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

[diffusion] model: support MiniMax-H3 singularity hybrid checkpoints (#38455)

Browse Source 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
This commit is contained in:
Mick
2026-09-09 08:35:39 +08:00
committed by GitHub
co-authored by Mick Qian
parent db272201a2
commit 65400bb420
12 changed files with 231 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/sglang-diffusion/api/cli.mdx
+1 -1
View File
@@ -76,7 +76,7 @@ Use `sglang generate --help` and `sglang serve --help` for the full argument lis
- `--model-path {MODEL}`: model path or Hugging Face model ID
- `--served-model-name {NAME}`: stable model name exposed by serving APIs. Defaults to `--model-id` when set, otherwise `--model-path`.
- `--model-variant {NAME}`: semantic checkpoint variant to load when one model repository contains multiple weight partitions. The pipeline maps this stable name to the repository layout before loading; for example, MiniMax-H3 accepts `fl2va` and `ref2va`. This is a server/load-time choice, unlike a request's `task`.
- `--model-variant {NAME}`: semantic checkpoint variant to load when one model repository contains multiple weight partitions. The pipeline maps this stable name to the repository layout before loading; for example, MiniMax-H3 accepts `fl2va` and `ref2va`, or `hybrid` with explicit merged transformer weights to serve all three tasks (see the [H3 cookbook](/cookbook/diffusion/MiniMax/MiniMax-H3#singularity-hybrid-weights)). This is a server/load-time choice, unlike a request's `task`.
- `--minimax-h3-adaln-cache-path {FILE}`: advanced MiniMax-H3-only inference cache. It replaces the checkpoint's AdaLN projection weights with precomputed outputs and only accepts requests whose exact FP32 timestep plan is included in the cache. It requires unquantized weights and the matching model variant.
- `--minimax-h3-adaln-online {true,false}`: rebuild MiniMax-H3 AdaLN outputs from the checkpoint on demand instead of keeping the 24.2 GiB of `adaln_proj` weights resident. Works with any step count or schedule; requires the unquantized native-layout checkpoint. Built plans live in a GPU slab with per-plan LRU eviction and, by default, a pinned-host cache so previously seen schedules swap back in over PCIe instead of re-reading the checkpoint.
- `--minimax-h3-adaln-plan-width {N}`: widest timestep plan the online slab is sized for (default 4 covers every task; t2va needs 2, fl2va 3).