v0.2.5

The juiciest bits 🚀

refactor: metric attributes by @begumcig in #81

We improved the evaluation framework for a cleaner UX: every metric is now atomic (returns a single float) with clear attributes (name, units, higher_is_better) and a unified MetricResult wrapper. All metrics consistently accept single or pairwise calls, name alignment is enforced, and the EvaluationAgent shares inference across metrics to avoid redundant computation.

refactor: remove deprecated awq algorithm by @johnrachwan123 in #143 | feat: add llm_compressor quantizer by @johnrachwan123 in #144

To continue support of the popular AWQ quantizer, we moved from auto-awq to llm_compressor.

Fixing some bugs 🐞

• fix: enhance model saving functionality to load multiple JSON configs present in diffusers by @davidberenstein1957 in #98

Full Changelog: v0.2.4...v0.2.5

v0.2.4

The juiciest bits 🚀

• feat: automate loading arguments by @johannaSommer in #77
• feat: max_batch_size refactoring by @johannaSommer in #67
• feat: add fastercache and pab by @nifleisch in #92
• refactor: move argument compatibility checks by @johannaSommer in #102
• docs: general structure refactor by @davidberenstein1957 in #90
• feat: add option for compilation for module lists by @johnrachwan123 in #105
• feat: add fora cacher by @nifleisch in #106
• test: use tiny random models to speed up tests by @nifleisch in #109
• refactor: remove deprecated algorithm names by @johannaSommer in #104
• feat: add device validation utility for improved device management by @davidberenstein1957 in #103
• feat: qkv fusing by @llcnt in #75
• feat: add torchao quantizer by @nifleisch in #110

Fixing some bugs 🐞

• fix: lower-bound ConfigSpace version by @johannaSommer in #101
• fix: fastercache and pab compatibility by @begumcig in #112
• fix: memory cleanup bug by @johannaSommer in #131

Full Changelog: v0.2.3...v0.2.4

Release v0.2.3

The juiciest bits 🚀

• feat: Add Hugging Face integration to save and load models by @davidberenstein1957 in #44
• feat: compile forward pass llm by @llcnt @johnrachwan123 in #51
• feat: support portable torch compilation by @johannaSommer in #69
• feat: add comfy support sfast by @agNikitaras in #66

Pruning some bugs 🐞

• fix: pin huggingface datasets version by @johannaSommer in #79
• fix: broken links docs by @begumcig in #74
• fix: GPUMemory metric memory bug by @johannaSommer in #78
• fix: collate_fn compatibility check logging by @johannaSommer in #76

New Contributors

• @agNikitaras made their first contribution in #66

Full Changelog: v0.2.2...v0.2.3

Release v0.2.2

The juiciest bits 🚀

• feat: enable bnb with torch compile by @llcnt in #45

Pruning some bugs 🐞

• chore: remove a double dependency when installing pruna[full] by @simlang in #52
• fix: python version compatibility and mypy issues by @begumcig in #54
• fix: fix inference issues for LLM evals by @begumcig in #53

New Contributors 🏋️‍♂️

• @simlang made their first contribution in #52

Full Changelog: v0.2.1...v0.2.2

Release v0.2.1

The juiciest bits 🚀

• feat: add cmmd by @begumcig in #38
• docs: update flux tutorial notebook from quanto to hqq by @johnrachwan123 in #42
• feat: switch autogptq to gptqmodel by @johnrachwan123 in #41
• feat: enable combination of torch_compile and hqq_diffusers by @johnrachwan123 in #23

Pruning some bugs 🐞

• fix: unpin quanto version and hfhub by @llcnt in #34
• style: clean cls implicit argument in PrunaDataModule by @gsprochette in #1
• fix: fix cudnn libs path in CTranslate compiler by @SaboniAmine in #37

No longer supported 👋

• feat: remove onediff from pruna by @johnrachwan123 in #40

New Contributors 🏋️‍♂️

• @antoinebrl made their first contribution in #31

Full Changelog: v0.2.0...v0.2.1

Release v0.2.0

Pruna is Open-Source 🥳🎉