vllm.benchmarks
Modules:
Name | Description |
---|---|
datasets |
This module defines a framework for sampling benchmark requests from various |
endpoint_request_func |
The request function for API endpoints. |
latency |
Benchmark the latency of processing a single batch of requests. |
serve |
Benchmark online serving throughput. |
throughput |
Benchmark offline inference throughput. |
utils |
|