Banghua Zhu
@BanghuaZ
You probably didn’t have Thinking Machines Lab dropping a 975B open model on your bingo card.
Inkling takes text, images, and audio as input, and it looks insanely strong.
SGLang already provides broad support for Inkling: PD disaggregation, multi-LoRA serving, HiCache, plus a
Inkling takes text, images, and audio as input, and it looks insanely strong.
SGLang already provides broad support for Inkling: PD disaggregation, multi-LoRA serving, HiCache, plus a
LMSYS Org@lmsysorg · Jul 15Inkling, @thinkymachines' first open model, dropped today: 975B total / 41B active MoE, up to 1M context, reasoning natively over text, images, and audio.
Serving and RL support are already live: you can run and shape it on an open stack, starting now.
Day 0 support on SGLang
Serving and RL support are already live: you can run and shape it on an open stack, starting now.
Day 0 support on SGLang
1:01 2 97