dbyoung18

ao

Custom data types and layouts for training and inference

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

inference

Reference implementations of MLPerf™ inference benchmarks

inference_results_v1.1

intel-extension-for-deepspeed

Intel® Extension for DeepSpeed* is an extension that brings Intel GPU (XPU) support to DeepSpeed.

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.

training

Reference implementations of MLPerf™ training benchmarks

pai

Resource scheduling and cluster management for AI

dbyoung18/ao

Custom data types and layouts for training and inference

dbyoung18/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

dbyoung18/DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

dbyoung18/gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

dbyoung18/inference

Reference implementations of MLPerf™ inference benchmarks

dbyoung18/inference_results_v1.1

dbyoung18/intel-extension-for-deepspeed

Intel® Extension for DeepSpeed* is an extension that brings Intel GPU (XPU) support to DeepSpeed.

dbyoung18/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.

dbyoung18/training

Reference implementations of MLPerf™ training benchmarks

dbyoung18/KE-complex_modifications

Karabiner-Elements complex_modifications rules

dbyoung18/mlx

MLX: An array framework for Apple silicon

dbyoung18/safetensors

Simple, safe way to store and distribute tensors

dbyoung18/TensorRT

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

dbyoung18/training_results_v2.1

dbyoung18/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

dbyoung18/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

dbyoung18/warp-transducer

A fast parallel implementation of RNN Transducer.

dbyoung18/xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.