Intel Corporation's repositories
neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
intel-extension-for-transformers
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
scikit-learn-intelex
Intel(R) Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application
compute-runtime
Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver
intel-extension-for-tensorflow
Intel® Extension for TensorFlow*
confidential-computing-zoo
Confidential Computing Zoo provides confidential computing solutions based on Intel SGX, TDX, HEXL, etc. technologies.
intel-sgx-ssl
Intel® Software Guard Extensions SSL
neural-speed
An innovative library for efficient LLM inference via low-bit quantization
cartwheel-ffmpeg
Intel developer staging area for unmerged upstream patch contributions to FFmpeg
intel-xpu-backend-for-triton
OpenAI Triton backend for Intel® GPUs
linux-npu-driver
Intel® NPU (Neural Processing Unit) Driver
onnxruntime
ONNX Runtime: cross-platform, high performance scoring engine for ML models
llm-on-ray
Pretrain, finetune and serve LLMs on Intel platforms with Ray
auto-round
SOTA Weight-only Quantization Algorithm for LLMs
compute-aggregation-layer
Compute Aggregation Layer for oneAPI Level Zero and OpenCL(TM) Applications
cve-bin-tool-action
Known vulnerability scanning for your GitHub repository using CVE Binary Tool. This Action can scan binaries, component lists and SBOMs for known vulnerabilities and CVEs. It can generate SBOM component lists as well as reports in the Security Tab and in HTML/JSON/PDF format.
GenAIExamples
Intel Generative AI Examples such as ChatQnA based on RAG, Code Generation, Summarization etc.