#cplusplus #cuda #physics_engine #artificial_life #agent_based_simulation #open_ended_evolution

https://github.com/chrxh/alien

#cuda #training #inference #transformer #bart #beam_search #sampling #bert #multilingual_nmt #gpt_2 #diverse_decoding

https://github.com/bytedance/lightseq

#cplusplus #3d #3d_perception #arm #computer_graphics #cpp #cuda #gpu #gui #machine_learning #mesh_processing #odometry #opengl #pointcloud #python #pytorch #reconstruction #registration #rendering #tensorflow #visualization

https://github.com/isl-org/Open3D

#cplusplus #cuda #deep_learning #deep_neural_networks #distributed #machine_learning #ml #neural_network

https://github.com/Oneflow-Inc/oneflow

#cplusplus #cuda #deep_learning #gpu #mlp #nerf #neural_network #real_time #rendering

https://github.com/NVlabs/tiny-cuda-nn

#cuda #3d_reconstruction #computer_graphics #computer_vision #function_approximation #machine_learning #nerf #neural_network #real_time #real_time_rendering #realtime #signed_distance_functions

https://github.com/NVlabs/instant-ngp

#cplusplus #cpp #cpp11 #cuda #deep_learning #deep_learning_library #gpu #nvidia

https://github.com/NVIDIA/cutlass

#python #cublas #cuda #cudnn #cupy #curand #cusolver #cusparse #cusparselt #cutensor #gpu #nccl #numpy #nvrtc #nvtx #rocm #scipy #tensor

https://github.com/cupy/cupy

#jupyter_notebook #3d_reconstruction #cuda #instant_ngp #nerf #pytorch #pytorch_lightning

https://github.com/kwea123/ngp_pl

#cuda

https://github.com/19reborn/NeuS2

#python #command_line_tool #console #cuda #curses #gpu #gpu_monitoring #htop #monitoring #monitoring_tool #nvidia #nvidia_smi #nvml #process_monitoring #resource_monitor #top

https://github.com/XuehaiPan/nvitop

#cplusplus #compiler #cuda #jax #machine_learning #mlir #pytorch #runtime #spirv #tensorflow #vulkan

IREE is a tool that helps run Machine Learning (ML) models on different devices, from big data centers to small mobile and edge devices. It uses a special way to convert ML models into a uniform format, making it easier to deploy them anywhere. This tool is still in the early stages but is being actively improved. Using IREE can help you scale your ML models efficiently across various platforms, making it beneficial for developers who need to deploy models in different environments.

https://github.com/iree-org/iree

#python #amd #cuda #gpt #inference #inferentia #llama #llm #llm_serving #llmops #mlops #model_serving #pytorch #rocm #tpu #trainium #transformer #xpu

vLLM is a library that makes it easy, fast, and cheap to use large language models (LLMs). It is designed to be fast with features like efficient memory management, continuous batching, and optimized CUDA kernels. vLLM supports many popular models and can run on various hardware including NVIDIA GPUs, AMD CPUs and GPUs, and more. It also offers seamless integration with Hugging Face models and supports different decoding algorithms. This makes it flexible and easy to use for anyone needing to serve LLMs, whether for research or other applications. You can install vLLM easily with `pip install vllm` and find detailed documentation on their website.

https://github.com/vllm-project/vllm