#Triton
Showing 21 of 21 repositories tagged #triton, ranked by stars
Efficient Triton Kernels for LLM Training
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
A service for autodiscovery and configuration of applications running in containers
FlagGems is an operator library for large language models implemented in the Triton Language.
🎓 系统性大语言模型构建课程｜🛠️ 覆盖预训练数据工程、Tokenizer、Transformer、MoE、GPU 编程 (CUDA/Triton)、分布式训练、Scaling Laws、推理优化及对齐 (SFT/RLHF/GRPO)｜🚀 6 个渐进式作业 + 代码驱动，建立 LLM 全栈认知体系
🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.
Trainable fast and memory-efficient sparse attention
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.
🚀🚀🚀 This repository lists some awesome public CUDA, cuda-python, cuBLAS, cuDNN, CUTLASS, TensorRT, TensorRT-LLM, Triton, TVM, MLIR, PTX and High Performance Computing (HPC) projects.
Automatic ROPChain Generation
Ozoz dotfiles for bspwm, i3WM
ClearML - Model-Serving Orchestration and Repository Solution
KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required
lm-scratch-pytorch - The code is designed to be beginner-friendly, with a focus on understanding the fundamentals of PyTorch and implementing LLMs from scratch,step by step.
🦎Triton_RAT is free and easy to use, one of the best remote administration tools written in Python, fully integrated with Telegram🦎
[CVPR 2026 Highlight] Official implementation of Log-linear Sparse Attention (LLSA).
LLM4Kernel: A Survey of Large Language Models for GPU Kernel Development
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
[Hackathon winner]A production-ready micropayment gateway that implements HTTP 402 (Payment Required) to monetize access to historical Solana blockchain data via Old Faithful. Users pay micro-amounts in USDC to query historical transactions and blocks.
[ICLR2025] ReAttention, a training-free approach to break the maximum context length in length extrapolation