Origin/nightly update rebased

README.md

@@ -8,7 +8,7 @@
 *  Advanced software optimizations and unique compression-aware runtime (released with NeurIPS 2022's paper [Fast Distilbert on CPUs](https://arxiv.org/abs/2211.07715) and [QuaLA-MiniLM: a Quantized Length Adaptive MiniLM](https://arxiv.org/abs/2210.17114), and NeurIPS 2021's paper [Prune Once for All: Sparse Pre-Trained Language Models](https://arxiv.org/abs/2111.05754))
 
 
-*  Accelerated end-to-end Transformer-based applications such as [Stable Diffusion](./examples/optimization/pytorch/huggingface/textual_inversion), [GPT-J-6B](./examples/optimization/pytorch/huggingface/language-modeling/inference/README.md#GPT-J), [BLOOM-176B](./examples/optimization/pytorch/huggingface/language-modeling/inference/README.md#BLOOM-176B), [T5](https://github.com/intel/intel-extension-for-transformers/blob/main/examples/optimization/pytorch/huggingface/summarization/quantization), and [SetFit](./docs/tutorials/pytorch/text-classification/SetFit_model_compression_AGNews.ipynb)       
+*  Accelerated end-to-end Transformer-based applications such as [Stable Diffusion](./examples/optimization/pytorch/huggingface/textual_inversion), [GPT-J-6B](./examples/optimization/pytorch/huggingface/language-modeling/inference/README.md#GPT-J), [BLOOM-176B](./examples/optimization/pytorch/huggingface/language-modeling/inference/README.md#BLOOM-176B), [T5](https://github.com/intel/intel-extension-for-transformers/blob/main/examples/optimization/pytorch/huggingface/summarization/quantization), and [SetFit](./docs/tutorials/pytorch/text-classification/SetFit_model_compression_AGNews.ipynb) by leveraging Intel AI software such as [Intel® Extension for PyTorch](https://github.com/intel/intel-extension-for-pytorch)     
 
 
 ## Installation

docs/api_doc/kernel/api_c.rst

@@ -1,8 +1,10 @@
-.. _api:
-Kernel C++ APIs
-####
-.. doxygenfile:: interface.hpp
-   :project: Intel® Extension for Transformers
+Kernels C++ APIs
+============================================   
 
-.. doxygenfile:: kernel.hpp
-   :project: Intel® Extension for Transformers
+.. toctree::
+   :maxdepth: 1
+
+   interface.rst
+   engine.rst
+   operator_desc.rst
+   types.rst

docs/api_doc/kernel/engine.rst

@@ -2,3 +2,6 @@ Class engine
 ####
 .. doxygenfile:: engine.hpp
    :project: Intel® Extension for Transformers
+
+.. doxygenfile:: cpu_engine.hpp
+   :project: Intel® Extension for Transformers

docs/api_doc/kernel/kernel.rst → docs/api_doc/kernel/interface.rst

@@ -1,4 +1,4 @@
-Class kernel
+Class Kernel
 ####
-.. doxygenfile:: kernel.hpp
+.. doxygenfile:: interface.hpp
    :project: Intel® Extension for Transformers

docs/api_doc/kernel/operator_desc.rst

@@ -0,0 +1,4 @@
+Class operator_desc
+####
+.. doxygenfile:: operator_desc.hpp
+   :project: Intel® Extension for Transformers

docs/api_doc/kernel/types.rst

@@ -0,0 +1,21 @@
+Operator Specific Types
+####
+.. doxygenfile:: kernels/attention_types.hpp
+   :project: Intel® Extension for Transformers
+.. doxygenfile:: kernels/eltwiseop_types.hpp
+   :project: Intel® Extension for Transformers
+.. doxygenfile:: kernels/gather_types.hpp
+   :project: Intel® Extension for Transformers
+.. doxygenfile:: kernels/layernorm_ba_types.hpp
+   :project: Intel® Extension for Transformers
+.. doxygenfile:: kernels/matmul_types.hpp
+   :project: Intel® Extension for Transformers
+.. doxygenfile:: kernels/mean_var_reduce_types.hpp
+   :project: Intel® Extension for Transformers
+.. doxygenfile:: kernels/softmax_types.hpp
+   :project: Intel® Extension for Transformers
+.. doxygenfile:: kernels/spmm_types.hpp
+   :project: Intel® Extension for Transformers
+.. doxygenfile:: kernels/transpose_mha_types.hpp
+   :project: Intel® Extension for Transformers
+

docs/api_doc/optimization.rst

@@ -11,4 +11,4 @@ The following API information is available:
    optimization/pipeline.rst
    optimization/optimizer_tf.rst
    optimization/optimizer.rst
-   optimization/trainer.rst
+   optimization/trainer.rst

docs/build_docs/source/kernel.rst

@@ -1,11 +1,12 @@
-Transformers-accelerated Libraries
+Kernels
 ============================================
+Transformers-accelerated Libraries (formerly known as SparseLib) is a high-performance operator computing library implemented by assembly. Transformers-accelerated Libraries contains a JIT domain, a kernel domain, and a scheduling proxy framework.
 
 .. toctree::
    :maxdepth: 1
 
    docs/intel_extension_for_transformers/backends/neural_engine/kernels/README.md
-   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/profiling.md
-   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/validated_data.md
-   docs/api_doc/api_kernel.rst
+   kernel_perf.rst
+   kernel_desc.rst
+   docs/api_doc/kernel/api_c.rst
 

docs/build_docs/source/kernel_desc.rst

@@ -0,0 +1,16 @@
+Implementation Details
+============================================
+
+.. toctree::
+   :maxdepth: 1
+
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/3D_inference.md  
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/binaryop_injector.md  
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/eltwise_injector.md  
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/kernel_vnni.md
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/kernel_amx.md  
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/kernel_avx512f.md  
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/kernel_layernormalized_spmm.md  
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/kernel_transpose_matmul.md  
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/kernel_desc/kernel_transpose_mha.md  
+

docs/build_docs/source/kernel_perf.rst

@@ -0,0 +1,11 @@
+Performance
+============================================
+
+Here we introduce performance relates issues  for users who might want detailed profiling intructions or check whether performance met requests.
+
+.. toctree::
+   :maxdepth: 1
+
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/profiling.md
+   docs/intel_extension_for_transformers/backends/neural_engine/kernels/docs/validated_data.md
+