Iguana: fast SIMD-optimized decompression (sneller.io)

Screenshot of sneller.io: Iguana: fast SIMD-optimized decompression

First screen, captured 3 years ago.

Looks similar

Screenshot of elliotarledge.com: Batmobile: 10-20x Faster CUDA Kernels for Equivariant Graph Neural Networks

Batmobile: 10-20x Faster CUDA Kernels for Equivariant Graph Neural Networks (elliotarledge.com)

83 points by ipnon 9 months ago | 11 comments

Screenshot of wasmi-labs.github.io: Engineering of the fastest WebAssembly interpreters

Engineering of the fastest WebAssembly interpreters (wasmi-labs.github.io)

124 points by herobird 1 month ago | 15 comments

Screenshot of shraiwi.github.io: SIMD-accelerated computer vision on a $2 microcontroller

SIMD-accelerated computer vision on a $2 microcontroller (shraiwi.github.io)

281 points by shraiwi 2 years ago | 43 comments

Screenshot of justine.lol: LLaMA now goes faster on CPUs

LLaMA now goes faster on CPUs (justine.lol)

1286 points by lawrencechen 2 years ago | 413 comments

Justine Tunney's blog post describing 84 new matrix multiplication kernels that make llamafile prompt evaluation 30-500% faster on CPUs than llama.cpp.

llamafile llama-cpp matrix-multiplication cpu-inference

Screenshot of simdjson.org: The simdjson library

The simdjson library (simdjson.org)

52 points by fanf2 2 years ago | 22 comments

Screenshot of johnnysswlab.com: Decreasing the number of memory accesses

Decreasing the number of memory accesses (johnnysswlab.com)

73 points by g0xA52A2A 3 years ago | 43 comments

Looks similar

Batmobile: 10-20x Faster CUDA Kernels for Equivariant Graph Neural Networks(elliotarledge.com)

Engineering of the fastest WebAssembly interpreters(wasmi-labs.github.io)

SIMD-accelerated computer vision on a $2 microcontroller(shraiwi.github.io)

LLaMA now goes faster on CPUs(justine.lol)

The simdjson library(simdjson.org)

Decreasing the number of memory accesses(johnnysswlab.com)