Posts
All the articles I've posted.
Why Numeric Responses Alone Fall Short for Function Calling in LLMs
Published: at 04:33 PMWhy Numeric Responses Alone Fall Short for Function Calling in LLMs
TensorRT LLM first impressions
Published: at 02:22 PMLearnings from building a TensorRT engine for serving Llama-3 on a RTX 4090.