Skip to content

Popular repositories Loading

  1. pegainfer pegainfer Public

    Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

    Rust 742 121

  2. kern kern Public

    A model-agnostic GPU runtime for shipping models as verified programs.

    Rust 187 13

  3. pega-omni pega-omni Public

    OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one GPU.

    Rust 51 5

  4. kern-k31 kern-k31 Public

    Kimi-K3.1 Pro on the kern runtime: the manifest generator, kernels and pinned hashes for its P/D stack

    Cuda 7 1

  5. kern-k3-pp-prefill kern-k3-pp-prefill Public

    Kimi-K3 prefill as pipeline-parallel stages for kern: manifests, kernel sources, build recipes

    Cuda 6 1

  6. website website Public

    Documentation website for openinfer — Astro Starlight on Cloudflare Workers

    MDX 4 1

Repositories

Showing 10 of 12 repositories
  • pega-omni Public

    OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one GPU.

    pegainfer-project/pega-omni's past year of commit activity
    Rust 51 5 2 3 Updated Nov 14, 2026
  • pegainfer Public

    Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

    pegainfer-project/pegainfer's past year of commit activity
    Rust 742 Apache-2.0 121 38 (5 issues need help) 15 Updated Nov 14, 2026
  • kern Public

    A model-agnostic GPU runtime for shipping models as verified programs.

    pegainfer-project/kern's past year of commit activity
    Rust 187 Apache-2.0 13 17 9 Updated Nov 11, 2026
  • kern-qwen3 Public

    Dense Qwen3 manifests, portable CUDA kernels, and seeded sampling for the kern runtime

    pegainfer-project/kern-qwen3's past year of commit activity
    Python 0 Apache-2.0 0 0 0 Updated Nov 8, 2026
  • kern-dsv41-flash Public

    DeepSeek V4.1 Flash kernels for kern: sources, pinned upstreams, a reproducible build

    pegainfer-project/kern-dsv41-flash's past year of commit activity
    Python 2 Apache-2.0 0 0 0 Updated Nov 8, 2026
  • kern-glm53 Public

    GLM-5.3 on the kern runtime: the manifest generator, kernels and pinned hashes for its pipeline-parallel prefill

    pegainfer-project/kern-glm53's past year of commit activity
    Cuda 0 Apache-2.0 0 0 0 Updated Nov 8, 2026
  • kern-k3-pp-prefill Public

    Kimi-K3 prefill as pipeline-parallel stages for kern: manifests, kernel sources, build recipes

    pegainfer-project/kern-k3-pp-prefill's past year of commit activity
    Cuda 6 1 0 2 Updated Nov 8, 2026
  • kern-k31 Public

    Kimi-K3.1 Pro on the kern runtime: the manifest generator, kernels and pinned hashes for its P/D stack

    pegainfer-project/kern-k31's past year of commit activity
    Cuda 7 Apache-2.0 1 0 0 Updated Nov 8, 2026
  • infront Public

    Implement one Scheduler, get an OpenAI-compatible inference server (vLLM Rust frontend)

    pegainfer-project/infront's past year of commit activity
    Rust 1 Apache-2.0 0 1 0 Updated Nov 2, 2026
  • website Public

    Documentation website for openinfer — Astro Starlight on Cloudflare Workers

    pegainfer-project/website's past year of commit activity
    MDX 4 1 2 0 Updated Sep 23, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.