Skip to content

@neuralmagic Neural Magic

Change the repository type filter

All

    Repositories list

    87 repositories

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •14k•16•0•28•Updated Feb 27, 2026Feb 27, 2026

    • lm-evaluation-harness

      Public
      A framework for few-shot evaluation of language models.
      Python
      •
      MIT License
      •3.1k•5•0•1•Updated Feb 27, 2026Feb 27, 2026

    • nm-vllm-omni-ent

      Public
      A framework for efficient model inference with omni-modality models
      Python
      •
      Apache License 2.0
      •464•0•0•0•Updated Feb 26, 2026Feb 26, 2026

    • model-validation-configs

      Public
      1•2•1•0•Updated Feb 26, 2026Feb 26, 2026

    • tpu-inference

      Public
      TPU inference for vLLM, with unified JAX and PyTorch support.
      Python
      •
      Apache License 2.0
      •109•0•0•0•Updated Feb 25, 2026Feb 25, 2026

    • axolotl

      Public
      Go ahead and axolotl questions
      Python
      •
      Apache License 2.0
      •1.3k•0•0•5•Updated Feb 22, 2026Feb 22, 2026

    • GuardBench

      Public
      A Python library for guardrail models evaluation with vLLM support.
      Python
      •
      European Union Public License 1.2
      •7•0•0•2•Updated Feb 21, 2026Feb 21, 2026

    • pytorch

      Public
      Tensors and Dynamic neural networks in Python with strong GPU acceleration
      Python
      •
      Other
      •27k•1•0•6•Updated Feb 11, 2026Feb 11, 2026

    • SWE-bench

      Public
      SWE-bench: Can Language Models Resolve Real-world Github Issues?
      Python
      •
      MIT License
      •766•0•0•0•Updated Feb 11, 2026Feb 11, 2026

    • lmms-eval

      Public
      Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.
      Python
      •
      Other
      •524•0•0•12•Updated Feb 5, 2026Feb 5, 2026

    • nm-actions

      Public
      Neural Magic GHA
      Python
      •
      Apache License 2.0
      •0•0•0•4•Updated Jan 22, 2026Jan 22, 2026

    • research

      Public
      Repository to enable research flows
      Python
      •0•3•0•3•Updated Jan 9, 2026Jan 9, 2026

    • lighteval

      Public
      Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
      Python
      •
      MIT License
      •429•0•0•0•Updated Dec 17, 2025Dec 17, 2025

    • nm-vllm

      Public archive
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Other
      •14k•267•0•0•Updated Dec 4, 2025Dec 4, 2025

    • arena-hard-auto

      Public
      Arena-Hard-Auto: An automatic LLM benchmark.
      Python
      •
      Apache License 2.0
      •146•0•0•1•Updated Nov 19, 2025Nov 19, 2025

    • speculators-research

      Public
      Python
      •1•0•0•1•Updated Nov 13, 2025Nov 13, 2025

    • opendatahub-operator

      Public
      Open Data Hub operator to manage ODH component integrations
      Go
      •
      Apache License 2.0
      •233•0•0•0•Updated Nov 12, 2025Nov 12, 2025

    • sglang

      Public
      SGLang is a fast serving framework for large language models and vision language models.
      Python
      •
      Apache License 2.0
      •4.6k•1•0•1•Updated Oct 17, 2025Oct 17, 2025

    • DeepEP-test

      Public
      DeepEP: an efficient expert-parallel communication library
      Cuda
      •
      MIT License
      •1.1k•0•0•0•Updated Sep 26, 2025Sep 26, 2025

    • pydantic-regmix

      Public
      Common mixins, registries, and utilities with native support for Pydantic used across popular repos such as GuideLLM and Speculators
      Apache License 2.0
      •0•0•0•0•Updated Sep 17, 2025Sep 17, 2025

    • upstream-transformers

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      •
      Apache License 2.0
      •32k•2•0•0•Updated Sep 12, 2025Sep 12, 2025

    • pplx-kernels

      Public
      Perplexity GPU Kernels
      C++
      •
      MIT License
      •75•0•0•0•Updated Aug 29, 2025Aug 29, 2025

    • DeepEP

      Public
      DeepEP: an efficient expert-parallel communication library
      Cuda
      •
      MIT License
      •1.1k•0•0•0•Updated Aug 29, 2025Aug 29, 2025

    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      •
      MIT License
      •825•0•0•0•Updated Aug 29, 2025Aug 29, 2025

    • github-jira-sandbox

      Public
      proving grounds for GitHub to JIRA ... yay!
      Apache License 2.0
      •0•0•0•0•Updated Aug 27, 2025Aug 27, 2025

    • flashinfer

      Public
      FlashInfer: Kernel Library for LLM Serving
      Cuda
      •
      Apache License 2.0
      •745•0•0•0•Updated Jul 18, 2025Jul 18, 2025

    • collective_op_benchmarks

      Public
      Python
      •0•0•0•0•Updated Jul 11, 2025Jul 11, 2025

    • LMCache

      Public
      Redis for LLMs
      Python
      •
      Apache License 2.0
      •912•0•0•1•Updated Jun 18, 2025Jun 18, 2025

    • vllm-flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •2.4k•5•0•0•Updated Jun 11, 2025Jun 11, 2025

    • pytest-nm-releng

      Public
      Pytest plugin used by the Release Engineering team
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Jun 9, 2025Jun 9, 2025