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

docs(minimax-m3): use published AMD ROCm images (#28777)

Browse Source 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
zijiexia
2026-06-23 07:48:16 +01:00
committed by GitHub
co-authored by Claude Opus 4.8
parent 7e6587c94a
commit 52a90c9a36
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/cookbook/autoregressive/MiniMax/MiniMax-M3.mdx
+1 -1
View File
@@ -39,7 +39,7 @@ Then run the **Python** output of the command panel below in that environment. T
docker pull lmsysorg/sglang:dev-cu13-minimax-m3
```
The command panel below fills in the right tag per platform: `dev-cu13-minimax-m3` (CUDA 13 — B300, GB200, GB300), `dev-cu12-minimax-m3` (CUDA 12 — Hopper H200), or `dev-minimax-m3` (default). On AMD Instinct it uses the matching ROCm image (MI300X/MI325X → `…-rocm700-mi30x`, MI350X/MI355X → `…-rocm720-mi35x`). For how to launch the image, see [Install → Method 3: Using Docker](../../../docs/get-started/install#method-3-using-docker), substituting the inner `sglang serve ...` with what the command generator produces.
The command panel below fills in the right tag per platform: `dev-cu13-minimax-m3` (CUDA 13 — B300, GB200, GB300), `dev-cu12-minimax-m3` (CUDA 12 — Hopper H200), or `dev-minimax-m3` (default). On AMD Instinct it uses the matching ROCm image (MI300X/MI325X → `aigmkt/minimax-m3-sglang-rocm700-mi30x`, MI350X/MI355X → `aigmkt/minimax-m3-sglang-rocm720-mi35x`). For how to launch the image, see [Install → Method 3: Using Docker](../../../docs/get-started/install#method-3-using-docker), substituting the inner `sglang serve ...` with what the command generator produces.
<Note>
These M3 dev images now **bundle MiniMax's MSA sparse-attention kernel** (`fmha_sm100`), so Blackwell users get the recommended fast path automatically — no manual install needed (see **§2.1**). On a custom image without it, the same recipe still serves on the built-in Triton sparse path.
docs_new/src/snippets/configs/MiniMaxAI/minimax-m3.jsx
+5 -5
View File
@@ -97,11 +97,11 @@ sgl-eval run mmmu_pro \\
gb200: "lmsysorg/sglang:dev-cu13-minimax-m3",
gb300: "lmsysorg/sglang:dev-cu13-minimax-m3",
h200: "lmsysorg/sglang:dev-cu12-minimax-m3",
// AMD ROCm images — pin the exact tag from the validated build (see Configuration Tips).
mi300x: "lmsysorg/sglang:<rocm-tag>-rocm700-mi30x",
mi325x: "lmsysorg/sglang:<rocm-tag>-rocm700-mi30x",
mi350x: "lmsysorg/sglang:<rocm-tag>-rocm720-mi35x",
mi355x: "lmsysorg/sglang:<rocm-tag>-rocm720-mi35x",
// AMD ROCm images — published M3 builds, by arch (gfx942 -> mi30x, gfx950 -> mi35x).
mi300x: "aigmkt/minimax-m3-sglang-rocm700-mi30x",
mi325x: "aigmkt/minimax-m3-sglang-rocm700-mi30x",
mi350x: "aigmkt/minimax-m3-sglang-rocm720-mi35x",
mi355x: "aigmkt/minimax-m3-sglang-rocm720-mi35x",
},
github: {