Intel-npu-acceleration-library

Please update the NPU driver to the latest version to fully utilize the library features
- Windows: [link](https://www.intel.com/content/www/us/en/download/794734/intel-npu-driver-windows.html)
- Linux: [ink](https://github.com/intel/linux-npu-driver)

PIP package: https://pypi.org/project/intel-npu-acceleration-library/1.4.0/

What's Changed
* Add doc for implementing new operations by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/79
* Adding power and log softmax operations by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/80
* Adding support for operations on tensors by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/81
* Add c++ examples by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/86
* NPU compilation tutorial by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/87
* Fix ops and r_ops in case of float and int by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/88
* Adding support and testing for chunk tensor operation by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/90
* Make matmul op () torch compliant by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/91
* Update scikit-learn requirement from <=1.5.0 to <=1.5.1 by dependabot in https://github.com/intel/intel-npu-acceleration-library/pull/93
* Support for Phi-3 MLP layer by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/84
* Fix OpenSSF scan by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/99
* Enable npu compile in compiler.py by xduzhangjiayu in https://github.com/intel/intel-npu-acceleration-library/pull/100
* Dtype mismatch fix for model training by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/104
* Add the position_imbeddings param to LlamaAttention.forward by Nagico2 in https://github.com/intel/intel-npu-acceleration-library/pull/105
* add param in profile_mlp.py to enable graph mode or not by xduzhangjiayu in https://github.com/intel/intel-npu-acceleration-library/pull/106
* Add prelu and normalize ops by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/107
* qwen2_math_7b.py to support Qwen Math 7b LLM network by andyyeh75 in https://github.com/intel/intel-npu-acceleration-library/pull/119
* Update scikit-learn requirement from <=1.5.1 to <=1.5.2 by dependabot in https://github.com/intel/intel-npu-acceleration-library/pull/123
* Fix some issues on CI by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/130
* Model compiling demo by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/115
* 'Audio-Spectrogram-Transformer' example added by sbasia in https://github.com/intel/intel-npu-acceleration-library/pull/134
* Building on Ubuntu 24.04 by ytxmobile98 in https://github.com/intel/intel-npu-acceleration-library/pull/129
* Add turbo mode by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/140
* Reinstate llama tests by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/141

New Contributors
* Nagico2 made their first contribution in https://github.com/intel/intel-npu-acceleration-library/pull/105
* andyyeh75 made their first contribution in https://github.com/intel/intel-npu-acceleration-library/pull/119
* sbasia made their first contribution in https://github.com/intel/intel-npu-acceleration-library/pull/134
* ytxmobile98 made their first contribution in https://github.com/intel/intel-npu-acceleration-library/pull/129

**Full Changelog**: https://github.com/intel/intel-npu-acceleration-library/compare/v1.3.0...v1.4.0

Please update the NPU driver to the latest version to fully utilize the library features
- Windows: [link](https://www.intel.com/content/www/us/en/download/794734/intel-npu-driver-windows.html)
- Linux: [ink](https://github.com/intel/linux-npu-driver)

PIP package: https://pypi.org/project/intel-npu-acceleration-library/1.3.0/

What's Changed
* Fix export error with trust_remote_code by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/43
* Create warnings if driver is old by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/46
* Fix int4 quantization for llama and gemma by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/47
* Add C++ example by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/54
* adding new operations by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/50
* Fix for NaNs in LLM inference by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/58
* Change function generate_with_static_shape by xduzhangjiayu in https://github.com/intel/intel-npu-acceleration-library/pull/60
* Native convolution and dw convolution by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/61
* Sarah/feature/constant operation support by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/62
* Add memory operation and tensor class by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/63
* Adding support for L2 normalisation operation by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/65
* Better torch integration by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/66
* Add torch.nn.functional.conv2d by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/70
* fix BatchNorm layer by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/71
* Sarah/feature/operations by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/68
* Add torch NPU device by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/72
* Automatic handling of output layers by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/73
* Sarah/feature/reduce ops by SarahByrneIntel in https://github.com/intel/intel-npu-acceleration-library/pull/74
* Hotfix for module by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/76
* Fix SDPA in case attn_mask == None by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/78

New Contributors
* SarahByrneIntel made their first contribution in https://github.com/intel/intel-npu-acceleration-library/pull/50
* xduzhangjiayu made their first contribution in https://github.com/intel/intel-npu-acceleration-library/pull/60

**Full Changelog**: https://github.com/intel/intel-npu-acceleration-library/compare/v1.2.0...v1.3.0

**Please use the latest driver to take full advantage of the new features** [link](https://www.intel.com/content/www/us/en/download/794734/intel-npu-driver-windows.html)

What's Changed
* Update scikit-learn requirement from <1.5.0 to <1.6.0 by dependabot in https://github.com/intel/intel-npu-acceleration-library/pull/31
* Add int4 support by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/32
* Backend performance optimization by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/35
* Implement SDPA (Scalar dot product attention) NPU kernel by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/36
* Persistent compilation by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/39

New Contributors
* dependabot made their first contribution in https://github.com/intel/intel-npu-acceleration-library/pull/31

**Full Changelog**: https://github.com/intel/intel-npu-acceleration-library/compare/v1.1.0...v1.2.0

**Be sure to use the latest NPU driver to fully exploit latest features!** [link](https://www.intel.com/content/www/us/en/download/794734/intel-npu-driver-windows.html)


What's Changed
* Alessandro/feature/better compilation by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/11
* Add Conv2D support by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/18
* Add attribute to conv by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/19
* Add function to explicitly clean model cache to improve tests and avoid OOM errors by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/21
* Add driver versioning script for windows by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/28
* Driver support for true quantization in eager mode by alessandropalla in https://github.com/intel/intel-npu-acceleration-library/pull/20


**Full Changelog**: https://github.com/intel/intel-npu-acceleration-library/compare/v1,0,0...v1.1.0

v1,0,0
Intel NPU Acceleration Library release!

New Contributors
* alessandropalla made their first contribution in https://github.com/intel/intel-npu-acceleration-library/pull/1

**Full Changelog**: https://github.com/intel/intel-npu-acceleration-library/commits/v1,0,0