Lilac
@LilacML
(YC S25) Lilac serves fast model inference on idle GPUs.
๊ฐ์
August 2025
18 ํ๋ก์ ์ค 123 ํฌ
Our GLM 5.1 endpoint is averaging 70 TPS under full-load right now ๐ Thanks to everyone using it!
์ธ๊ธฐ ์๋ ์ฌ์ฉ์
