Soup
via star
Docker
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Plugins Filament, pacotes Laravel e starter kits open source mantidos ativamente. Tudo MIT, com releases para v3, v4 e v5 quando aplicável.
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Giant MoE models on a single consumer GPU by streaming experts from SSD. CUDA fork of antirez/ds4: runs GLM-5.2 (743B), Tencent Hy3 (295B), and DeepSeek 4 Flash, with io_uring expert streaming, LFU host cache, cross-layer expert prefetch, and the first MTP speculative decoding for GLM-5.2.
Todos os pacotes têm CI, testes Pest e issues abertas marcadas com good first issue.
Nova versão disponível.