Morph MORPH
SIGN IN SIGN UP
unslothai / unsloth UNCLAIMED

Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.

0 0 98 Python

COMMITS

main
May 31, 2026
D
Studio: stop hidden source badges from inflating chat scroll height (#5822)
Daniel Han committed
b66d35b
D
Studio: harden stdio MCP gating and fix transport edge cases (#5892)
Daniel Han committed
4b6a733
D
Studio: clearer error for diffusion GGUFs loaded as chat models (#5857)
Daniel Han committed
6cc2220
O
studio/frontend: fix MCP dialog overflow on long URLs (#5864)
oobabooga committed
76574fb
O
Studio: add stdio MCP server support (#5863)
oobabooga committed
ff00fdd
D
ci(security-audit): make package installs network-resilient (#5853)
Daniel Han committed
f213663
T
Remove dead top-level bitsandbytes import from models/_utils.py (#5875)
Trishanu Das committed
a2d77fb
D
studio: make NVIDIA prebuilt selection track CUDA version bumps (Windows + Linux) (#5879)
Daniel Han committed
5076837
D
studio: pick a macOS llama.cpp prebuilt that loads on the host OS (#5883)
Daniel Han committed
366937d
M
Update Studio sidebar logout icon to logout-05 (#5878)
Michael Han committed
1016fff
S
Fix error when context-resizing (#5860)
Suyadi committed
87ee06a
O
fix: bump openssl, rand, rustls-webpki, tar in Studio src-tauri for security advisories (#5866)
OrbisAI Security committed
109a666
M
fix: wrong code block language for nightly Windows install (#5877)
mervivian committed
faea796
May 30, 2026
D
studio: ROCm cleanups follow-up to #5301 (#5874)
Daniel Han committed
8ec9a74
L
feature/use lemonade-sdk llamacpp-rocm binaries (#5303)
Leo Borcherding committed
61df3aa
J
Version downpairing for Radeon+ROCm PyTorch wheels (#5353)
Jaeic Lee committed
187c81f
L
fix/strix halo and windows AMD ROCm support (#5301)
Leo Borcherding committed
b6d5636
May 29, 2026
D
studio/setup.sh: cope with fresh CUDA toolkits like 13.3 (#5826)
Daniel Han committed
a3a0cb1
R
Studio: keep web search/code pills off on model load if user disabled them (#5851)
Roland Tannous committed
db5a988
L
Fix/studio colab proxy and iframe - Unsloth Studio not loading in Colab (iframe "refused to connect" and wrong URL) (#5844)
Leo Borcherding committed
ee66951
May 28, 2026
A
Fix non-streaming GGUF chat completion usage (#5781)
alkinun committed
185ff00
M
fix: honor --ctx-size and other forwarded args from `unsloth studio run` in Studio's context-fit logic (#5815)
Matt Van Horn committed
15d70a1
May 27, 2026
L
Studio: remove dark mode upload circle (#5813)
Lee Jackson committed
99e1f67
D
Detect CUDA UMD Version from newer nvidia-smi output (fixes #5812) (#5817)
Daniel Han committed
a62eb80
D
Clear MRoPE after generation for GRPO (#5683)
Datta Nimmaturi committed
015fa57
N
Studio: add remote MCP server support (#5750)
Nilay committed
9a907a8
D
Studio: add Gemini provider with web_search, code_execution, prompt caching, and Nano Banana image generation (#5720)
Daniel Han committed
ab48465
D
[RL] make sync weights conditional (#4925)
Datta Nimmaturi committed
8839118
D
Trim README Advanced launch options blurb (#5809)
Daniel Han committed
131fa4f
A
Studio: add configurable CPU thread pool limit (#5760)
alkinun committed
9222ffd