AI Briefing#intel-gaudi
The latest AI and developer news about #intel-gaudi, with the original source and a short summary.
The latest AI and developer news about #intel-gaudi, with the original source and a short summary.
HuggingFace's LLM serving solution TGI now natively supports Intel Gaudi hardware.
Intel Gaudi now supports Speculative Sampling-based Assisted Generation, boosting LLM inference speed by up to 2x.
This introduces how to use a text generation pipeline based on Optimum Habana to efficiently run Llama 2 models on Intel Gaudi 2 accelerators.