Benchmark
==================

执行Benchmark
^^^^^^^^^^^^^

.. code-block:: shell

   find /usr/local/lib/python3.11/site-packages/mindie* -name *config.json |xargs chmod -R 640

   # 开启日志打屏，关闭时日志默认保存在~/mindie/log/debug/mindie-benchmarkxxxxx.log
   export MINDIE_LOG_TO_STDOUT="benchmark:1; client:0"

   benchmark --DatasetType synthetic --ModelName deepseek-r1-qwen-32b --ModelPath /data/llm_models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --TestType vllm_client --Http http://127.0.0.1:1025 --ManagementHttp http://127.0.0.1:1026 --Concurrency 10 --TaskKind stream --MaxOutputLen 512 --Tokenizer True

结果解析
^^^^^^^^

.. code-block:: python

   GeneratedTokenSpeed = GeneratedTokens / GenerateTime
   Throughput = RequestCount / TimeElapsed
   OutputGenerateSpeed = GeneratedTokens * RequestCount / TimeElapsed
   InputGenerateSpeed = InputTokens * RequestCount / TimeElapsed
   TotalGenerateSpeed = OutputGenerateSpeed + InputGenerateSpeed
   GenerateSpeedPerClient = OutputGenerateSpeed / Concurrency