All

7 repositories

paged-infer
Public
用于学习 Paged KV、continuous batching 与服务控制面的 Rust 模拟推理系统
rust machine-learning high-performance
rust machine-learning high-performance inference transformer gpu-computing production-ready systems-programming inference-engine serving
Rust
•
MIT License
•0•1•0•0•Updated Aug 14, 2026Aug 14, 2026
cudaimg
Public
CUDA 图像处理入门教学项目 - 通过图像处理算子学习 CUDA 编程
0•0•0•0•Updated Aug 7, 2026Aug 7, 2026
tiny-llm
Public
用于学习模型加载、CUDA 算子、KV Cache 与 token 生成的轻量 C++ 推理运行时
cmake cpp cuda
cmake cpp cuda nvidia transformer quantization kv-cache tensor-core llm-inference w8a16
C++
•
MIT License
•0•0•0•0•Updated Aug 7, 2026Aug 7, 2026
cuflash-attn
Public
用于学习 FlashAttention 前后向的 CUDA C++ 实现，支持 FP32/FP16/BF16 与 causal mask
c-plus-plus machine-learning deep-learning
c-plus-plus machine-learning deep-learning cpp hpc gpu cuda pytorch nvidia transformer
Cuda
•
MIT License
•0•0•0•0•Updated Aug 6, 2026Aug 6, 2026
triton-fused-ops
Public
面向 Transformer 推理学习的精简 Triton 算子：RMSNorm+RoPE、Gated MLP、FlashAttention
python acceleration deep-learning
python acceleration deep-learning high-performance cuda inference pytorch nvidia triton gpu-computing
Python
•
MIT License
•0•4•0•0•Updated Aug 6, 2026Aug 6, 2026
cuda-kernel-academy
Public
从 SGEMM 到推理组件的系统性 CUDA 学习主仓，整合四条历史实验路径
education tutorial cplusplus
education tutorial cplusplus hpc cuda gemm inference-engine gpu-programming sgemm cuda-programming
C++
•
MIT License
•0•2•0•0•Updated Aug 6, 2026Aug 6, 2026
.github
Public
AICL-Lab org profile: AI Infra portfolio navigation
0•0•0•0•Updated Aug 6, 2026Aug 6, 2026

ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.

Navigation Menu

aicl-lab

All

All

7 repositories

paged-infer

cudaimg

tiny-llm

cuflash-attn

triton-fused-ops

cuda-kernel-academy

.github

All

All

Repositories list

7 repositories