# Recipe: Qwen3.5-122B-A10B-FP8
# Qwen3.5-122B model in native FP8 quantization

recipe_version: "1"
name: Qwen3.5-122B-FP8
description: vLLM serving Qwen3.5-122B-FP8

# HuggingFace model to download (optional, for --download-model)
model: Qwen/Qwen3.5-122B-A10B-FP8

# Only cluster is supported
cluster_only: true

# Container image to use
container: vllm-node

# No mods required
mods:
  - mods/fix-qwen3.5-chat-template

# 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: 262144
  max_num_batched_tokens: 8192

# Environment variables
env: {}

# The vLLM serve command template
command: |
  vllm serve Qwen/Qwen3.5-122B-A10B-FP8 \
    --max-model-len {max_model_len} \
    --gpu-memory-utilization {gpu_memory_utilization} \
    --port {port} \
    --host {host} \
    --load-format fastsafetensors \
    --enable-prefix-caching \
    --enable-auto-tool-choice \
    --tool-call-parser qwen3_coder \
    --reasoning-parser qwen3 \
    --chat-template unsloth.jinja \
    -tp {tensor_parallel} --distributed-executor-backend ray \
    --max-num-batched-tokens {max_num_batched_tokens}