IBM UFCG

#llm

2026

• LLM Inference with Ollama on IBM Power9 Using CPU Apr 1

2025

• Evaluation of IBM Granite Models for Code-Generation Tasks on HumanEvalX Nov 28
• Computação@UFCG Leads Brazil’s Contributions to the HELM-Stanford Framework in Partnership with IBM Jul 9
• LLMs Inference API on IBM Power9 Server Jul 3
• Building an API for LLM inferences on IBM Power9 servers Jul 2
• Setting Up the Conda and PyTorch on IBM Power9 Servers Jun 30
• Setting Up the OS, NVIDIA Drivers, CUDA, and cuDNN on IBM Power 9 Servers Jun 29
• Evaluating Small-Scale LLMs (up to 8B) on PT-BR Benchmarks Jun 2
• Performing CPU Inference on Power10 Apr 6