Projects
Showcase your projects with a hero image (16 x 9)
Text Generation Inference (TGI)
Production-ready inference server for Large Language Models. I work on optimization and multi-backend support, including Intel Gaudi integration, to make LLM deployment fast and efficient.
Learn more →
TGI on Intel Gaudi
Native Intel Gaudi hardware support integrated directly into TGI, enabling diverse deployment options for LLMs with optimized performance on specialized AI accelerators.
Learn more →