sunkx109 / My-Torch-Extension
A minimalist and extensible PyTorch extension for implementing custom backend operators in PyTorch.
☆33Updated last year
Alternatives and similar repositories for My-Torch-Extension:
Users that are interested in My-Torch-Extension are comparing it to the libraries listed below
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆86Updated 3 months ago
- learning how CUDA works☆240Updated last month
- Examples of CUDA implementations by Cutlass CuTe☆159Updated 2 months ago
- A light llama-like llm inference framework based on the triton kernel.☆108Updated this week
- ☆122Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆334Updated 3 months ago
- ☆115Updated 4 months ago
- Implement Flash Attention using Cute.☆76Updated 4 months ago
- 📚FFPA(Split-D): Yet another Faster Flash Attention with O(1) GPU SRAM complexity large headdim, 1.8x~3x↑🎉 faster than SDPA EA.☆169Updated 3 weeks ago
- Tutorials for writing high-performance GPU operators in AI frameworks.☆130Updated last year
- ☆61Updated 3 months ago
- ☆121Updated this week
- 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。☆331Updated 3 weeks ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆50Updated 5 months ago
- CUDA 算子手撕与面试指南☆314Updated 3 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆342Updated 7 months ago
- A CUDA tutorial to make people learn CUDA program from 0☆225Updated 9 months ago
- ☆19Updated last month
- ☆131Updated last month
- ☆109Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆263Updated 10 months ago
- ☆138Updated 4 months ago
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆39Updated 8 months ago
- ☆90Updated 3 weeks ago
- A tutorial for CUDA&PyTorch☆137Updated 3 months ago
- Implement custom operators in PyTorch with cuda/c++☆58Updated 2 years ago
- Optimize softmax in triton in many cases☆20Updated 7 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆63Updated 8 months ago
- ☆65Updated last week
- hands on model tuning with TVM and profile it on a Mac M1, x86 CPU, and GTX-1080 GPU.☆47Updated last year