Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions MiniMax/MiniMax-M2.md
Original file line number Diff line number Diff line change
Expand Up @@ -177,6 +177,20 @@ vllm serve MiniMaxAI/MiniMax-M2.5 \

You can use 2x or 4x MI300X/MI325X/MI350X/MI355X GPUs to launch this model with [AITER](https://github.com/ROCm/aiter) acceleration enabled:

#### MiniMax-M2

- TP4 (4x MI300X/MI325X/MI350X/MI355X)
```bash
VLLM_ROCM_USE_AITER=1 vllm serve MiniMaxAI/MiniMax-M2 \
--tensor-parallel-size 4 \
--tool-call-parser minimax_m2 \
--reasoning-parser minimax_m2_append_think \
--enable-auto-tool-choice \
--trust-remote-code
```

#### MiniMax-M2.5

- TP2 (2x MI300X/MI325X/MI350X/MI355X)
```bash
VLLM_ROCM_USE_AITER=1 vllm serve MiniMaxAI/MiniMax-M2.5 \
Expand Down