A customisable 3D platform for agent-based AI research

Felafax is building AI infra for non-NVIDIA GPUs

Latency and Memory Analysis of Transformer Models for Training and Inference

3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt.

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

The Triton TensorRT-LLM Backend

NCCL Profiling Kit

[ECCV2024] FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally

ROCm Parallel Primitives

Reusable software components for ROCm developers

An extension library of WMMA API (Tensor Core API)

PyTorch bindings for CUTLASS grouped GEMM.

CUDA Kernel Benchmarking Library

HIP Kernel Benchmarking Library

AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and versatility of software and hardware.

Fast, differentiable sorting and ranking in PyTorch

Our insights of Openpilot, a deepdive project on it

[ECCV 2022] ST-P3, an end-to-end vision-based autonomous driving framework via spatial-temporal feature learning.

[NeurIPS 2022] Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline.

OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving

Official implementation of paper "Pyramid Diffusion for Fine 3D Large Scene Generation" (ECCV 2024 Oral)

PyTorch Implementation of "Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model"

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds