ text encoders (#36046) 2026-08-25 15:43:30 +08:00
Артем Савкинandronnie_zheng 61b67316d8 [NPU] [Diffusion] Support MiniMax H3 on Ascend NPU's (#33569)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
2026-08-25 09:44:14 +03:00
Mick 67853c5804 [diffusion] feat: dispatch fp8 companions in mixed NVFP4 checkpoints (#36066) 2026-08-25 11:26:37 +08:00
Mick ddea7b9156 [diffusion] feat: support mixed Comfy NVFP4 and INT8 layers (#36061) 2026-08-25 09:19:47 +08:00
Mick 30f9ed09d1 [diffusion] feat: support loading minimax h3 gguf text encoders (#36055) 2026-08-24 23:00:49 +08:00
Mick 9b0007ed19 [diffusion] feat: support loading comfy nvfp4 minimax h3 checkpoints (#36044) 2026-08-24 22:57:02 +08:00
Mick 76d1401881 [diffusion] feat: support mixed w4a4 and int8 checkpoints (#36040) 2026-08-24 20:35:11 +08:00
Mick bfeae4e79a [diffusion] feat: support loading serialized convrot w4a4 checkpoints (#36039) 2026-08-24 19:13:35 +08:00
Mick adc09a1f63 [diffusion] feat: support loading self-describing quanto int8 encoders (#36052) 2026-08-24 16:37:09 +08:00
Mick 8df3b9eff9 [diffusion] feat: support loading mixed w4a8 text encoders (#36037) 2026-08-24 13:31:27 +08:00
Mick 2d84de5e69 [diffusion] feat: support loading serialized comfy w4a8 checkpoints (#36036) 2026-08-24 10:32:21 +08:00
Mick 1c1c9d9b4e [diffusion] refactor: reuse srt quantization contracts and mxfp8 kernels (#36063) 2026-08-24 09:26:54 +08:00
Mick dd15fb57b5 [diffusion] feat: automatically infer comfy fp8 activation scaling (#36060) 2026-08-23 18:43:33 +08:00
Mick a36c0746b9 [diffusion] feat: support serialized comfy convrot int8 dits (#35994) 2026-08-23 09:29:59 +08:00
MickandClaude Opus 5 7d22b7a875 [diffusion] docs: add tuning guide for h3 on consumer-level gpu (#35816)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-22 23:48:40 +08:00