Skip to content
@AMD-AGI

AMD-AGI

Popular repositories Loading

  1. Instella Instella Public

    Fully Open Language Models with Stellar Performance

    Python 333 31

  2. AMD-LLM AMD-LLM Public

    Training code and resources for AMD-135M language models on AMD GPUs.

    Python 195 13

  3. Hyperloom Hyperloom Public

    An agentic system that auto-optimizes LLM workloads on AMD GPUs.

    Python 190 51

  4. GEAK GEAK Public

    Generating Efficient AI-Centric Kernels

    Python 176 51

  5. FLy FLy Public

    FLy: Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match (ICLR 2026)

    Python 128 5

  6. Nitro-1 Nitro-1 Public

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

    Python 127 6

Repositories

Showing 10 of 70 repositories
  • Hyperloom Public

    An agentic system that auto-optimizes LLM workloads on AMD GPUs.

    AMD-AGI/Hyperloom's past year of commit activity
    Python 190 51 24 51 Updated Sep 17, 2026
  • Primus Public

    A flexible and high-performance training framework designed for large-scale foundation model training on AMD GPUs

    AMD-AGI/Primus's past year of commit activity
    Python 126 59 3 (1 issue needs help) 31 Updated Sep 17, 2026
  • TraceLens Public

    Automating analysis from trace files

    AMD-AGI/TraceLens's past year of commit activity
    Python 91 MIT 25 97 48 Updated Sep 17, 2026
  • PrimusClaw Public

    LLM agent orchestration on Kubernetes: autonomous coding-agent sessions in per-session sandboxes.

    AMD-AGI/PrimusClaw's past year of commit activity
    TypeScript 3 0 2 3 Updated Sep 17, 2026
  • GEAK Public

    Generating Efficient AI-Centric Kernels

    AMD-AGI/GEAK's past year of commit activity
    Python 176 Apache-2.0 51 12 19 Updated Sep 17, 2026
  • Primus-Turbo Public

    A high-performance acceleration library dedicated to large-scale model training on AMD GPUs

    AMD-AGI/Primus-Turbo's past year of commit activity
    Python 70 30 7 19 Updated Sep 17, 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 116 Apache-2.0 14 8 11 Updated Sep 17, 2026
  • Infera Public

    More token goodput from frontier models. A distributed, SLA-aware serving mesh — disaggregated prefill/decode, KV-aware routing, and cache offload, tuned to your production SLA.

    AMD-AGI/Infera's past year of commit activity
    Python 20 MIT 4 15 11 Updated Sep 17, 2026
  • ALTO Public

    ALTO: Advanced Low-precision Training and Optimization

    AMD-AGI/ALTO's past year of commit activity
    Python 0 2 0 7 Updated Sep 17, 2026
  • diffusion-models-inference Public

    Diffusion model inference benchmarking, profiling and optimizing

    AMD-AGI/diffusion-models-inference's past year of commit activity
    Python 0 MIT 0 3 7 Updated Sep 17, 2026