ROCm / apexLinks
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
☆22Updated this week
Alternatives and similar repositories for apex
Users that are interested in apex are comparing it to the libraries listed below
Sorting:
- ☆36Updated this week
- oneCCL Bindings for Pytorch*☆97Updated last month
- Ahead of Time (AOT) Triton Math Library☆64Updated last week
- RCCL Performance Benchmark Tests☆67Updated 2 weeks ago
- Bandwidth test for ROCm☆56Updated 2 weeks ago
- An extension library of WMMA API (Tensor Core API)☆97Updated 10 months ago
- ☆24Updated last month
- A CUTLASS implementation using SYCL☆23Updated last week
- Development repository for the Triton language and compiler☆122Updated this week
- Benchmarks to capture important workloads.☆31Updated 4 months ago
- OpenAI Triton backend for Intel® GPUs☆189Updated this week
- ☆88Updated 5 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆79Updated this week
- Test suite for probing the numerical behavior of NVIDIA tensor cores☆38Updated 10 months ago
- ROCm Tracer Callback/Activity Library for Performance tracing AMD GPUs☆83Updated last week
- ☆96Updated 8 months ago
- ROCm BLAS marshalling library☆142Updated this week
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆95Updated 2 weeks ago
- ☆208Updated 10 months ago
- Fast and memory-efficient exact attention☆173Updated this week
- ☆97Updated last year
- ☆20Updated 2 months ago
- RDC☆29Updated this week
- Experimental projects related to TensorRT☆105Updated last week
- hipBLASLt is a library that provides general matrix-matrix operations with a flexible API and extends functionalities beyond a traditiona…☆97Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆109Updated 10 months ago
- oneAPI Collective Communications Library (oneCCL)☆234Updated 2 weeks ago
- Stretching GPU performance for GEMMs and tensor contractions.☆242Updated last week
- ROC profiler library. Profiling with perf-counters and derived metrics.☆148Updated last week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆11Updated 11 months ago