访客信息
☁️
--°天气加载中
正在获取所在地区…
💨 风力--
💧 湿度--
正在读取天气
公告
音乐
音乐
暂未播放
0:00/0:00
暂无歌词
LeetGPU Index
333 字
2 分钟
LeetGPU Index
Content
| Index | Problem | Link |
|---|---|---|
| 1 | Vector Addition | 01_Vector_Addition |
| 2 | Matrix Multiplication | 02_Matrix_Multiplication |
| 3 | Matrix Transpose | To be completed. |
| 4 | Color Inversion | To be completed. |
| 5 | Matrix Addition | To be completed. |
| 6 | 1D Convolution | To be completed. |
| 7 | Reverse Array | To be completed. |
| 8 | ReLU | To be completed. |
| 9 | Leaky ReLU | To be completed. |
| 10 | Rainbow Table | To be completed. |
| 11 | Matrix Copy | To be completed. |
| 12 | Simple Inference | To be completed. |
| 13 | Sigmoid Linear Unit | To be completed. |
| 14 | Swish Gated Linear Unit | To be completed. |
| 15 | Value Clipping | To be completed. |
| 16 | Interleave Arrays | To be completed. |
| 17 | Gaussian Error Gated Linear Unit | To be completed. |
| 18 | RGB to Grayscale | To be completed. |
| 19 | Sigmoid Activation | To be completed. |
| 20 | Reduction | To be completed. |
| 21 | Softmax | To be completed. |
| 22 | Softmax Attention | To be completed. |
| 23 | 2D Convolution | To be completed. |
| 24 | 3D Convolution | To be completed. |
| 25 | Histogramming | To be completed. |
| 26 | Prefix Sum | To be completed. |
| 27 | Dot Product | To be completed. |
| 28 | Sparse Matrix Vector Multiplication | To be completed. |
| 29 | General Matrix Multiplication GEMM | To be completed. |
| 30 | Categorical Cross Entropy Loss | To be completed. |
| 31 | Mean Squared Error | To be completed. |
| 32 | Gaussian Blur | To be completed. |
| 33 | Top K Selection | To be completed. |
| 34 | Batched Matrix Multiplication | To be completed. |
| 35 | INT8 Quantized MatMul | To be completed. |
| 36 | Ordinary Least Squares | To be completed. |
| 37 | Logistic Regression | To be completed. |
| 38 | Monte Carlo Integration | To be completed. |
| 39 | Matrix Power | To be completed. |
| 40 | Nearest Neighbor | To be completed. |
| 41 | Batch Normalization | To be completed. |
| 42 | 2D Max Pooling | To be completed. |
| 43 | Count Array Element | To be completed. |
| 44 | Count 2D Array Element | To be completed. |
| 45 | Count 3D Array Element | To be completed. |
| 46 | Subarray Sum | To be completed. |
| 47 | 2D Subarray Sum | To be completed. |
| 48 | 3D Subarray Sum | To be completed. |
| 49 | RMS Normalization | To be completed. |
| 50 | Max Subarray Sum | To be completed. |
| 51 | Attention with Linear Biases | To be completed. |
| 52 | FP16 Batched Matrix Multiplication | To be completed. |
| 53 | FP16 Dot Product | To be completed. |
| 54 | Top p Sampling | To be completed. |
| 55 | Rotary Positional Embedding | To be completed. |
| 56 | Weight Dequantization | To be completed. |
| 57 | MoE Top K Gating | To be completed. |
| 58 | 2D Jacobi Stencil | To be completed. |
| 59 | Segmented Exclusive Prefix Sum | To be completed. |
| 60 | Parallel Merge | To be completed. |
| 61 | Stream Compaction | To be completed. |
| 62 | Sparse Matrix Dense Matrix Multiplication | To be completed. |
| 63 | Adder Transformer Inference | To be completed. |
| 64 | 2D FFT | To be completed. |
| 65 | Grouped Query Attention | To be completed. |
| 66 | INT4 Weight Only Quantized MatMul | To be completed. |
| 67 | Linear Recurrence | To be completed. |
| 68 | SwiGLU MLP Block | To be completed. |
| 69 | LoRA Linear | To be completed. |
| 70 | Speculative Decoding Verification | To be completed. |
| 71 | Causal Depthwise Conv1d | To be completed. |
| 72 | Decaying Causal Attention | To be completed. |
| 73 | SSM Selective Scan | To be completed. |
| 74 | INT8 KV Cache Attention | To be completed. |
| 75 | Group Normalization | To be completed. |
| 76 | Token Embedding Layer | To be completed. |
| 77 | Multi Head Attention | To be completed. |
| 78 | Multi Agent Simulation | To be completed. |
| 79 | Sorting | To be completed. |
| 80 | K Means Clustering | To be completed. |
| 81 | Radix Sort | To be completed. |
| 82 | Fast Fourier Transform | To be completed. |
| 83 | BFS Shortest Path | To be completed. |
| 84 | Causal Self Attention | To be completed. |
| 85 | Linear Self Attention | To be completed. |
| 86 | Sliding Window Self Attention | To be completed. |
| 87 | All Pairs Shortest Paths | To be completed. |
| 88 | GPT 2 Transformer Block | To be completed. |
| 89 | Llama Transformer Block | To be completed. |
References
LeetGPU repository for more.
文章分享
如果这篇文章对你有帮助,欢迎分享给更多人!
相关文章智能推荐
1
LeetGPU | 02_Matrix_Multiplication
LeetGPULeetGPU Matrix Multiplication 题解:CUDA、Triton 与 PyTorch 实现。
2
LeetGPU | 01_Vector_Addition
LeetGPULeetGPU Vector Addition 题解:CUDA、Triton 与 PyTorch 三种实现方式。
3
全网Infra优秀资料合集
合集AI Infra 优质学习资料索引,汇集公众号、视频、开源项目、各平台模型部署教程与专题资源。
4
Roofline Model
llm-algo-leetcode 推理优化Roofline Model 的基本概念、Arithmetic Intensity、memory-bound / compute-bound 判断,以及 GEMM、FlashAttention、算子融合等常见优化方向。
5
推理结构地基
llm-algo-leetcode 推理优化Datawhale llm-algo-leetcode 推理优化课程 Task 0(Attention MHA 与 GQA)学习笔记,正在完善中。
随机文章随机推荐
暂无随机文章
评论区
分享你的想法,与大家交流讨论
站点统计
文章
448
分类
29
标签
451
总字数
6,178,652
运行时长
0 天
最后活动
0 天前
最新动态
日
一
二
三
四
五
六
文章目录
访客信息
☁️
--°天气加载中
正在获取所在地区…
💨 风力--
💧 湿度--
正在读取天气
公告
音乐
音乐
暂未播放
0:00/0:00
暂无歌词
站点统计
文章
448
分类
29
标签
451
总字数
6,178,652
运行时长
0 天
最后活动
0 天前
最新动态



