hkproj / triton-flash-attentionLinks
☆203Updated 9 months ago
Alternatives and similar repositories for triton-flash-attention
Users that are interested in triton-flash-attention are comparing it to the libraries listed below
Sorting:
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆226Updated 5 months ago
- making the official triton tutorials actually comprehensible☆54Updated last month
- A curated list of resources for learning and exploring Triton, OpenAI's programming language for writing efficient GPU code.☆417Updated 6 months ago
- Cataloging released Triton kernels.☆261Updated 3 weeks ago
- A repository to unravel the language of GPUs, making their kernel conversations easy to understand☆193Updated 4 months ago
- Learn CUDA with PyTorch☆84Updated last week
- ☆173Updated last year
- An extension of the nanoGPT repository for training small MOE models.☆195Updated 6 months ago
- ☆222Updated this week
- ☆242Updated this week
- Fast low-bit matmul kernels in Triton☆376Updated last week
- a minimal cache manager for PagedAttention, on top of llama3.☆122Updated last year
- GPU Kernels☆198Updated 5 months ago
- Collection of kernels written in Triton language☆155Updated 6 months ago
- Efficient LLM Inference over Long Sequences☆391Updated 3 months ago
- Applied AI experiments and examples for PyTorch☆296Updated last month
- ring-attention experiments☆152Updated 11 months ago
- LLaMA 2 implemented from scratch in PyTorch☆353Updated 2 years ago
- Recreating PyTorch from scratch (C/C++, CUDA, NCCL and Python, with multi-GPU support and automatic differentiation!)☆159Updated last year
- LLM KV cache compression made easy☆623Updated last week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆577Updated last month
- 100 days of building GPU kernels!☆508Updated 5 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆268Updated 2 months ago
- Load compute kernels from the Hub☆290Updated last week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆230Updated this week
- Fastest kernels written from scratch☆366Updated 2 weeks ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆290Updated 2 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆245Updated this week
- Simple MPI implementation for prototyping or learning☆284Updated 2 months ago
- coding CUDA everyday!☆61Updated 5 months ago