The RAM shortage could last years
theverge.com
The RAM shortage could last years
1–10 of 536 posts
Re: The RAM shortage could last years
#2Re: The RAM shortage could last years
#3Given that TurboQuant results in a 6x reduction in memory usage for KV caches and up to 8x boost in speed, this optimization is already showing up in llama.cpp, enabling significantly bigger contexts without having to run a smaller model to fit it all in memory.
Some people thought it might significantly improve the RAM situation, though I remain a bit skeptical - the demand is probably still larger than the reduction turboquant brings.
Re: The RAM shortage could last years
#4can't read the article due to a paywall.
Re: The RAM shortage could last years
#5Re: The RAM shortage could last years
#6can't read the article due to a paywall.
Re: The RAM shortage could last years
#7I'm a bit surprised the article makes no mention of Google's TurboQuant[0] introduced 26 days prior. Given that TurboQuant results in a 6x reduction in memory usage for KV caches and up to 8x boost in speed, this optimization is already showing up in llama.cpp, enabling significantly bigger contexts without having to run a smaller model to fit it all in memory. Some people thought it might significantly improve the R…
Re: The RAM shortage could last years
#8I'm a bit surprised the article makes no mention of Google's TurboQuant[0] introduced 26 days prior. Given that TurboQuant results in a 6x reduction in memory usage for KV caches and up to 8x boost in speed, this optimization is already showing up in llama.cpp, enabling significantly bigger contexts without having to run a smaller model to fit it all in memory. Some people thought it might significantly improve the R…
Re: The RAM shortage could last years
#9The era of optimisation is finally here. I'm excited.