Download Latest Version
Release v0.3.0 source code.tar.gz (4.6 MB)
Get an email when there's a new version of Pruna AI
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2025-09-15 | 2.3 kB | |
| v0.2.10 source code.tar.gz | 2025-09-15 | 7.3 MB | |
| v0.2.10 source code.zip | 2025-09-15 | 7.5 MB | |
| Totals: 3 Items | 14.8 MB | 0 | |
The juiciest bits 🚀
feat: add unconstrained hyperparameter by @gsprochette in https://github.com/PrunaAI/pruna/pull/263
Introduces target modules, so you can pass custom configs while still keeping dependencies intact.
feat: new quantizer for vllm by @llcnt in https://github.com/PrunaAI/pruna/pull/239
Adds new config options (patch_for_inference,default_to_hf) so vLLM models play nicer with quantization workflows.
feat: add pre-smash-hook for model preparation by @simlang in https://github.com/PrunaAI/pruna/pull/309
Adds a hook so algorithms can prep or tweak models before smashing, making customization easier.
Our documentation got a huge glow up 💅 thanks to @sdiazlor and @davidberenstein1957:
- docs: create end to end reasoning tutorial by @sdiazlor in https://github.com/PrunaAI/pruna/pull/283
- docs: create end to end video tutorial by @sdiazlor in https://github.com/PrunaAI/pruna/pull/233
- docs: fix discord broken link by @sdiazlor in https://github.com/PrunaAI/pruna/pull/305
- docs: updates gtm by @davidberenstein1957 in https://github.com/PrunaAI/pruna/pull/316
Pruning some bugs 🐞 and maintenance 🧑🌾
- torch.load always to cpu first by @simlang in https://github.com/PrunaAI/pruna/pull/308
- Rework Model Context by @simlang in https://github.com/PrunaAI/pruna/pull/323
- fix: make qkv compatible with torch.compile in next diffusers release by @llcnt in https://github.com/PrunaAI/pruna/pull/302
- fix: hqq diffusers saving and loading forget non linear layers by @llcnt in https://github.com/PrunaAI/pruna/pull/275
- fix: namespace package conflict of optimum and optimum-quanto by @ParagEkbote in https://github.com/PrunaAI/pruna/pull/298
- fix: deprecated call types & fixture bug by @begumcig in https://github.com/PrunaAI/pruna/pull/313
- fix: nightly tests llmcompressor and gptq by @llcnt in https://github.com/PrunaAI/pruna/pull/315
- fix: update datamodules for datasets v4.0.0 by @begumcig in https://github.com/PrunaAI/pruna/pull/328
- fix: update model card tags to include 'pruna-ai' by default by @davidberenstein1957 in https://github.com/PrunaAI/pruna/pull/334
Full Changelog: https://github.com/PrunaAI/pruna/compare/v0.2.9...v0.2.10
