CUDA Templates and Python DSLs for High-Performance Linear Algebra
Repository Index
47,133 repositories indexed
1–5 of 5 · Most stars
NVIDIA cuML: GPU-Accelerated Machine Learning
eBPF based always-on CPU/GPU profiler auto-discovering targets in Kubernetes and systemd, zero code changes or restarts needed!
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
Push-to-talk voice dictation for Linux. 100% local, multilingual (25+ languages), with speaker diarization. Qt frontend, Rust backend on NVIDIA Parakeet via ONNX Runtime. KDE Plasmoid integrated.