GPUStack

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 5.8k 687

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 25

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

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

   Go 306 30

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 4 6