For quite some time I had been submitting tasks to LLMs via llama-cli (natively) or llama-server (API), both from the excellent llama.cpp project. On CPU-only llama-cli starts fast and can restart from a checkpoint which has already parsed
For quite some time I had been submitting tasks to LLMs via llama-cli (natively) or llama-server (API), both from the excellent llama.cpp project. On CPU-only llama-cli starts fast and can restart from a checkpoint which has already parsed
I recently stumbled upon this llama.cpp fork which supports AMD Radeon Instinct MI50-32GB cards ("gfx906"). That made me discover this card, and notice that some of them were amazingly cheap, around $250 used. The 16GB variant is even cheap…
I recently stumbled upon this llama.cpp fork which supports AMD Radeon Instinct MI50-32GB cards ("gfx906"). That made me discover this card, and notice that some of them were amazingly cheap, around $250 used. The 16GB variant is even cheap…
All those who run a small infrastructure at home know this problem. It's Monday morning, while drinking your first coffee you're checking your e-mails, you find that you received surprisingly few during the night, and that the last one was
All those who run a small infrastructure at home know this problem. It's Monday morning, while drinking your first coffee you're checking your e-mails, you find that you received surprisingly few during the night, and that the last one was
In the previous synthetic comparison between ebtree and cebtree it was quite clear that performance varies quite a bit between key types, key distribution, lookup-to-update ratio, and tree type. While the initial utility was fine to get a r…
Tests were run on a single core of an Intel Core i7-6700K running at 4.4 GHz equipped with dual-channel DDR4-2400, using the "bench" utility from the "tests/" directory, comparing the performance of the two libraries at the following commit…
Tests were run on a single core of an Intel Core i7-6700K running at 4.4 GHz equipped with dual-channel DDR4-2400, using the "bench" utility from the "tests/" directory, comparing the performance of the two libraries at the following commit…
Those who often hear me discuss about my week-end projects have been accustomed to hearing about deuterium fusion (that's for another post), laser engraving, and the compact version of the ebtrees, aka compact elastic binary trees, without
Those who often hear me discuss about my week-end projects have been accustomed to hearing about deuterium fusion (that's for another post), laser engraving, and the compact version of the ebtrees, aka compact elastic binary trees, without
There are plenty of nice devices these days designed around ARMv8.2 SoCs such as RK3568 or variations around RK3588. Many of them have been using the HYM8563 I2C RTC chip for about a decade. This device is reasonably cheap, requires few com…