Pinned Repositories
whisper.cpp
Port of OpenAI's Whisper model in C/C++
ai-edu
AI education materials for Chinese students, teachers and IT professionals.
EdgeML
This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.
faster-whisper
Faster Whisper transcription with CTranslate2
fastmoe
A fast MoE impl for PyTorch
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
triton-backend
Common source, scripts and utilities for creating Triton backends.
triton-repeat_backend
An example Triton backend that demonstrates sending zero, one, or multiple responses for each request.
triton-server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
vits
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
knitvoger's Repositories
knitvoger/fastmoe
A fast MoE impl for PyTorch
knitvoger/ai-edu
AI education materials for Chinese students, teachers and IT professionals.
knitvoger/EdgeML
This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.
knitvoger/faster-whisper
Faster Whisper transcription with CTranslate2
knitvoger/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
knitvoger/triton-backend
Common source, scripts and utilities for creating Triton backends.
knitvoger/triton-repeat_backend
An example Triton backend that demonstrates sending zero, one, or multiple responses for each request.
knitvoger/triton-server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
knitvoger/vits
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech