LLaMA Jobs

I'm in need of an expert to help me enhance the performance of my RAG assistant on my local PC. The assistant currently handles generative AI, specifically text generation, but I'm facing significant issues with its inference speed. Key Tasks: - Analyze the current setup and identify bottlenecks that are affecting the performance, especially the inference speed of the RAG assistant. - Suggest and implement optimizations that will improve the inference speed without compromising the quality of the text generation. - Test the enhancements thoroughly to ensure they are effective and reliable. Ideal Skills and Experience: - Proficiency in generative AI, particularly text generation, is a must. - Extensive experience in optimizing inference speed for generative AI models. - Strong b...