model: Qwen/Qwen3-8B
gpu-memory-utilization: 0.95
max-model-len: 8192
dtype: auto
trust-remote-code: true
quantization: fp8
kv-cache-dtype: fp8
enforce-eager: false
enable-prefix-caching: true
speculative-config: '{"model":"RedHatAI/Qwen3-8B-speculator.eagle3","method":"eagle3","num_speculative_tokens":3}'