# Recipe: Qwen3.5-397B-A17B-INT4-Autoround
# Qwen3.5-397B model in Intel INT4-Autoround quantization, TP=4 across 4 DGX Spark nodes
# Benchmarked at 37 tok/s single-user, 103 tok/s aggregate (4 concurrent) on 4× DGX Spark
# Requires NVIDIA driver 580.x (590.x has CUDAGraph deadlock bug on GB10)

recipe_version: "1"
name: Qwen3.5-397B-INT4-Autoround
description: Qwen3.5-397B with TP=4 across 4 DGX Spark nodes (Marlin fix applied)

# HuggingFace model to download (optional, for --download-model)
model: Intel/Qwen3.5-397B-A17B-int4-AutoRound

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

build_args:
  - --tf5

# Mods required: coder-next tool/reasoning parser + Marlin TP fix
mods:
  - mods/fix-qwen3-coder-next
  - mods/fix-qwen35-tp4-marlin

# Environment variables
env:
  VLLM_MARLIN_USE_ATOMIC_ADD: 1

# Default settings (can be overridden via CLI, e.g. --tensor_parallel 2)
defaults:
  port: 8000
  host: 0.0.0.0
  tensor_parallel: 4
  gpu_memory_utilization: 0.78
  max_model_len: 32768
  max_num_batched_tokens: 8192

# The vLLM serve command template
command: |
  vllm serve Intel/Qwen3.5-397B-A17B-int4-AutoRound \
    --tool-call-parser qwen3_coder \
    --reasoning-parser qwen3 \
    --enable-auto-tool-choice \
    --tensor-parallel-size {tensor_parallel} \
    --distributed-executor-backend ray \
    --kv-cache-dtype fp8 \
    --gpu-memory-utilization {gpu_memory_utilization} \
    --max-model-len {max_model_len} \
    --max-num-batched-tokens {max_num_batched_tokens} \
    --enable-prefix-caching \
    --trust-remote-code \
    --host {host} \
    --port {port}