A high-throughput and memory-efficient inference and serving engine for LLMs
Repository Index
47,133 repositories indexed
1–24 of 88 · Most stars
The open-source AI voice studio. Clone, dictate, create.
- ai
- voice-clone
- qwen3-tts
- voice-ai
SGLang is a high-performance serving framework for large language models and multimodal models.
LLM training in simple, raw C/CUDA
World's fastest and most advanced password recovery utility
Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Instant neural graphics primitives: lightning fast NeRF and more
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
- autodiff
- deep-learning
- machine-learning
- rust
kaldi-asr/kaldi is the official location of the Kaldi project.
CUDA on non-NVIDIA GPUs
- cuda
- rust
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
- text2music
Open3D: A Modern Library for 3D Data Processing
- mesh-processing
- computer-graphics
- opengl
- cpp
Solve puzzles. Learn CUDA.
- cuda
- machine-learning
- puzzles
NumPy & SciPy for GPU
- cuda
- cudnn
- cublas
- cusolver
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
A General-purpose Task-parallel Programming System in C++
- parallel-programming
- threadpool
- concurrent-programming
- high-performance-computing
An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.
- cuda
- hgemm
- cuda-kernels
- cuda-toolkit
HVM1 (2022): a massively parallel, optimal functional runtime in Rust
NumPy aware dynamic Python compiler using LLVM
CUDA Templates and Python DSLs for High-Performance Linear Algebra
- cuda
- deep-learning
- deep-learning-library
- cpp
cuDF - GPU DataFrame Library
- gpu
- rapids
- cudf
- arrow
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
- machine-learning
- decision-trees
- gradient-boosting
- gbm