Mixed precision training from scratch with Tensors and CUDA
☆30May 14, 2024Updated 2 years ago
Alternatives and similar repositories for mixed-precision-from-scratch
Users that are interested in mixed-precision-from-scratch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- a minimal cache manager for PagedAttention, on top of llama3.☆146Aug 26, 2024Updated last year
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Triton kernels for Flux☆23Jul 7, 2025Updated 11 months ago
- BFloat16 Fused Adam Operator for PyTorch☆19Nov 16, 2024Updated last year
- Build CUDA Neural Network From Scratch☆22Aug 28, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆48Nov 1, 2025Updated 7 months ago
- A vector field rendering library☆17Jul 31, 2019Updated 6 years ago
- High-performance GEMM implementation optimized for NVIDIA H100 GPUs, leveraging Hopper architecture's TMA, WGMMA, and Thread Block Cluste…☆11Dec 4, 2024Updated last year
- Reimplentation of paper using gzip + knn for text classification☆18Aug 1, 2023Updated 2 years ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆81Aug 12, 2024Updated last year
- A practical way of learning Swizzle☆41Feb 3, 2025Updated last year
- 使用 cutlass 实现 flash-attention 精简版，具有教学意义☆59Aug 12, 2024Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆16Aug 31, 2023Updated 2 years ago
- 2014: Variational Monte Carlo for the harmonic oscillator, helium, hydrogen and H2 - IPython notebook and FORTRAN90☆13Jun 23, 2016Updated 9 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Implement Flash Attention using Cute.☆108Dec 17, 2024Updated last year
- ☆23Jun 7, 2026Updated last week
- This project is about convolution operator optimization on GPU, include GEMM based (Implicit GEMM) convolution.☆44Sep 29, 2025Updated 8 months ago
- ☆22Sep 3, 2024Updated last year
- Stochastic Series Expansion (SSE) for a isotropic S=1/2 antiferromagnetic quantum Heisenberg model in 1D, 2D or 3D lattice . Every lattic…☆15Jan 23, 2021Updated 5 years ago
- ☆122May 16, 2025Updated last year
- Created a simple neural network using C++17 standard and the Eigen library that supports both forward and backward propagation.☆11Jul 27, 2024Updated last year
- Transformers components but in Triton☆34May 9, 2025Updated last year
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆34Nov 29, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Framework to reduce autotune overhead to zero for well known deployments.☆101Sep 19, 2025Updated 8 months ago
- pytorch版基于gpt+nezha的中文多轮Cdial☆11Oct 22, 2022Updated 3 years ago
- TensorRT encapsulation, learn, rewrite, practice.☆30Oct 19, 2022Updated 3 years ago
- 数据库内核笔记☆14Aug 18, 2022Updated 3 years ago
- Using FlexAttention to compute attention with different masking patterns☆47Sep 22, 2024Updated last year
- Terminal UI for NVIDIA Nsight Systems profiles — timeline viewer, kernel navigator, NVTX hierarchy☆58Updated this week
- GEMV implementation with CUTLASS☆21Aug 21, 2025Updated 9 months ago
- Official PyTorch implementation of The Linear Attention Resurrection in Vision Transformer☆15Sep 7, 2024Updated last year
- llama.cpp to PyTorch Converter☆38Apr 8, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆47Jun 11, 2025Updated last year
- ☆11May 2, 2023Updated 3 years ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆12Jun 10, 2024Updated 2 years ago
- Fastest kernels written from scratch☆583Sep 18, 2025Updated 8 months ago
- A performance-oriented prototyping harness for state of the art Molecular Dynamics algorithms☆17May 27, 2026Updated 2 weeks ago
- A neural network quantum ground state solver☆27May 31, 2017Updated 9 years ago
- Visual Question Answering System☆11Nov 13, 2019Updated 6 years ago