Skip to content

@HabanaAI Intel® Gaudi® AI Accelerator

Change the repository type filter

All

    Repositories list

    37 repositories

    • optimum-habana-fork

      Public
      Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)
      Python
      •
      Apache License 2.0
      •224•3•0•1•Updated Jan 26, 2025Jan 26, 2025

    • Gaudi-tutorials

      Public
      Tutorials for running models on First-gen Gaudi and Gaudi2 for Training and Inference. The source files for the tutorials on https://developer.habana.ai/
      Jupyter Notebook
      •37•56•3•3•Updated Jan 25, 2025Jan 25, 2025

    • vllm-fork

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •5.3k•47•7•38•Updated Jan 24, 2025Jan 24, 2025

    • vllm-hpu-extension

      Public
      Python
      •
      Apache License 2.0
      •16•3•2•5•Updated Jan 24, 2025Jan 24, 2025

    • pytorch-lightning

      Public
      The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
      Python
      •
      Apache License 2.0
      •3.4k•1•0•11•Updated Jan 21, 2025Jan 21, 2025

    • Model-References

      Public
      Reference models for Intel(R) Gaudi(R) AI Accelerator
      Jupyter Notebook
      •84•159•7•4•Updated Jan 21, 2025Jan 21, 2025

    • Megatron-LM

      Public
      Ongoing research training transformer models at scale
      Python
      •
      Other
      •2.5k•5•0•0•Updated Jan 18, 2025Jan 18, 2025

    • gaudi-pytorch-bridge

      Public
      C++
      •
      Apache License 2.0
      •0•9•0•0•Updated Jan 17, 2025Jan 17, 2025

    • TOWL

      Public
      HTML
      •
      Apache License 2.0
      •2•3•0•0•Updated Jan 16, 2025Jan 16, 2025

    • pytorch-fork

      Public
      Tensors and Dynamic neural networks in Python with strong GPU acceleration
      Python
      •
      Other
      •23k•1•0•5•Updated Jan 8, 2025Jan 8, 2025

    • hccl_demo

      Public
      C++
      •
      Apache License 2.0
      •12•18•1•1•Updated Jan 8, 2025Jan 8, 2025

    • neural-compressor

      Public
      SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
      Python
      •
      Apache License 2.0
      •260•0•0•0•Updated Dec 26, 2024Dec 26, 2024

    • HCL

      Public
      C++
      •4•9•0•0•Updated Dec 24, 2024Dec 24, 2024

    • Setup_and_Install

      Public
      Setup and Installation Instructions for Habana binaries, docker image creation
      Python
      •
      Apache License 2.0
      •13•25•5•5•Updated Dec 24, 2024Dec 24, 2024

    • DeepSpeed

      Public
      DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
      Python
      •
      Apache License 2.0
      •4.2k•12•0•2•Updated Dec 19, 2024Dec 19, 2024

    • Megatron-DeepSpeed

      Public
      Intel Gaudi's Megatron DeepSpeed Large Language Models for training
      Python
      •
      Other
      •2.5k•13•0•1•Updated Dec 19, 2024Dec 19, 2024

    • drivers.accel.habanalabs.kernel

      Public
      C
      •
      Other
      •0•2•1•0•Updated Dec 16, 2024Dec 16, 2024

    • hccl_ofi_wrapper

      Public
      C++
      •
      BSD 3-Clause "New" or "Revised" License
      •1•2•0•0•Updated Dec 9, 2024Dec 9, 2024

    • Habana_Custom_Kernel

      Public
      Provides the examples to write and build Habana custom kernels using the HabanaTools
      C++
      •23•19•3•2•Updated Dec 3, 2024Dec 3, 2024

    • Gaudi-solutions

      Public
      Full End-to-End examples showing how to use First-gen Gaudi and Gaudi2 in common use cases
      Jupyter Notebook
      •
      Apache License 2.0
      •6•10•0•0•Updated Dec 2, 2024Dec 2, 2024

    • AutoGPTQ

      Public
      An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
      Python
      •
      MIT License
      •502•0•0•2•Updated Nov 19, 2024Nov 19, 2024

    • Fairseq

      Public
      Python
      •
      MIT License
      •1•3•0•0•Updated Nov 18, 2024Nov 18, 2024

    • drivers.gpu.linux-nic.kernel

      Public
      NIC drivers (Ethernet, IBverbs and common) for the NIC IP that is inside Intel's data-center GPU
      C
      •
      Other
      •2•0•0•0•Updated Nov 12, 2024Nov 12, 2024

    • Intel_Gaudi3_Software

      Public
      Intel® Gaudi® Software is an implementation of the runtime and graph compiler for Gaudi3
      C++
      •
      Other
      •3•5•1•0•Updated Nov 11, 2024Nov 11, 2024

    • tpc_llvm

      Public
      TPC-CLANG compiler that compiles a TPC C programming language which is used in HabanaLabs Deep-Learning Accelerators
      5•26•2•3•Updated Nov 11, 2024Nov 11, 2024

    • habanalabs-k8s-device-plugin

      Public
      HABANA device plugin for Kubernetes
      kubernetescloud
      Go
      •
      Apache License 2.0
      •4•4•2•6•Updated Nov 11, 2024Nov 11, 2024

    • deepspeed_old

      Public
      Python
      •
      MIT License
      •3•6•0•3•Updated Nov 11, 2024Nov 11, 2024

    • slurm

      Public
      Slurm: A Highly Scalable Workload Manager
      C
      •
      Other
      •676•2•0•1•Updated Sep 29, 2024Sep 29, 2024

    • rdma-core

      Public
      RDMA core userspace libraries and daemons
      C
      •
      Other
      •710•1•0•0•Updated Jul 24, 2024Jul 24, 2024

    • papers

      Public
      Academic papers by Habana research team
      2•2•0•0•Updated Jul 20, 2024Jul 20, 2024