๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

netrunner
@plotarmordev
Cofounder & engineer. Running local AI, building things with it, and sharing what I learn.
๊ฐ€์ž… April 2022
675 ํŒ”๋กœ์ž‰ ์ค‘    7.1K ํŒฌ
The last update already beat what we promised for some setups, and more is coming! I'm testing the next one now: swap during model load will likely be lowered by over 90%, and long-prompt cache reuse will work better too. Results as soon as validation ends ๐Ÿ‘€
๋” ๋ณด๊ธฐ