v0.1.2-beta

Hey guys, this is our first release since we launched Unsloth Studio last week. From now on you can directly access all our updates through our changelog here: https://unsloth.ai/docs/new/changelog

**You can now update Unsloth Studio!** Just use: `unsloth studio update`. Please update to use all the newest fixes and features.

* **Tool calling improved.** Better llama.cpp parsing, no raw tool markup in chat, faster inference, a new Tool Outputs panel, timers.
* **Windows** CPU or GPU now works seamlessly. Please reinstall!
* **App shortcuts**. Once installed, you can now launch in Windows, MacOS and Linux via a shortcut icon in the Start / Launch and Desktop.
* **Pre-compiled** `llama.cpp` **binaries** and `mamba_ssm` for finetuning - 6x faster installs! Also <300MB in size for binaries.
* **50% reduced installation sizes** (-7GB or more savings), 2x faster installs and faster resolving. 50% smaller pypi sizes.
* **Colab** with free T4 GPUs with Unsloth Studio now fixed! [Try it here](https://colab.research.google.com/github/unslothai/unsloth/blob/main/studio/Unsloth_Studio_Colab.ipynb). Due to pre-compiled binaries, it's also 20x faster!
* You can now properly use **old GGUFs** from Hugging Face or LM Studio
* MacOS and CPU now have Data Recipes enabled with multi-file uploading.
* **AMD support preliminary for Linux** only machines - auto detects.
* **Settings sidebar redesign.** Settings are now grouped into **Model, Sampling, Tools, and Preferences**
* **Context length** now adjustable. Keep in mind this is not needed as llama.cpp smartly uses the exact context you need via `--fit on`
* **Persistent system prompts and presets.** Custom system prompts and chat presets now persist across reloads and page changes.
* **Multi-file upload.** Data recipes now support multiple drag-and-drop uploads for PDF, DOCX, TXT, and MD, with backend extraction, saved uploads, and improved previews.
* **Better chat observability.** Studio now shows `llama-server` timings and usage, a context-window usage bar, and richer source hover cards.
* **Better UX overall** \- clickable links, better LaTeX parsing, tool / code / web tooltips for default cards and much more!
* **LiteLLM -** Unsloth Studio and Unsloth were **NOT** affected by the recent LiteLLM compromise. Nemo Data Designer used LiteLLM only up to `1.80`, not the affected `1.82.7` or `1.82.8`, and has since removed it entirely.
* We now have a new one line install command, just run:  Copy`curl -fsSL` [`https://unsloth.ai/install.sh`](https://unsloth.ai/install.sh) `| sh`

### Fixes:
* **Windows/setup improvements.** Fixed silent Windows exits, Anaconda/conda-forge startup crashes, broken non-NVIDIA Windows installs, and missing early CUDA/stale-venv setup checks.
* **System prompts fixed.** They work again for non-GGUF text and vision inference.
* **GGUF export expanded.** Full fine-tunes, not just LoRA/PEFT, can now export to GGUF. Base model resolution is more reliable, and unsupported export options are disabled in the UI.
* **Chat scroll/layout fixes.** Fixed scroll-position issues during generation, thinking-panel layout shift, and viewport jumps when collapsing reasoning panels.
* **Smarter port conflict detection.** Studio now detects loopback conflicts, can identify the blocking process when possible, and gives clearer fallback-port messages.

Example of automatic parameter settings for context length etc:

https://github.com/user-attachments/assets/6a70a680-fccd-4d50-ad47-eb45d6827a06

## What's Changed
* [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in https://github.com/unslothai/unsloth/pull/4542
* fix: store embedding_learning_rate on self in UnslothTrainingArguments by @GoldenGrapeGentleman in https://github.com/unslothai/unsloth/pull/4531
* studio: persist system prompt and preset settings across navigation by @Imagineer99 in https://github.com/unslothai/unsloth/pull/4538
* studio: stop scroll hijack during generation and fix thinking panel layout shift by @Imagineer99 in https://github.com/unslothai/unsloth/pull/4543
* Fix Studio port conflict detection for loopback addresses by @danielhanchen in https://github.com/unslothai/unsloth/pull/4532
* fix(studio): show Windows-specific reset-password command by @Shine1i in https://github.com/unslothai/unsloth/pull/4529
* fix(studio): restore scroll lock on reasoning panel collapse by @danielhanchen in https://github.com/unslothai/unsloth/pull/4545
* fix: always show chat tool icons by @Shine1i in https://github.com/unslothai/unsloth/pull/4525
* fix: system prompt ignored in unsloth inference by @Shine1i in https://github.com/unslothai/unsloth/pull/4528
* fix: handle prompt/completion datasets in slow-path BOS detection by @danielhanchen in https://github.com/unslothai/unsloth/pull/4548
* fix: give @0xKushwaha git history credit for completion_only_loss fix by @danielhanchen in https://github.com/unslothai/unsloth/pull/4552
* ⚠️Remove quarantined `litellm` for precaution -- Unsloth Studio **NOT** affected by @danielhanchen in https://github.com/unslothai/unsloth/pull/4553
* fix: pin unsloth>=2026.3.11 in install scripts by @danielhanchen in https://github.com/unslothai/unsloth/pull/4556
* Regroup chat settings sidebar into focused sections by @Shine1i in https://github.com/unslothai/unsloth/pull/4551
* Add GRPO resume vLLM cleanup guard by @MagellaX in https://github.com/unslothai/unsloth/pull/4411
* fix: prevent UnicodeEncodeError on Windows CP1252 consoles in studio setup by @Krishnachaitanyakc in https://github.com/unslothai/unsloth/pull/4563
* studio: windows desktop shortcut launcher  by @Imagineer99 in https://github.com/unslothai/unsloth/pull/4558
* Remove duplicate frontend assets from wheel (~31 MB savings) by @danielhanchen in https://github.com/unslothai/unsloth/pull/4567
* feat(studio): training history persistence and past runs viewer by @Shine1i in https://github.com/unslothai/unsloth/pull/4501
* fix: remove auto wandb.finish() after train() to allow post-training evaluate() by @Krishnachaitanyakc in https://github.com/unslothai/unsloth/pull/4564
* feat: Implement Q-GaLore optimizer and custom embedding learning rate… by @OnePunchMonk in https://github.com/unslothai/unsloth/pull/4511
* Bump Data Designer to 0.5.4 (removes litellm dependency) by @danielhanchen in https://github.com/unslothai/unsloth/pull/4569
* feat(chat): cleaner tool UI, inline LaTeX, clickable links by @Shine1i in https://github.com/unslothai/unsloth/pull/4561
* [Studio] Try installing causal-conv1d from prebuilt wheels if avialable by @Datta0 in https://github.com/unslothai/unsloth/pull/4547
* Feature/add dependabot and codeql security checks by @pkloehn1 in https://github.com/unslothai/unsloth/pull/4479
* build(deps): bump the actions group with 2 updates by @dependabot[bot] in https://github.com/unslothai/unsloth/pull/4570
* build(deps): bump oxc-parser from 0.116.0 to 0.121.0 in /studio/backend/core/data_recipe/oxc-validator in the npm-oxc-validator group by @dependabot[bot] in https://github.com/unslothai/unsloth/pull/4571
* Remove advanced CodeQL workflow (conflicts with default setup) by @danielhanchen in https://github.com/unslothai/unsloth/pull/4584
* Add macOS and Linux desktop shortcuts to install.sh by @danielhanchen in https://github.com/unslothai/unsloth/pull/4568
* perf(studio): upgrade to Vite 8 + auto-install bun for faster frontend builds by @Etherll in https://github.com/unslothai/unsloth/pull/4522
* feat(tokenizer): add get_tokenizer_info() diagnostic helper by @cz-03 in https://github.com/unslothai/unsloth/pull/4436
* Add ROCm (AMD GPU) support to studio setup by @danielhanchen in https://github.com/unslothai/unsloth/pull/4585
* Consolidate dual venvs and separate install from update by @rolandtannous in https://github.com/unslothai/unsloth/pull/4530
* studio: stabilize reasoning panel scroll behavior and prevent composer overlap by @Imagineer99 in https://github.com/unslothai/unsloth/pull/4587
* Use prebuilt llama.cpp for unsloth studio setup by @mmathew23 in https://github.com/unslothai/unsloth/pull/4562
* fix(studio): add -ngl flag for GPU offloading in llama-server by @danielhanchen in https://github.com/unslothai/unsloth/pull/4588
* fix(studio): add pip nvidia CUDA libs to LD_LIBRARY_PATH for llama-server by @danielhanchen in https://github.com/unslothai/unsloth/pull/4590
* fix(studio): validate bun install and retry from official source on failure by @danielhanchen in https://github.com/unslothai/unsloth/pull/4589
* fix(studio): clear bun cache on failure and retry before falling back to npm by @danielhanchen in https://github.com/unslothai/unsloth/pull/4594
* Pin torch>=2.4,<2.11.0 in Studio installers by @danielhanchen in https://github.com/unslothai/unsloth/pull/4595
* fix(studio): source-build fallback prefers Unsloth's tested tag over upstream latest by @danielhanchen in https://github.com/unslothai/unsloth/pull/4593
* fix(studio): add bun cache validation to Windows setup.ps1 by @danielhanchen in https://github.com/unslothai/unsloth/pull/4596
* feat: multi-source model discovery (HF default, legacy cache, LM Studio) by @rolandtannous in https://github.com/unslothai/unsloth/pull/4591
* Add unsloth to User PATH on Windows after install by @danielhanchen in https://github.com/unslothai/unsloth/pull/4597
* Add PID file tracking and `unsloth studio stop` command by @danielhanchen in https://github.com/unslothai/unsloth/pull/4598
* feat(studio): editable context length with Apply/Reset for GGUF settings by @danielhanchen in https://github.com/unslothai/unsloth/pull/4592

## New Contributors
* @MagellaX made their first contribution in https://github.com/unslothai/unsloth/pull/4411
* @Krishnachaitanyakc made their first contribution in https://github.com/unslothai/unsloth/pull/4563
* @OnePunchMonk made their first contribution in https://github.com/unslothai/unsloth/pull/4511
* @pkloehn1 made their first contribution in https://github.com/unslothai/unsloth/pull/4479
* @dependabot[bot] made their first contribution in https://github.com/unslothai/unsloth/pull/4570
* @cz-03 made their first contribution in https://github.com/unslothai/unsloth/pull/4436

**Full Changelog**: https://github.com/unslothai/unsloth/compare/b8475...v0.1.2-beta