sunkx109 / My-Torch-Extension
A minimalist and extensible PyTorch extension for implementing custom backend operators in PyTorch.
☆28Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for My-Torch-Extension
- learning how CUDA works☆169Updated 3 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆202Updated 5 months ago
- ☆99Updated 8 months ago
- Examples of CUDA implementations by Cutlass CuTe☆98Updated last week
- Tutorials for writing high-performance GPU operators in AI frameworks.☆123Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆52Updated 3 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆121Updated last week
- Summary of some awesome work for optimizing LLM inference☆37Updated 2 weeks ago
- ☆79Updated 8 months ago
- tutorial for writing custom pytorch cpp+cuda kernel, applied on volume rendering (NeRF)☆21Updated 11 months ago
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆32Updated 3 months ago
- ☆79Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆219Updated 5 months ago
- A CUDA tutorial to make people learn CUDA program from 0☆194Updated 4 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆29Updated 2 months ago
- 校招、秋招、春招、实习好项目,带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理 框架。☆225Updated 2 weeks ago
- hands on model tuning with TVM and profile it on a Mac M1, x86 CPU, and GTX-1080 GPU.☆41Updated last year
- ☆57Updated 2 weeks ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆87Updated last month
- ☆79Updated last year
- TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.☆154Updated this week
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆49Updated 2 months ago
- Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.☆23Updated 2 weeks ago
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆63Updated last week
- A Easy-to-understand TensorOp Matmul Tutorial☆290Updated 2 months ago
- ☆140Updated 6 months ago
- Codes & examples for "CUDA - From Correctness to Performance"☆70Updated 3 weeks ago
- ☆42Updated 7 months ago
- ☆19Updated 3 months ago
- 📒A small curated list of Awesome Diffusion Inference Papers with codes.☆96Updated this week