All news

2 articles

Min score

paperarXiv (systems, data, ML)·22 Oct 20264.3
Evaluating the Applicability of LLM Inference Optimizations on Apple Silicon
Tests which LLM inference optimizations designed for NVIDIA GPUs actually help on Apple Silicon.
llm-inference performance-optimization apple-silicon
blogHugging Face Blog·20 Oct 20263.5
MPS in PyTorch 2.15
PyTorch 2.15 brings FP8 and faster decoding kernels to the Apple MPS backend.
llm-inference apple-silicon