dblalock / bolt
10x faster matrix and vector operations
☆2,474Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for bolt
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,555Updated 3 weeks ago
- A C++ standalone library for machine learning☆5,285Updated 2 weeks ago
- Flax is a neural network library for JAX that is designed for flexibility.☆6,113Updated this week
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆2,698Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,011Updated 6 months ago
- JAX-based neural network library☆2,894Updated this week
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,534Updated 8 months ago
- PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.☆747Updated last year
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,201Updated last year
- Library for reading and writing large multi-dimensional arrays.☆1,351Updated this week
- functorch is JAX-like composable function transforms for PyTorch.☆1,395Updated this week
- An efficient C++17 GPU numerical computing library with Python-like syntax☆1,215Updated this week
- FFCV: Fast Forward Computer Vision (and other ML workloads!)☆2,861Updated 4 months ago
- High-efficiency floating-point neural network inference operators for mobile, server, and Web☆1,879Updated this week
- Development repository for the Triton language and compiler☆13,354Updated this week
- PyTorch extensions for high performance and large scale training.☆3,191Updated 2 months ago
- Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.☆1,477Updated this week
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,205Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,220Updated this week
- Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, an…☆975Updated this week
- Vulkan/CUDA/HIP/OpenCL/Level Zero/Metal Fast Fourier Transform library☆1,544Updated last month
- General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). …☆1,995Updated 3 weeks ago
- Bagua Speeds up PyTorch☆875Updated 3 months ago
- maximal update parametrization (µP)☆1,399Updated 3 months ago
- Performance-portable, length-agnostic SIMD with runtime dispatch☆4,206Updated last week
- Tuplex is a parallel big data processing framework that runs data science pipelines written in Python at the speed of compiled code. Tupl…☆810Updated 7 months ago
- A Python toolbox for performing gradient-free optimization☆3,959Updated last month
- Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains☆1,743Updated last year
- The Tensor Algebra SuperOptimizer for Deep Learning☆691Updated last year