Focused on building optmized inference for large language models and minimizing cost per token. Creating tools for developers. Currently working on LLmHub.dev
Beyond Work
Solo-Synth-GAN
A novel zero-shot learning model generating videos from images
LLMhub.dev
Platform optimizing large language model deployment, significantly reducing inference latency by 300ms and costs by $0.05 per API call.
How I spend time
Something to remember
Barter System
Feel free to ping me at prateekjannu@gmail.com