Skip to content
@AMD-AGI

AMD-AGI

Popular repositories Loading

  1. Instella Instella Public

    Fully Open Language Models with Stellar Performance

    Python 317 29

  2. AMD-LLM AMD-LLM Public

    Python 193 14

  3. Nitro-1 Nitro-1 Public

    This repo provides a working re-implementation of Latent Adversarial Diffusion Distillation by AMD

    Python 124 6

  4. Nitro-E Nitro-E Public

    Python 108 8

  5. Primus Primus Public

    Python 74 27

  6. GEAK GEAK Public

    It is an LLM-based AI agent, which can write correct and efficient gpu kernels automatically.

    Python 68 13

Repositories

Showing 10 of 57 repositories
  • Primus-SaFE Public

    Primus-SaFE(Stability and Fault Endurance)

    AMD-AGI/Primus-SaFE’s past year of commit activity
    Go 50 1 0 5 Updated Feb 25, 2026
  • Magpie Public

    A lightweight, general-purpose framework for evaluating GPU kernel correctness and performance.

    AMD-AGI/Magpie’s past year of commit activity
    Python 29 MIT 2 0 0 Updated Feb 25, 2026
  • Primus Public
    AMD-AGI/Primus’s past year of commit activity
    Python 74 27 5 14 Updated Feb 25, 2026
  • TraceLens Public

    Automating analysis from trace files

    AMD-AGI/TraceLens’s past year of commit activity
    Python 59 MIT 9 78 11 Updated Feb 25, 2026
  • AgentKernelArena Public

    AgentKernelArena provides an end-to-end siloed-benchmarking environment where different LLM-powered agents—such as Cursor Agent, Claude Code, Codex, SWE-agent, and GEAK—can be evaluated side-by-side on the same GPU kernel tasks, using objective and reproducible metrics.

    AMD-AGI/AgentKernelArena’s past year of commit activity
    Python 8 Apache-2.0 3 12 1 Updated Feb 25, 2026
  • Primus-Turbo Public
    AMD-AGI/Primus-Turbo’s past year of commit activity
    Python 60 11 11 5 Updated Feb 25, 2026
  • GEAK Public

    It is an LLM-based AI agent, which can write correct and efficient gpu kernels automatically.

    AMD-AGI/GEAK’s past year of commit activity
    Python 68 13 2 4 Updated Feb 25, 2026
  • DUET-VLM Public

    DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference

    AMD-AGI/DUET-VLM’s past year of commit activity
    Python 7 Apache-2.0 0 1 1 Updated Feb 25, 2026
  • maxtext-slurm Public

    Toolkit for launching and observing MaxText training on Slurm-managed GPU clusters

    AMD-AGI/maxtext-slurm’s past year of commit activity
    Shell 18 MIT 1 0 0 Updated Feb 25, 2026
  • nixl Public Forked from ai-dynamo/nixl

    NVIDIA Inference Xfer Library (NIXL)

    AMD-AGI/nixl’s past year of commit activity
    C++ 1 248 0 0 Updated Feb 24, 2026

Top languages

Loading…

Most used topics

Loading…