caa28c8e12
Add a vLLM serving recipe for the MiniMax M2.7 model using the cyankiwi/MiniMax-M2.7-AWQ-4bit quantization. Uses the same minimax_m2 tool-call and reasoning parsers as the existing M2 recipe, with Ray distributed backend on 2 GPUs.
45 lines
1.1 KiB
YAML
45 lines
1.1 KiB
YAML
# Recipe: MiniMax-M2.7-AWQ
|
|
# MiniMax M2.7 model with AWQ quantization
|
|
|
|
recipe_version: "1"
|
|
name: MiniMax-M2.7-AWQ
|
|
description: vLLM serving MiniMax-M2.7-AWQ with Ray distributed backend
|
|
|
|
# HuggingFace model to download (optional, for --download-model)
|
|
model: cyankiwi/MiniMax-M2.7-AWQ-4bit
|
|
|
|
# Container image to use
|
|
container: vllm-node
|
|
|
|
# Can only be run in a cluster
|
|
cluster_only: true
|
|
|
|
# No mods required
|
|
mods: []
|
|
|
|
# Default settings (can be overridden via CLI)
|
|
defaults:
|
|
port: 8000
|
|
host: 0.0.0.0
|
|
tensor_parallel: 2
|
|
gpu_memory_utilization: 0.8
|
|
max_model_len: 196608
|
|
|
|
# Environment variables
|
|
env: {}
|
|
|
|
# The vLLM serve command template
|
|
command: |
|
|
vllm serve cyankiwi/MiniMax-M2.7-AWQ-4bit \
|
|
--trust-remote-code \
|
|
--port {port} \
|
|
--host {host} \
|
|
--gpu-memory-utilization {gpu_memory_utilization} \
|
|
-tp {tensor_parallel} \
|
|
--distributed-executor-backend ray \
|
|
--max-model-len {max_model_len} \
|
|
--load-format fastsafetensors \
|
|
--enable-auto-tool-choice \
|
|
--tool-call-parser minimax_m2 \
|
|
--reasoning-parser minimax_m2
|