Enigmatisms
Follow
Lists (17)
C++
Excellent C++ projs.170 repositories
CUDA
Some CUDA repos.32 repositories
DeepLearning
Deep learning based algorithms and repos.273 repositories
Game Engine
Engine EngineeringGraphics
Computer graphics related.341 repositories
HPC
High performance computing140 repositories
Interesting
Interesting little project or games.301 repositories
Learning
Excellent learning resources49 repositories
Lightning
Fast! Make your code faster.2 repositories
LLMs
Interesting LLMs46 repositories
Math Algos
Mathematically based Algorithms1 repository
NeRF&GS
NeRF and 3D Gaussian81 repositories
Python
Python interesting repos and utilities91 repositories
Re-implementation
"My-own" series.2 repositories
Rust
Repos about rust programming language.44 repositories
SLAM
Repos of SLAM45 repositories
Utilities
Speed boosters (CUDA) and useful repos.206 repositories
Starred repositories
qqr is an RL training framework for open-ended agents.
A tool for bandwidth measurements on NVIDIA GPUs.
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Machine Learning Engineering Open Book
High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI
Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
Open-source release accompanying Gao et al. 2025
verl: Volcano Engine Reinforcement Learning for LLMs
Accelerating MoE with IO and Tile-aware Optimizations
2021年最新总结，推荐工程师合适读本，计算机科学，软件技术，创业，思想类，数学类，人物传记书籍
vLLM Kunlun (vllm-kunlun) is a community-maintained hardware plugin designed to seamlessly run vLLM on the Kunlun XPU.
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
Helpful kernel tutorials and examples for tile-based GPU programming
An experimental implementation of compiler-driven automatic sharding of models across a given device mesh.
An early research stage expert-parallel load balancer for MoE models based on linear programming.
A cinematic Git commit replay tool for the terminal, turning your Git history into a living, animated story.
Enjoy the magic of Diffusion models!
Large-Area Fabrication-Aware Computational Diffractive Optics (SIGGRAPH Asia & TOG 2025)
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
Unifying 3D Mesh Generation with Language Models
A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
Core Functional Library for Distributed Training
