harleyszhang / lite_llama
A light llama-like llm inference framework based on the triton kernel.
☆103Updated 3 weeks ago
Alternatives and similar repositories for lite_llama:
Users that are interested in lite_llama are comparing it to the libraries listed below
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆81Updated 2 months ago
- learning how CUDA works☆226Updated last month
- ☆18Updated 2 weeks ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆48Updated 4 months ago
- CUDA 算子手撕与面试指南☆286Updated 2 months ago
- 分层解耦的深度学习推理引擎☆72Updated last month
- 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。☆317Updated 2 weeks ago
- ☆115Updated last year
- A tutorial for CUDA&PyTorch☆131Updated 2 months ago
- ☆58Updated 4 months ago
- Examples of CUDA implementations by Cutlass CuTe☆148Updated 2 months ago
- A CUDA tutorial to make people learn CUDA program from 0☆223Updated 8 months ago
- EasyNN是一个面向教学而开发的神经网络推理框架,旨在让大家0基础也能自主完成推理框架 编写!☆26Updated 7 months ago
- ☆145Updated 2 months ago
- b站上的课程☆72Updated last year
- Optimize softmax in triton in many cases☆20Updated 6 months ago
- 📚FFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) GPU SRAM complexity for headdim > 256, ~2x↑🎉vs SDPA EA.☆157Updated last week
- A minimalist and extensible PyTorch extension for implementing custom backend operators in PyTorch.☆34Updated 11 months ago
- Tutorials for writing high-performance GPU operators in AI frameworks.☆130Updated last year
- Implement Flash Attention using Cute.☆74Updated 3 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆315Updated 3 months ago
- how to learn PyTorch and OneFlow☆417Updated last year
- ☆139Updated 11 months ago
- ☆112Updated 3 months ago
- Triton Documentation in Chinese Simplified / Triton 中文文档☆62Updated 2 months ago
- ☆257Updated 5 months ago
- ☆36Updated 5 months ago
- 《CUDA编程基础与实践》一书的代码☆116Updated 2 years ago
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆38Updated 7 months ago
- 先进编译实验室的个人主页☆58Updated 2 months ago