NIR: Nim Intermediate Representation(github.com)

173 points by michaelsbradley 3 years ago | 63 comments

AI has a deep understanding of how this code works(github.com)

212 points by theresistor 11 months ago | 93 comments

Llama.cpp: Full CUDA GPU Acceleration(github.com)

640 points by gzer0 3 years ago | 265 comments

A draft GitHub pull request to llama.cpp adding full CUDA GPU acceleration for all ggml tensors, including storing the KV cache in VRAM.

ONNX Runtime merges WebGPU backend(github.com)

165 points by b_mc2 3 years ago | 30 comments

Java Panama Vector API Integrated with Apache Lucene(github.com)

67 points by kurhan 3 years ago | 12 comments

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy(github.com)

368 points by weinzierl 2 years ago | 72 comments

GitHub pull request to llama.cpp by jart that upstreams llamafile's vectorized expf() functions to compute SiLU and softmax faster and more accurately on CPU.