BBuf/how-to-optim-algorithm-in-cuda
how to optimize some algorithm in cuda.
This project provides optimized CUDA implementations for fundamental deep learning operations like reduce, softmax, and element-wise calculations. It offers practitioners faster computation for common tasks in machine learning by taking existing code and demonstrating how to improve its GPU performance. Researchers and engineers working with deep learning frameworks and large models would find this valuable for accelerating their model training and inference.
2,863 stars. Actively maintained with 11 commits in the last 30 days.
Use this if you are a machine learning engineer or researcher looking to understand and apply advanced CUDA optimization techniques to speed up your deep learning models and operations.
Not ideal if you are a beginner looking for an introductory guide to GPU programming or if you primarily work with pre-optimized, high-level deep learning libraries without needing to delve into custom kernel development.
Stars
2,863
Forks
260
Language
Cuda
License
—
Category
Last pushed
Mar 11, 2026
Commits (30d)
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/BBuf/how-to-optim-algorithm-in-cuda"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
vllm-project/vllm-ascend
Community maintained hardware plugin for vLLM on Ascend
SemiAnalysisAI/InferenceX
Open Source Continuous Inference Benchmarking Qwen3.5, DeepSeek, GPTOSS - GB200 NVL72 vs MI355X...
kvcache-ai/Mooncake
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
uccl-project/uccl
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache...
sophgo/tpu-mlir
Machine learning compiler based on MLIR for Sophgo TPU.