8000 GPUStack · GitHub
[go: up one dir, main page]
Skip to content
8000
@gpustack

GPUStack

GPU cluster manager for optimized AI model deployment

Pinned Loading

  1. gpustack gpustack Public

    A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

    Python 6k 724

  2. runner runner Public

    Collection of Dockerfiles to build images for various inference services across different accelerated backends.

    Python 16 16

  3. runtime runtime Public

    Provides a unified interface to detect GPU resources and manages GPU workloads.

    Python 17 26

  4. gguf-parser-go gguf-parser-go Public

    Review/Check GGUF files and estimate the memory usage and maximum tokens per second.

    Go 310 31

  5. vox-box vox-box Public

    A text-to-speech and speech-to-text server compatible with the OpenAI API, supporting Whisper, FunASR, Bark, and CosyVoice backends.

    Python 217 36

  6. gpustack-operator gpustack-operator Public

    Manage heterogeneous accelerators, vGPU slicing, shared KV cache, model delivery, and inference workloads.

    Go 5 7

Repositories

Showing 10 of 18 repositories
  • gpustack-operator Public

    Manage heterogeneous accelerators, vGPU slicing, shared KV cache, model delivery, and inference workloads.

    gpustack/gpustack-operator's past year of commit activity
    Go 5 Apache-2.0 7 29 1 Updated Nov 6, 2026
  • gpustack Public

    A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

    gpustack/gpustack's past year of commit activity
    Python 5,983 Apache-2.0 723 667 80 Updated Nov 6, 2026
  • gpustack-ui Public
    gpustack/gpustack-ui's past year of commit activity
    TypeScript 100 Apache-2.0 88 4 19 Updated Nov 6, 2026
  • runner Public

    Collection of Dockerfiles to build images for various inference services across different accelerated backends.

    gpustack/runner's past year of commit activity
    Python 16 Apache-2.0 16 0 1 Updated Nov 6, 2026
  • core-ui Public
    gpustack/core-ui's past year of commit activity
    TypeScript 0 Apache-2.0 5 1 1 Updated Nov 6, 2026
  • runtime Public

    Provides a unified interface to detect GPU resources and manages GPU workloads.

    gpustack/runtime's past year of commit activity
    Python 17 Apache-2.0 26 0 4 Updated Nov 6, 2026
  • benchmark-runner Public

    Benchmark OpenAI-compatible LLM servers: find throughput peaks and latency SLO capacity, with terminal charts.

    gpustack/benchmark-runner's past year of commit activity
    Python 5 Apache-2.0 3 1 0 Updated Nov 4, 2026
  • gpustack-higress-plugin Public
    gpustack/gpustack-higress-plugin's past year of commit activity
    Go 3 9 1 1 Updated Nov 3, 2026
  • gguf-parser-go Public

    Review/Check GGUF files and estimate the memory usage and maximum tokens per second.

    gpustack/gguf-parser-go's past year of commit activity
    Go 310 MIT 31 1 0 Updated Oct 30, 2026
  • gpustack.github.io Public
    gpustack/gpustack.github.io's past year of commit activity
    HTML 1 3 0 0 Updated Oct 26, 2026
View all repositories
0