minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[diffusion] feat: support loading comfy nvfp4 minimax h3 checkpoints (#36044)

Browse Source
This commit is contained in:
Mick
2026-08-24 22:57:02 +08:00
committed by GitHub
parent 76d1401881
commit 9b0007ed19
9 changed files with 123 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cookbook/diffusion/MiniMax/MiniMax-H3.mdx
+6
View File
@@ -314,6 +314,12 @@ honors each layer's activation mode; omit `--quantization`.
Mixed exports use the same command: SGLang dispatches each marked layer to its
serialized W4A4 or INT8 ConvRot kernel instead of applying one global method.
Comfy NVFP4 DiTs reuse SGLang's ModelOpt NVFP4 backend, which requires CUDA
compute capability 10.0 or newer. Pass a pruned FL2VA / Ref2VA file such as
`Abiray/Minimax-H3-nvfp4-INT4-INT8-Convrot/MiniMax_H3_FL2VA_pruned_nvfp4.safetensors`
to `--transformer-weights-path` and omit `--quantization`. SGLang infers the
packed group size and Comfy scale layout from the checkpoint; FSDP is rejected.
### Advanced: precomputed AdaLN cache
The [model card](https://huggingface.co/MiniMaxAI/MiniMax-H3) notes that about
docs/docs/sglang-diffusion/quantization.mdx
+3 -3
View File
@@ -154,11 +154,11 @@ backend.
</tr>
<tr>
<td><code>modelopt-nvfp4</code></td>
<td>Mixed transformer directory/repo with <code>config.json</code>, raw NVFP4 safetensors export/repo, or full ModelOpt Diffusers repo</td>
<td>Mixed transformer directory/repo with <code>config.json</code>, raw or Comfy layer-marked NVFP4 safetensors, or full ModelOpt Diffusers repo</td>
<td><code>--transformer-path</code> for mixed overrides; <code>--transformer-weights-path</code> for raw exports; <code>--model-path</code> for full repos</td>
<td>FLUX.1, FLUX.2, Wan2.2, Qwen Image, Qwen Image 2512, Qwen Image Edit, Qwen Image Edit 2511</td>
<td>FLUX.1, FLUX.2, Wan2.2, Qwen Image, Qwen Image 2512, Qwen Image Edit, Qwen Image Edit 2511, MiniMax-H3</td>
<td>None</td>
<td>Mixed override repos keep the base model separate; full Qwen Image exports can be loaded directly as <code>--model-path</code>; raw exports such as <code>black-forest-labs/FLUX.2-dev-NVFP4</code> still use the weights-path flow</td>
<td>Mixed override repos keep the base model separate; full Qwen Image exports can be loaded directly as <code>--model-path</code>; raw exports such as <code>black-forest-labs/FLUX.2-dev-NVFP4</code> use the weights-path flow. Comfy markers select their checkpoint layout automatically; omit <code>--quantization</code>.</td>
</tr>
<tr>
<td><code>gguf</code></td>