Home » Inference

Intel® Gaudi® AI Accelerators Blog

/ Inference
We have optimized additional Large Language Models on Hugging Face using the Optimum Habana library.
With Habana’s SynapseAI 1.8.0 release support of DeepSpeed Inference, users can run inference on large language models, including BLOOM 176B.
Stay Informed: Register for the latest Intel Gaudi AI Accelerator developer news, events, training, and updates.