P
prometheus-and-grafana

  • Any
  • Batchfile
  • Blade
  • C
  • C#
  • C++
  • CMake
  • CSS
  • Dockerfile
  • Go
  • HCL
  • HTML
  • Java
  • JavaScript
  • Kotlin
  • Makefile
  • Objective-C
  • PHP
  • Python
  • Ruby
  • SCSS
  • Shell
  • Swift
  • TSX
  • TypeScript
  • Vue

Projects with this topic

Sort by:
  • Sort by
  • Updated date
  • Name
  • Name, descending
  • Oldest updated
  • Oldest created
  • Last created
  • Most stars
  • Hide archived projects
  • Show archived projects
  • Show archived projects only
  • View inference-fabric project
    I

    Corey James / inference-fabric

    A throughput-first GPU inference pipeline on consumer NVIDIA hardware: broker, saturated runtime, completion, vector store · high-throughput batch inference, token-aware scheduling, GPU inference optimisation, CUDA kernel development

    high-through... token-aware-... gpu-inferenc... cuda-kernel-... embedding-an... message-brok... exactly-once... tensorrt-and... append-only-... rust-systems... observabilit... inference-se... Rust cpp cuda tensorrt-llm fp8-inference memory-mappe... approximate-... prometheus-a...
    0
    Updated Oct 28, 2026
    0 0 0
    Updated Oct 28, 2026