Stars
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
AdamW optimizer for bfloat16 models in pytorch 🔥.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
PyTorch native quantization and sparsity for training and inference
A modern model graph visualizer and debugger
Modular hardware build system
A modular, parametrizable, and highly flexible Data Movement Accelerator (DMA)
🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.
🦀⚙️ Sudoless performance monitoring for Apple Silicon processors. CPU / GPU / RAM usage, power consumption & temperature 🌡️
Synthesizable Floating point unit written using Verilog. Supports 32-bit (Single-Precision) Multiplication, Addition and Division and Square Root Operations based on the IEEE-754 standard for float…
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices
Inference and training library for high-quality TTS models.
ffmpeg static binaries for Mac OSX and Linux and Windows
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
The Art of Writing Efficient Programs, published by Packt
This repository is an official implementation of the paper "LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection".
DSPy: The framework for programming—not prompting—language models
Dynamically create python functions with a proper signature.
TensorDict is a pytorch dedicated tensor container.
🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.
Open source code for AlphaFold 2.
Thunder gives you PyTorch models superpowers for training and inference. Unlock out-of-the-box optimizations for performance, memory and parallelism, or roll out your own.
terrelln / dietgpu
Forked from facebookresearch/dietgpuGPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compression of numerical and other data types in HPC/ML applications.