A validation and profiling tool for AI infrastructure
Перейти к файлу
Yifan Xiong 1ad1c21c38
Dockerfile - Upgrade Docker image to CUDA 12.2 (#577)
Upgrade Docker image to CUDA 12.2 for H100:
* upgrade base image to 23.10
* fix onnxruntime version in python3.10
* fix compilation errors
2023-11-22 13:48:18 +00:00
.azure-pipelines Benchmarks: Micro benchmark - Add hipBLASLt function benchmark (#576) 2023-11-22 19:48:10 +08:00
.devcontainer Update Python setup for require packages (#387) 2022-08-17 11:33:57 +08:00
.github Dockerfile - Upgrade Docker image to CUDA 12.2 (#577) 2023-11-22 13:48:18 +00:00
.vscode Docs - Add config and docs for development experience (#155) 2021-08-16 13:49:19 +08:00
dockerfile Dockerfile - Upgrade Docker image to CUDA 12.2 (#577) 2023-11-22 13:48:18 +00:00
docs Analyzer - Generate baseline given results from multiple nodes. (#575) 2023-11-22 14:42:32 +08:00
examples/benchmarks Benchmarks - Add distributed inference benchmark (#493) 2023-03-24 17:15:17 +08:00
superbench Dockerfile - Upgrade Docker image to CUDA 12.2 (#577) 2023-11-22 13:48:18 +00:00
tests Benchmarks: Micro benchmark - add initialization options for rocm gemm flops (#578) 2023-11-22 12:52:22 +00:00
third_party Benchmarks: Micro benchmark - Add hipBLASLt function benchmark (#576) 2023-11-22 19:48:10 +08:00
website Analyzer - Generate baseline given results from multiple nodes. (#575) 2023-11-22 14:42:32 +08:00
.clang-format Benchmarks: Add Benchmark - Add the source code of cuda kernel launch overhead benchmark. (#71) 2021-05-18 14:07:27 +08:00
.codecov.yml Benchmarks: micro benchmarks - add python code for DirectXGPUCoreFlops (#542) 2023-07-05 16:56:21 +08:00
.dockerignore CLI - Update version to include revision hash and date (#427) 2022-10-31 10:44:41 +08:00
.editorconfig Docs - Add config and docs for development experience (#155) 2021-08-16 13:49:19 +08:00
.flake8 Setup: Revision - Update lint rules (#7) 2021-02-01 14:12:02 +08:00
.gitattributes Setup: Init - Initialize setup.py and basic configs (#4) 2021-01-28 21:01:28 +08:00
.gitignore Benchmarks: micro benchmark - source code for evaluating NVDEC decoding performance (#560) 2023-08-22 10:56:33 +00:00
.gitmodules Benchmarks: Add Feature - Add GPU-Burn as microbenchmark (#324) 2022-03-16 16:20:11 +08:00
.mypy.ini Config - Add inference config for NC A100 and NV A10 series (#329) 2022-03-21 14:24:37 +08:00
.pre-commit-config.yaml Setup: Init - Initialize setup.py and basic configs (#4) 2021-01-28 21:01:28 +08:00
.style.yapf Setup: Revision - Update lint rules (#7) 2021-02-01 14:12:02 +08:00
CODE_OF_CONDUCT.md Initial CODE_OF_CONDUCT.md commit 2020-12-16 18:22:21 -08:00
LICENSE Initial LICENSE commit 2020-12-16 18:22:25 -08:00
MANIFEST.in Bug bash - Fix bugs in multi GPU benchmarks (#98) 2021-06-23 18:16:43 +08:00
Makefile Dockerfile - Add SuperBench Windows Dockerfile (#534) 2023-06-28 05:35:11 +00:00
README.md Release - SuperBench v0.9.0 (#558) 2023-07-27 10:42:31 +08:00
SECURITY.md Setup: Init - Initialize setup.py and basic configs (#4) 2021-01-28 21:01:28 +08:00
SUPPORT.md Docs - Initialize README (#6) 2021-02-01 20:21:12 +08:00
setup.py Dockerfile - Upgrade Docker image to CUDA 12.2 (#577) 2023-11-22 13:48:18 +00:00

README.md

SuperBench

Build Image Codecov Website Latest Release Docker Pulls License

Azure Pipelines Build Status
cpu-unit-test Build Status
cuda-unit-test Build Status
ansible-integration-test Build Status

SuperBench is a validation and profiling tool for AI infrastructure.

📢 v0.9.0 has been released!

Check aka.ms/superbench for more details.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.