Free lessonsLLM Application Performance Testing
LLM Application Performance Testing
1 lessons
Lesson 1 · 6 min
Compare Ollama and vLLM with a Load Test
Experiment：Compare local LLM services across speed, concurrency, stability, and safety.
Open this lesson on Bilibili璟易智能Bilibili seriesThe lesson is in Chinese and plays from Bilibili.
Not translated yet — showing the Chinese originals.
About the series
Learn to performance-test LLM applications by comparing speed, concurrency, stability, and safety in Ollama and vLLM inference services.
- Who it is for
- Testers and AI engineers who need to validate latency, concurrency, and stability of LLM applications.
- What you can do afterwards
- Design a performance test around speed, concurrency, stability, and safety, and interpret measured differences between Ollama and vLLM.
Training a whole team? It is arranged by scope. Book an evaluation