30f16f1d4e
Introduces a YAML recipe system for simplified model deployment: - run-recipe.py: Main script handling build, download, and launch - run-recipe.sh: Bash wrapper for dependency management - recipes/: Pre-configured recipes for common models - glm-4.7-flash-awq.yaml: GLM-4.7-Flash with AWQ quantization - glm-4.7-nvfp4.yaml: GLM-4.7 with NVFP4 (cluster-only) - minimax-m2-awq.yaml: MiniMax M2 with AWQ - openai-gpt-oss-120b.yaml: OpenAI GPT-OSS 120B with MXFP4 Key features: - Auto-discover cluster nodes with --discover, saves to .env - Load nodes from .env automatically on subsequent runs - cluster_only flag for models requiring multi-node setup - build_args field for Dockerfile selection (--pre-tf, --exp-mxfp4) - Solo mode auto-strips --distributed-executor-backend ray - --setup flag for full build + download + run workflow - --dry-run to preview execution without running Usage: ./run-recipe.sh --discover # Find and save cluster nodes ./run-recipe.sh glm-4.7-flash-awq --solo --setup ./run-recipe.sh glm-4.7-nvfp4 --setup # Uses nodes from .env
41 lines
1007 B
YAML
41 lines
1007 B
YAML
# Recipe: MiniMax-M2-AWQ
|
|
# MiniMax M2 model with AWQ quantization
|
|
|
|
recipe_version: "1"
|
|
name: MiniMax-M2-AWQ
|
|
description: vLLM serving MiniMax-M2-AWQ with Ray distributed backend
|
|
|
|
# HuggingFace model to download (optional, for --download-model)
|
|
model: QuantTrio/MiniMax-M2-AWQ
|
|
|
|
# Container image to use
|
|
container: vllm-node
|
|
|
|
# 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: 0.7
|
|
max_model_len: 128000
|
|
|
|
# Environment variables
|
|
env: {}
|
|
|
|
# The vLLM serve command template
|
|
command: |
|
|
vllm serve QuantTrio/MiniMax-M2-AWQ \
|
|
--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_append_think
|