Raullen Chai

Improve vllm-mlx performance through research, small experiments, and benchmarks on real models. The skill records results, keeps changes that improve measured performance, and carries successful work through implementation, testing, review, and pull request creation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing the time before a model starts responding
• Improving token generation speed
• Exploring memory and cache optimizations