engine = "vllm"
name = "MiniMax M3 MXFP8 (vLLM)"
docker_image = "aidendle94/sparkrun-vllm-ds4-gb10:production-v2"
model = "MiniMaxAI/MiniMax-M3-MXFP8"
required_nodes = 4
tensor_parallel_size = 4
pipeline_parallel_size = 1
distributed_backend = "mp"

# MXFP8 quantized MiniMax M3 (~440B params, ~23B active).
# 4 nodes × 1 GPU (DGX Spark GB10 Blackwell), TP=4 across nodes.
# MSA sparse attention requires --block-size 128.
# Text-only mode skips the vision encoder to save VRAM.

entrypoint = ["vllm", "serve"]

args = [
    "--block-size", "128",
    "--kv-cache-dtype", "fp8",
    "--gpu-memory-utilization", "0.85",
    "--tool-call-parser", "minimax_m3",
    "--reasoning-parser", "minimax_m3",
    "--enable-auto-tool-choice",
    "--language-model-only",
    "--enable-expert-parallel",
    "--trust-remote-code",
    "--served-model-name", "minimax-m3-mxfp8", "default",
]

[env]
# M3 supports thinking via chat_template_kwargs.thinking_mode
# enabled / adaptive / disabled — pass per-request in extra_body