Видео ютуба по тегу Ik_Llama.cpp

ikawrakow/ik_llama.cpp - Gource visualisation
ikawrakow/ik_llama.cpp - Gource visualisation
The Fastest Local Long-Context LLM Engine - Breaking 150 tk/s Prefill Barrier on Large MoE models
The Fastest Local Long-Context LLM Engine - Breaking 150 tk/s Prefill Barrier on Large MoE models
How I Tamed 2 × RTX 5090 + 2 × 4090 with Llama.cpp fork
How I Tamed 2 × RTX 5090 + 2 × 4090 with Llama.cpp fork
GitHub - ikawrakow/ik_llama.cpp: llama.cpp fork with additional SOTA quants and improved performance
GitHub - ikawrakow/ik_llama.cpp: llama.cpp fork with additional SOTA quants and improved performance