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
53 lines
1.5 KiB
YAML
53 lines
1.5 KiB
YAML
# Recipe: OpenAI GPT-OSS 120B
|
|
# OpenAI's open source 120B MoE model with MXFP4 quantization support
|
|
|
|
recipe_version: "1"
|
|
name: OpenAI GPT-OSS 120B
|
|
description: vLLM serving openai/gpt-oss-120b with MXFP4 quantization and FlashInfer
|
|
|
|
# HuggingFace model to download (optional, for --download-model)
|
|
model: openai/gpt-oss-120b
|
|
|
|
# Container image to use
|
|
container: vllm-node-mxfp4
|
|
|
|
# Build arguments for build-and-copy.sh
|
|
build_args:
|
|
- --exp-mxfp4
|
|
|
|
# No mods required for this model
|
|
mods: []
|
|
|
|
# Default settings (can be overridden via CLI)
|
|
defaults:
|
|
port: 8888
|
|
host: 0.0.0.0
|
|
tensor_parallel: 2
|
|
gpu_memory_utilization: 0.70
|
|
max_num_batched_tokens: 8192
|
|
|
|
# Environment variables to set in the container
|
|
env:
|
|
VLLM_USE_FLASHINFER_MOE_MXFP4_MXFP8: "1"
|
|
|
|
# The vLLM serve command template
|
|
# Uses MXFP4 quantization for memory efficiency
|
|
command: |
|
|
vllm serve openai/gpt-oss-120b \
|
|
--tool-call-parser openai \
|
|
--reasoning-parser openai_gptoss \
|
|
--enable-auto-tool-choice \
|
|
--tensor-parallel-size {tensor_parallel} \
|
|
--distributed-executor-backend ray \
|
|
--gpu-memory-utilization {gpu_memory_utilization} \
|
|
--enable-prefix-caching \
|
|
--load-format fastsafetensors \
|
|
--quantization mxfp4 \
|
|
--mxfp4-backend CUTLASS \
|
|
--mxfp4-layers moe,qkv,o,lm_head \
|
|
--attention-backend FLASHINFER \
|
|
--kv-cache-dtype fp8 \
|
|
--max-num-batched-tokens {max_num_batched_tokens} \
|
|
--host {host} \
|
|
--port {port}
|