Skip to content
@neuralmagic

Neural Magic

Neural Magic empowers developers to optimize and deploy LLMs at scale. Our model compression and acceleration enable top performance with vLLM.

Pinned Loading

  1. nm-vllm-certs Public

    General Information, model certifications, and benchmarks for nm-vllm enterprise distributions

    11 2

  2. deepsparse Public

    Sparsity-aware deep learning inference runtime for CPUs

    Python 3.1k 183

  3. sparseml Public

    Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

    Python 2.1k 152

  4. docs Public

    Top-level directory for documentation and general content

    MDX 120 7

  5. sparsezoo Public

    Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

    Python 382 26

  6. guidellm Public

    Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

    Python 256 28

Repositories

Showing 10 of 66 repositories
  • vllm Public Forked from vllm-project/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Python 12 Apache-2.0 6,907 0 15 Updated Apr 13, 2025
  • depyf Public Forked from thuml/depyf

    depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

    Python 0 MIT 22 0 0 Updated Apr 13, 2025
  • axolotl Public Forked from axolotl-ai-cloud/axolotl

    Go ahead and axolotl questions

    Python 0 Apache-2.0 1,001 0 3 Updated Apr 13, 2025
  • 0 0 0 1 Updated Apr 12, 2025
  • compressed-tensors Public

    A safetensors extension to efficiently store sparse quantized tensors on disk

    Python 98 Apache-2.0 10 5 16 Updated Apr 12, 2025
  • guidellm Public

    Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

    Python 256 Apache-2.0 28 25 9 Updated Apr 11, 2025
  • nm-actions Public

    Neural Magic GHA

    Python 0 Apache-2.0 0 0 2 Updated Apr 11, 2025
  • research Public

    Repository to enable research flows

    Python 0 0 0 1 Updated Apr 11, 2025
  • lm-evaluation-harness Public Forked from EleutherAI/lm-evaluation-harness

    A framework for few-shot evaluation of language models.

    Python 4 MIT 2,317 0 1 Updated Apr 11, 2025
  • lmms-eval Public Forked from EvolvingLMMs-Lab/lmms-eval

    Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

    Python 0 248 0 1 Updated Apr 9, 2025