Stars
A plain vanilla transformer implementation in Rust using the Candle ML framework
NVIDIA Math Libraries for the Python Ecosystem
A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.
Numbast is a tool to build an automated pipeline that converts CUDA APIs into Numba bindings.
Universal cross-platform tokenizers binding to HF and sentencepiece
🐮 A utility to load environment variables from a .env file
Nvidia contributed CUDA tutorial for Numba
An LLM playground you can run on your laptop
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy
✨✨Latest Advances on Multimodal Large Language Models
ONNX and TensorRT implementation of Whisper
A plugin for Jupyter Notebook to run CUDA C/C++ code
CUDA tutorials for Maths & ML tutorials with examples, covers multi-gpus, fused attention, winograd convolution, reinforcement learning.
Convenience scripts to finetune (chat-)LLaMa3 and other models for any language
Real-time transcription using faster-whisper
PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.
This repository contains tutorials and examples for Triton Inference Server
OCR, layout analysis, reading order, table recognition in 90+ languages
[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a ca…