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

Ash Hart
@ashxhart
Doing my bit to bring local AI to everyone | building | | Thoughts are my own.
๊ฐ€์ž… October 2014
480 ํŒ”๋กœ์ž‰ ์ค‘    13.5K ํŒฌ
๐Ÿคฏ GLM-5.3-Flash 4bit on two M5 Ultras (tp=2) with TensorFold and 4x TB5 cables bonded. ๐Ÿš€ 114 tks decode on Prose single stream, and ~1600tks prefil. C=8 decode up to 200tps. There is headroom here as well, but this is where we landed today. A new-session TTFT with our prefix-cache lean mode is 0.06s. @digitalix Thanks for letting me use the M5Us!
๋” ๋ณด๊ธฐ