๊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 ๏ฃฟ | building | | Thoughts are my own.
๊ฐ€์ž… October 2014
482 ํŒ”๋กœ์ž‰ ์ค‘    13.7K ํŒฌ
TensorFold 1.2.5 is out. ๐Ÿš€ This release brings: โ€ข TensorFold Web, a local browser app for chat, models, learning, benchmarks and more. โ€ข LFM2.5-24B-A2B on CUDA. โ€ข Nemotron Parse and LightOnOCR-3 on HIP. โ€ข Clef's joint schema head on CUDA. Qwen3.8-27B MLX 8-bit on M5 Ultra also gets faster. In the measured test, cold prompts were 18% faster and decode 7.6% faster, with the same tokens and prompt state. There's lower memory use for Qwen CUDA streams, better conversation-cache handling and a fix for PDF rendering crashes on macOS too. A massive thank you to everyone contributing code, testing builds and reporting problems. These releases take a lot of work, and I really appreciate the time people put into them. @Bizuayeu @devopsfortunato @unigilby @teleogen @dubsthedev @kalin_swiss @Q4_K_M And on GitHub: AbrahamCete, gordonhatusupy, jschmied, mrv777 and yguanrong. Special credit to Stephane on GitHub for TensorFold Studio, which TensorFold Web builds on. @volatilemarkts @plotarmordev @MiaAI_lab @petruspennanen
๋” ๋ณด๊ธฐ