Optimum Nvidia Mistral, Memory support, qualitative comparision and improvements

premAI-io / benchmarks

🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.

MIT License

130 stars 5 forks source link

Optimum Nvidia Mistral, Memory support, qualitative comparision and improvements #177

Closed Anindyadeep closed 5 months ago

Anindyadeep commented 5 months ago

This PR introduces all the changes by PR https://github.com/premAI-io/benchmarks/pull/167 and integrates those in Optimum Nvidia. Optimum Nvidia README now has quality checks table for both Llama 2 Chat and Mistral Instruct.

Note this PR depends on: #175

So first PR #175 needs to be merged then this one