xyzjin's starred repositories
everyone-can-use-english
人人都能用英语
Visual-Instruction-Tuning
SVIT: Scaling up Visual Instruction Tuning
coyo-dataset
COYO-700M: Large-scale Image-Text Pair Dataset
Megatron-LM
Ongoing research training transformer models at scale
developer2gwy
公务员从入门到上岸,最佳程序员公考实践教程
cuda_learning
learning how CUDA works
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
CUDA-Learn-Notes
🎉CUDA/C++ 笔记 / 大模型手撕CUDA / 技术博客,更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
LLaVA-UHD-Better
A bug-free and improved implementation of LLaVA-UHD, based on the code from the official repo