huggingface / optimum-intel
๐ค Optimum Intel: Accelerate inference with Intel optimization tools
โ451Updated this week
Alternatives and similar repositories for optimum-intel:
Users that are interested in optimum-intel are comparing it to the libraries listed below
- Easy and lightning fast training of ๐ค Transformers on Habana Gaudi processor (HPU)โ177Updated this week
- Run Generative AI models with simple C++/Python API and using OpenVINO Runtimeโ245Updated this week
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.โ325Updated this week
- ๐๏ธ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Oโฆโ289Updated last month
- An innovative library for efficient LLM inference via low-bit quantizationโ351Updated 6 months ago
- Intelยฎ Extension for DeepSpeed* is an extension to DeepSpeed that brings feature support with SYCL kernels on Intel GPU(XPU) device. Noteโฆโ62Updated 2 weeks ago
- A high-throughput and memory-efficient inference and serving engine for LLMsโ262Updated 5 months ago
- Common utilities for ONNX convertersโ259Updated 3 months ago
- The Triton backend for the ONNX Runtime.โ140Updated last week
- onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtimeโ368Updated this week
- Examples for using ONNX Runtime for model training.โ329Updated 5 months ago
- GPTQ inference Triton kernelโ298Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.โ771Updated 6 months ago
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Rโฆโ2,360Updated this week
- A Python package for extending the official PyTorch that can easily obtain performance on Intel platformโ1,793Updated this week
- A pytorch quantization backend for optimumโ902Updated 2 weeks ago
- Generative AI extensions for onnxruntimeโ655Updated this week
- Advanced Quantization Algorithm for LLMs/VLMs.โ403Updated this week
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.โ163Updated 2 weeks ago
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.โ781Updated last month
- The Triton backend for the PyTorch TorchScript models.โ144Updated last week
- โ411Updated last year
- Provides end-to-end model development pipelines for LLMs and Multimodal models that can be launched on-prem or cloud-native.โ496Updated 2 weeks ago
- Reference models for Intel(R) Gaudi(R) AI Acceleratorโ160Updated 3 weeks ago
- LLaMa/RWKV onnx models, quantization and testcaseโ359Updated last year
- A unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, speculative decoding, etโฆโ808Updated this week
- ONNX Optimizerโ683Updated last week
- โ20Updated 8 months ago
- Universal cross-platform tokenizers binding to HF and sentencepieceโ312Updated last month
- Easy and Efficient Quantization for Transformersโ193Updated last month