Skip to content
@neuralmagic

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

  1. deepsparse deepsparse Public archive

    Sparsity-aware deep learning inference runtime for CPUs

    Python 3.2k 192

Repositories

Showing 10 of 109 repositories
  • vllm-vcr Public

    vLLM inference simulator and replay machine

    neuralmagic/vllm-vcr's past year of commit activity
    Rust 6 Apache-2.0 1 14 (2 issues need help) 11 Updated Sep 17, 2026
  • 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 17 Apache-2.0 22,545 0 38 Updated Sep 17, 2026
  • llm-manifesto Public

    Declarative Kubernetes renderer for llm-d and vLLM deployments

    neuralmagic/llm-manifesto's past year of commit activity
    Python 2 Apache-2.0 0 0 3 Updated Sep 17, 2026
  • model-validation-configs Public
    neuralmagic/model-validation-configs's past year of commit activity
    2 2 1 10 Updated Sep 16, 2026
  • research Public

    Repository to enable research flows

    neuralmagic/research's past year of commit activity
    Python 4 1 0 3 Updated Sep 16, 2026
  • eval-hub Public Forked from eval-hub/eval-hub
    neuralmagic/eval-hub's past year of commit activity
    Go 0 Apache-2.0 27 0 0 Updated Sep 16, 2026
  • eval-hub-contrib Public Forked from eval-hub/eval-hub-contrib

    Community-contributed evaluation framework adapters for eval-hub

    neuralmagic/eval-hub-contrib's past year of commit activity
    Python 0 Apache-2.0 23 0 1 Updated Sep 16, 2026
  • nm-vllm-omni-ent Public Forked from vllm-project/vllm-omni

    A framework for efficient model inference with omni-modality models

    neuralmagic/nm-vllm-omni-ent's past year of commit activity
    Python 3 Apache-2.0 1,783 0 1 Updated Sep 15, 2026
  • crucible Public

    Crucible: an autonomous goal-directed research loop engine

    neuralmagic/crucible's past year of commit activity
    Rust 8 Apache-2.0 3 4 9 Updated Sep 15, 2026
  • vllm-beam-search-plugin Public

    Beam search scheduler plugin for vLLM v1 with CoW block table forking

    neuralmagic/vllm-beam-search-plugin's past year of commit activity
    Python 3 Apache-2.0 1 1 0 Updated Sep 15, 2026
View all repositories