Pinned Repositories
accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
AITemplate
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
alband_subclass_zoo
fork of AlbanD'S subclass zoo
ao
torchao
ArchBenchSuite
low level kernels to benchmark peak compute, cache bandwidth on various levels, memory bandwidth, and some basic compute routines
attention-gym
Helpful tools and examples for working with flex-attention
benchmark
TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.
ClassyVision
An end-to-end PyTorch framework for image and video classification
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
sanchitintel's Repositories
sanchitintel/ArchBenchSuite
low level kernels to benchmark peak compute, cache bandwidth on various levels, memory bandwidth, and some basic compute routines
sanchitintel/FBGEMM
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
sanchitintel/hydra
Hydra is a framework for elegantly configuring complex applications
sanchitintel/kineto
A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.
sanchitintel/lazy-tensor-samples
Code samples using features from PyTorch's Lazy Tensor Core
sanchitintel/membench
Bert Maher's membench
sanchitintel/memkind
sanchitintel/nanoBench
A tool for running small microbenchmarks on recent Intel and AMD x86 CPUs.
sanchitintel/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
sanchitintel/pmu-tools
Intel PMU profiling tools
sanchitintel/taskflow
A General-purpose Parallel and Heterogeneous Task Programming System
sanchitintel/torchdynamo
sanchitintel/transformers
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.