Description
Running LLMs on NVIDIA, AMD and Apple chips usually means different inference frameworks with different setups and performance. ZSE is an open source community-built LLM inference engine supporting NVIDIA GPUs, AMD ROCm and Apple Silicon.
It also supports fine-tuning, aiming for efficient inference across hardware.
Hardware:NVIDIA, AMD and Apple.
Efficient:Optimized inference.
Fine-tuning:Supported.
It also supports fine-tuning, aiming for efficient inference across hardware.
Features
Hardware:NVIDIA, AMD and Apple.
Efficient:Optimized inference.
Fine-tuning:Supported.
