https://github.com/theodoreniu/llmperf
Benchmarking tool for stress testing self-hosted LLMs, Azure OpenAI, and OpenAI APIs. Measure latency, throughput, and optimize performance. 🚀
https://github.com/theodoreniu/llmperf
azure benchmarking deepseek latency llm openai qps test tps
Last synced: 2 months ago
JSON representation
Benchmarking tool for stress testing self-hosted LLMs, Azure OpenAI, and OpenAI APIs. Measure latency, throughput, and optimize performance. 🚀
- Host: GitHub
- URL: https://github.com/theodoreniu/llmperf
- Owner: theodoreniu
- Created: 2025-01-16T05:35:43.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-10-16T12:29:31.000Z (8 months ago)
- Last Synced: 2025-11-14T22:12:25.625Z (7 months ago)
- Topics: azure, benchmarking, deepseek, latency, llm, openai, qps, test, tps
- Language: Python
- Homepage:
- Size: 6.35 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LLM Perf
`llmperf` is a benchmarking tool for stress testing self-hosted LLMs, Azure OpenAI, and OpenAI APIs. It provides efficient concurrent request management, detailed performance analysis, and helps developers optimize inference latency and throughput. With customizable test parameters, it is suitable for various LLM workload evaluation scenarios.
## 1. Configure your env
Copy and set up the environment variables from `.env.example`.
```bash
cp .env.example .env
```
## 2. Launch your App
Copy and set up the environment variables.
```bash
./start.sh
```