Skip to content
View k9sret's full-sized avatar

Block or report k9sret

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

slime is an LLM training framework for RL Scaling.

Python 8,840 1,368 Updated Nov 5, 2026

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Python 24,267 4,923 Updated Nov 17, 2026

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

Python 898 89 Updated Aug 19, 2026

JAX bindings for the flash-attention3 kernels

C++ 23 2 Updated Sep 9, 2026

Flash Attention 2 implementation for Turing GPUs

C++ 136 19 Updated Sep 14, 2026

Implementation of FlashAttention (FA1-FA4) in PyTorch for educational and algorithmic clarity

Python 228 26 Updated Apr 12, 2026

FlashAttention (Metal Port)

Swift 615 44 Updated Sep 22, 2024
Python 3 Updated Jun 30, 2025
Python 2 Updated Aug 12, 2025

未使用cuTe和cutlass来实现一个功能全面的flash attention。

C++ 3 Updated Sep 15, 2025

Implement Flash Attention using Cute.

Cuda 113 8 Updated Dec 17, 2024

FP8-Attention: A CUDA-accelerated kernel for efficient transformer attention computation that uses E4M3 FP8 quantization and FlashAttention-style tiling to reduce memory usage and increase inferenc…

Cuda 1 Updated May 2, 2025

This repository contains multiple implementations of Flash Attention optimized with Triton kernels, showcasing progressive performance improvements through hardware-aware optimizations. The impleme…

Python 13 1 Updated Mar 26, 2026

Code from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch

Cuda 994 190 Updated Jul 19, 2023

Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.

Python 206 35 Updated May 29, 2026

(best/better) practices of megatron on veRL and tuning guide

Shell 141 10 Updated May 12, 2026

Kernel Library for Large Headdim Attention (64~1024, BF16/FP8/FP4), 1.5x~15x↑ vs PyTorch SDPA.

Python 350 29 Updated Nov 6, 2026

An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.

TeX 12,188 1,276 Updated Nov 17, 2026

Llama causal LM fully recreated in LibTorch. Designed to be used in Unreal Engine 5

C++ 17 3 Updated Sep 19, 2024

This is a code repository for pytorch c++ (or libtorch) tutorial.

C++ 839 131 Updated Nov 2, 2021

a modern C++ GUI library

C++ 2,483 347 Updated Nov 4, 2026

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Python 8,992 1,001 Updated Nov 17, 2026

12 Weeks, 24 Lessons, AI for All!

Jupyter Notebook 70,984 13,841 Updated Nov 15, 2026

Distributed Compiler and Optimized Parallel Kernels

Python 1,580 177 Updated Sep 18, 2026

🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.

Python 289 47 Updated Nov 24, 2025

Material for gpu-mode lectures

Jupyter Notebook 7,084 714 Updated Sep 9, 2026
Next