LLamaRecipes/tools/benchmarks/inference/cloud/azure/parameters.json

{
    "MAX_NEW_TOKEN" : 256,
    "CONCURRENT_LEVELS" : [1, 2, 4, 8, 16, 32, 64],
    "THRESHOLD_TPS" : 7,
    "MODEL_PATH" : "meta-llama/your-model-path",
    "RANDOM_PROMPT_LENGTH" : 25,
    "TEMPERATURE" : 0.6,
    "TOP_P" : 0.9,
    "MODEL_ENDPOINTS" : "https://your-endpoint.inference.ai.azure.com/v1/chat/completions",
    "API_KEY" : "your-auth-key",
    "SYS_PROMPT" : "You are a helpful assistant."
}