# Recipe: Qwen3.5-397B-A17B-FP8
# Qwen3.5-397B-A17B model in FP8 precision
# Multi-modal input

recipe_version: "1"
name: Qwen3.5-397B-A17B-FP8
description: vLLM serving Qwen3.5-397B-A17B-FP8

# HuggingFace model to download (optional, for --download-model)
model: Qwen/Qwen3.5-397B-A17B-FP8

#solo_only: true

# Container image to use
container: vllm-node-tf5

build_args:
  - --tf5
  - --rebuild-flashinfer
  - --rebuild-vllm

# Mod required to fix ROPE syntax error
mods:
  - mods/fix-qwen3.5-autoround

# Default settings (can be overridden via CLI)
defaults:
  port: 8000
  host: 0.0.0.0
  tensor_parallel: 4
  gpu_memory_utilization: 0.85
  max_model_len: 262144
  max_num_batched_tokens: 8192

# Environment variables
env: 
  VLLM_USE_DEEP_GEMM: 0
  VLLM_USE_FLASHINFER_MOE_FP16: 1
  VLLM_USE_FLASHINFER_SAMPLER: 0
  OMP_NUM_THREADS: 4

# The vLLM serve command template
command: |
  vllm serve Qwen/Qwen3.5-397B-A17B-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 \
    --max-num-batched-tokens {max_num_batched_tokens} \
    --trust-remote-code \
    -tp {tensor_parallel} \
    --distributed-executor-backend ray \
    --mm-encoder-tp-mode data \
    --kv-cache-dtype fp8 \
    --compilation-config.cudagraph_mode none \
    --max-num-seqs 32 \
    --attention-backend flashinfer