cd/entity/Justine Tunney· home› entities› Justine Tunney
grep -l @justine tunney /news/*.json | wc -l → 1

Justine Tunney

mentions 1 type Person feed RSS

// recent coverage 1 mentions

21:38
2026-10-02
justine.lol
large-language-models

LLaMA Now Goes Faster on CPUs

Justine Tunney wrote 84 new matrix multiplication kernels for llamafile that make prompt evaluation 30% to 500% faster than llama.cpp on CPU with F16 and Q8_0 weights, according to benchmarks publishe…

// co-occurs with top 7 entities
llamafile 1 Mozilla 1 llama.cpp 1 Cosmopolitan Libc 1 Mistral 7b 1 TinyLlama 1.1B 1 Raspberry Pi 1
// topics top 4 topics
large language models 1 ai infrastructure 1 machine learning 1 developer tools 1