Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
Repository Index
47,133 repositories indexed
73–89 of 89 · Most stars
Clojure library for CUDA development
- clojure-library
- clojure
- cuda-development
- cuda
Open source PTX to SASS assember (previously closed source by nvidia), more efficient SASS kernal for large scale Matrix Multiplication and Addition (MMA)
- compiler
- compiler-backend
- compiler-optimization
- gpu-acceleration
Latest hashcat docker for CUDA, OpenCL, and POCL. Deployed on Vast.ai
SIMT Abstractions for Runtime Extensible Kernels (GPGPU programing with OCaml)
- spoc
- ocaml
- opencl
- cuda
Fish Audio Drama 3 text-to-speech on the TensorFold native CUDA engine for DGX Spark (GB10): recipe, engine patches, benchmarks. Built with Fish Audio.
DCompute: Native execution of D on GPUs and other Accelerators
A GPU (CUDA) based Artificial Neural Network library
- self-organizing-map
- cuda
- c-plus-plus-11
- propagation-network
Controls for Delphi/Lazarus, used in CudaText: ATTabs, ATButton, ATListbox, ATScrollbar, ATStatusbar, ATGroups, ATGauge
Cumo (pronounced like "koomo") is CUDA aware numerical library whose interface is highly compatible with Ruby Numo
- ruby
- cuda
- numo
- scicentific-computing
MAT is library for working with multi-dimensional arrays which supports efficient interfacing to foreign and CUDA code. BLAS and CUBLAS bindings are available.
Ultra high-performance secp256k1 ECC engine | Python, Node.js, Rust, Go, C#, Swift, Java bindings | CUDA, Metal, OpenCL GPU | ECDSA, Schnorr, FROST, MuSig2, BIP-352 | 15+ platforms
- cryptography
- cuda
- riscv
- secp256k1
Efficient and expressive arrayed vector math library with multi-threading and CUDA support in Common Lisp.
A Dockerfile generator for running OpenGL (GLX) applications with nvidia-docker2, CUDA, ROS, and Gazebo on a remote headless server system by using VirtualGL&VNC and Lubuntu Desktop
The repository host gives no description.
Dynamic bindings to the CUDA library for the D Programming Language.
Prototype of an intelligent safety system for detecting driver drowsiness
- cpp
- cuda
- cudnn
- driver-drowsiness-detector