Stars
VideoNSA: Native Sparse Attention Scales Video Understanding
FlashMLA: Efficient Multi-head Latent Attention Kernels
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth
This repository contains the training code of ParetoQ introduced in our work "ParetoQ Scaling Laws in Extremely Low-bit LLM Quantization"
Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch
A sparse attention kernel supporting mix sparse patterns
Scalable toolkit for efficient model reinforcement
Official inference framework for 1-bit LLMs
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
本『ChatGPT资源库(原理/微调/代码/论文)』的初始版本来自July CSDN博客上阅读量高达50万的ChatGPT系列，联合发起人：七月ChatGPT原理课学员，6月初正式对外发布
Code release for book "Efficient Training in PyTorch"
Traffic light detection using deep learning with the YOLOv3 framework. PyTorch => YOLOv3
[IROS 2020] Targetless Calibration of LiDAR-IMU System Based on Continuous-time Batch Estimation
(ITSC 2021) Optimising the selection of samples for robust lidar camera calibration. This package estimates the calibration parameters from camera to lidar frame.
[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.
BoT-SORT: Robust Associations Multi-Pedestrian Tracking