# Recipe: Gemma4-26B-A4B
# Gemma4-26B-A4B model in online FP8 quantization

recipe_version: "1"
name: Gemma4-26B-A4B
description: vLLM serving Gemma4-26B-A4B

# HuggingFace model to download (optional, for --download-model)
model: google/gemma-4-26B-A4B-it

# Only cluster is supported
cluster_only: false
solo_only: false

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

build_args:
  - --tf5

# Mods
mods:
  - mods/fix-gemma4-tool-parser

# 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 google/gemma-4-26B-A4B-it  \
    --max-model-len {max_model_len} \
    --gpu-memory-utilization {gpu_memory_utilization} \
    --port {port} \
    --host {host} \
    --load-format instanttensor \
    --enable-prefix-caching \
    --enable-auto-tool-choice \
    --tool-call-parser gemma4 \
    --reasoning-parser gemma4 \
    --quantization fp8 \
    --kv-cache-dtype fp8 \
    --max-num-batched-tokens {max_num_batched_tokens} \
    -tp {tensor_parallel} --distributed-executor-backend ray