TensorFold 1.2.10 is out đ
Qwen3.8-27B decodes 57% faster on a GB10 at 8 streams with a shared 32K prefix, with the same replies in that test. DeepSeek-V4.1 cold prompts are 5â7% faster on an M5 Ultra.
We also shipped background responses, tensorfold launch and tensorfold rm, plus Qwen3-Embedding and Unlimited-OCR-2 on Metal.
Additionally squashed a few bugs and issues.
Massive thanks to everyone who wrote code, ran tests on their hardware and reported bugs.
@AIFlow_ML @Bizuayeu @codengod @devopsfortunato @EugineAi @unigilby @jayleaton @teleogen @niklaslenz_ai @plotarmordev @woolsey @petruspennanen, and on GitHub AbrahamCete, akol1, BadAd84, BobClawblaw, currencycaver29, cwschroeder, dinadur, drowzeys, garvrao80, ilya-bogin-keenable, jschmied, Mirrdhyn, robertosantosx2, srh3877, sx4im and tacosta. I really appreciate the time you all put into this.
@petruspennanen @volatilemarkts @MiaAI_lab @plotarmordev @jayleaton @tensorfold_dev