Chip Makers Resources

NVIDIA designs GPU accelerators and full-stack AI platforms for data center AI training, inference, HPC, robotics, and enterprise AI workloads.

AMD builds Instinct accelerators, EPYC CPUs, ROCm software, and heterogeneous compute platforms for AI and HPC.

Groq develops LPU inference systems focused on deterministic low-latency serving for large language models.

Hopper-generation data center GPU widely used for AI training, inference, and HPC workloads.

Hopper refresh with larger HBM3e memory footprint for memory-bound inference and training tasks.

AMD data center accelerator with high HBM capacity for large model training and inference.