Neural Magic

Neural Magic (Acquired by Red Hat) empowers developers to optimize & deploy LLMs at scale. Our model compression & acceleration enable top performance with vLLM

Pinned Loading

deepsparse deepsparse Public archive

Sparsity-aware deep learning inference runtime for CPUs

Python 3.2k 192

Repositories

vllm Public Forked from vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs

neuralmagic/vllm’s past year of commit activity

Python 15 Apache-2.0 10,674 0 20 Updated Oct 8, 2025
research Public
Repository to enable research flows

neuralmagic/research’s past year of commit activity

Python 3 0 0 1 Updated Oct 8, 2025
compressed-tensors Public
A safetensors extension to efficiently store sparse quantized tensors on disk

neuralmagic/compressed-tensors’s past year of commit activity

Python 167 Apache-2.0 33 3 21 Updated Oct 9, 2025
model-validation-configs Public

neuralmagic/model-validation-configs’s past year of commit activity

2 0 0 2 Updated Oct 8, 2025
nm-actions Public
Neural Magic GHA

neuralmagic/nm-actions’s past year of commit activity

Python 0 Apache-2.0 0 0 3 Updated Oct 8, 2025
arena-hard-auto Public Forked from lmarena/arena-hard-auto
Arena-Hard-Auto: An automatic LLM benchmark.

neuralmagic/arena-hard-auto’s past year of commit activity

Python 0 Apache-2.0 127 0 1 Updated Oct 8, 2025
axolotl Public Forked from axolotl-ai-cloud/axolotl
Go ahead and axolotl questions

neuralmagic/axolotl’s past year of commit activity

Python 0 Apache-2.0 1,176 0 5 Updated Oct 5, 2025
DeepEP-test Public Forked from smarterclayton/DeepEP
DeepEP: an efficient expert-parallel communication library

neuralmagic/DeepEP-test’s past year of commit activity

Cuda 0 MIT 951 0 0 Updated Sep 27, 2025
pytorch Public Forked from pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration

neuralmagic/pytorch’s past year of commit activity

Python 0 26,155 0 1 Updated Sep 17, 2025
pydantic-regmix Public
Common mixins, registries, and utilities with native support for Pydantic used across popular repos such as GuideLLM and Speculators

neuralmagic/pydantic-regmix’s past year of commit activity

0 Apache-2.0 0 0 0 Updated Sep 17, 2025