Skip to content

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

Commits on main

9dd4977
Count the final EOS token within the raw-text chunk budget (#11040)
Vineeth Sai Varikuntla committed 1 month ago
a809a51
Update _version.py
Daniel Han committed 1 month ago
1b58838
Collapse the llama.cpp install branch that never branched (#10268)
Vineeth Sai Varikuntla committed 1 month ago
1efc294
Keep the GRPO eval batch a multiple of num_generations (#12362)
Vineeth Sai Varikuntla committed 1 month ago
1f65728
Make the registry's default quant_type usable (#9887)
Vineeth Sai Varikuntla committed 1 month ago
11de7e7
9cf98aa
Update pyproject.toml
Daniel Han committed 1 month ago
befa974
Update _version.py
Daniel Han committed 1 month ago
ef30cfb