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.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
Commits on main
[pre-commit.ci] auto fixes from pre-commit.com hooks
70299d8 pre-commit-ci[bot] committed 2 months ago
Studio: pin both platform probes in the run re-exec test fixture
4b74b8f Daniel Han committed 2 months ago
Studio: stop the CLI gate undoing what the backend gate decided
b490f99 danielhanchen committed 2 months ago
[pre-commit.ci] auto fixes from pre-commit.com hooks
f693b6a pre-commit-ci[bot] committed 2 months ago
Studio: tell the operator what the refusal path will actually do
ad69044 danielhanchen committed 2 months ago
Studio: do not let the raw-bind prompt block a launch nobody is watching
178a73a danielhanchen committed 2 months ago
[pre-commit.ci] auto fixes from pre-commit.com hooks
a4296af pre-commit-ci[bot] committed 2 months ago
Studio: gate concrete non-loopback binds, and never block a launch that worked
605c7c2 danielhanchen committed 2 months ago
[pre-commit.ci] auto fixes from pre-commit.com hooks
a020246 pre-commit-ci[bot] committed 2 months ago
Studio: ask for a password on a raw `-H 0.0.0.0` bind too
70127b2 danielhanchen committed 2 months ago
docs: improve documentation on exporting models from Colab (#4247)
3b876a2 Sagar Gupta committed 8 months ago
Add Qwen3-Omni Support with Optimized MTP Fine-Tuning (#4235)
f0a40b0 AlanPonnachan committed 10 months ago
Fix Windows setup access-denied on existing llama-server ACLs (#4881)
8c101fd Mithilesh Kumar committed 2 months ago
Add persistent wiki-RAG pipeline with vendored Graphify, lint-driven enr (#5103)
faee9ee Zohair Shafi committed 2 months ago
fix: private dataset splits/metadata not loading in Studio UI (#4965)
9c67d53 shivam johri committed 2 months ago
Refactor setup.sh into modular functions and restructure main execution (#5408)
aa10547 xerrni committed 2 months ago
Scan release bundles for potentially unwanted applications too (#10478)
b3f1fd8 Daniel Han committed 2 months ago
Studio: harden the codec-audio eval config added in #10259 (#10477)
20d3451 Daniel Han committed 2 months ago
Assert the release publishing path uploads the wheel only (#10419)
edda486 Daniel Han committed 2 months ago
Recognise Windows code integrity blocks, and require the runtime we ship (#10404)
9ee3224 Daniel Han committed 2 months ago
Studio: show mlx-community models as MLX in the model picker (#10457)
a37dea7 Nilay committed 2 months ago
Studio: make the Min P and Repetition Penalty sliders work (#10456)
19f283a Nilay committed 2 months ago
fix(tokenizer): enable add_bos_token for Gemma 4 base models (#10312)
30529a6 Sourav Rajvi committed 2 months ago