diff --git a/README.md b/README.md index 7706fc472..8d4e0a8f1 100644 --- a/README.md +++ b/README.md @@ -15,7 +15,7 @@ __SuperBench__ is a validation and profiling tool for AI infrastructure. -📢 [v0.10.0](https://github.com/microsoft/superbenchmark/releases/tag/v0.10.0) has been released! +📢 [v0.11.0](https://github.com/microsoft/superbenchmark/releases/tag/v0.11.0) has been released! ## _Check [aka.ms/superbench](https://aka.ms/superbench) for more details._ diff --git a/docs/getting-started/installation.mdx b/docs/getting-started/installation.mdx index cf48c4caa..30fdee829 100644 --- a/docs/getting-started/installation.mdx +++ b/docs/getting-started/installation.mdx @@ -61,7 +61,7 @@ You can clone the source from GitHub and build it. :::note Note You should checkout corresponding tag to use release version, for example, -`git clone -b v0.10.0 https://github.com/microsoft/superbenchmark` +`git clone -b v0.11.0 https://github.com/microsoft/superbenchmark` ::: ```bash diff --git a/docs/getting-started/run-superbench.md b/docs/getting-started/run-superbench.md index a6bb3bc1e..73f00c9c0 100644 --- a/docs/getting-started/run-superbench.md +++ b/docs/getting-started/run-superbench.md @@ -27,7 +27,7 @@ sb deploy -f remote.ini --host-password [password] :::note Note You should deploy corresponding Docker image to use release version, for example, -`sb deploy -f local.ini -i superbench/superbench:v0.10.0-cuda12.2` +`sb deploy -f local.ini -i superbench/superbench:v0.11.0-cuda12.4` You should note that version of git repo only determines version of sb CLI, and not the sb container. You should define the container version even if you specified a release version for the git clone. diff --git a/docs/superbench-config.mdx b/docs/superbench-config.mdx index b8ad058fa..102b8d69f 100644 --- a/docs/superbench-config.mdx +++ b/docs/superbench-config.mdx @@ -70,7 +70,7 @@ superbench: ```yaml -version: v0.10 +version: v0.11 superbench: enable: benchmark_1 monitor: diff --git a/docs/user-tutorial/container-images.mdx b/docs/user-tutorial/container-images.mdx index ffca22796..58a8079d7 100644 --- a/docs/user-tutorial/container-images.mdx +++ b/docs/user-tutorial/container-images.mdx @@ -30,6 +30,9 @@ available tags are listed below for all stable versions. | Tag | Description | |--------------------|-------------------------------------| +| v0.11.0-cuda12.4 | SuperBench v0.11.0 with CUDA 12.4 | +| v0.11.0-cuda12.2 | SuperBench v0.11.0 with CUDA 12.2 | +| v0.11.0-cuda11.1.1 | SuperBench v0.11.0 with CUDA 11.1.1 | | v0.10.0-cuda12.2 | SuperBench v0.10.0 with CUDA 12.2 | | v0.10.0-cuda11.1.1 | SuperBench v0.10.0 with CUDA 11.1.1 | | v0.9.0-cuda12.1 | SuperBench v0.9.0 with CUDA 12.1 | @@ -50,6 +53,9 @@ available tags are listed below for all stable versions. | Tag | Description | |-------------------------------|--------------------------------------------------| +| v0.11.0-rocm6.2 | SuperBench v0.11.0 with ROCm 6.2 | +| v0.11.0-rocm6.0 | SuperBench v0.11.0 with ROCm 6.0 | +| v0.10.0-rocm6.0 | SuperBench v0.10.0 with ROCm 6.0 | | v0.10.0-rocm5.7 | SuperBench v0.10.0 with ROCm 5.7 | | v0.9.0-rocm5.1.3 | SuperBench v0.9.0 with ROCm 5.1.3 | | v0.9.0-rocm5.1.1 | SuperBench v0.9.0 with ROCm 5.1.1 | diff --git a/docs/user-tutorial/data-diagnosis.md b/docs/user-tutorial/data-diagnosis.md index 46eaeda18..80278e7da 100644 --- a/docs/user-tutorial/data-diagnosis.md +++ b/docs/user-tutorial/data-diagnosis.md @@ -65,7 +65,7 @@ superbench: example: ```yaml # SuperBench rules -version: v0.10 +version: v0.11 superbench: rules: failure-rule: diff --git a/docs/user-tutorial/result-summary.md b/docs/user-tutorial/result-summary.md index a85ec7863..8893f559c 100644 --- a/docs/user-tutorial/result-summary.md +++ b/docs/user-tutorial/result-summary.md @@ -58,7 +58,7 @@ superbench: ```yaml title="Example" # SuperBench rules -version: v0.10 +version: v0.11 superbench: rules: kernel_launch: diff --git a/superbench/__init__.py b/superbench/__init__.py index e1f4234fd..cbd47c45e 100644 --- a/superbench/__init__.py +++ b/superbench/__init__.py @@ -6,5 +6,5 @@ Provide hardware and software benchmarks for AI systems. """ -__version__ = '0.10.0' +__version__ = '0.11.0' __author__ = 'Microsoft' diff --git a/superbench/config/amd_mi100_hpe.yaml b/superbench/config/amd_mi100_hpe.yaml index 9aec785f5..0388fcda8 100644 --- a/superbench/config/amd_mi100_hpe.yaml +++ b/superbench/config/amd_mi100_hpe.yaml @@ -3,7 +3,7 @@ # Server: # - Product: HPE Apollo 6500 -version: v0.10 +version: v0.11 superbench: enable: null var: diff --git a/superbench/config/amd_mi100_z53.yaml b/superbench/config/amd_mi100_z53.yaml index 7e56d1a33..4ed8addf6 100644 --- a/superbench/config/amd_mi100_z53.yaml +++ b/superbench/config/amd_mi100_z53.yaml @@ -4,7 +4,7 @@ # - Product: G482-Z53 # - Link: https://www.gigabyte.cn/FileUpload/Global/MicroSite/553/G482-Z53.html -version: v0.10 +version: v0.11 superbench: enable: null var: diff --git a/superbench/config/azure/inference/standard_nc64as_t4_v3.yaml b/superbench/config/azure/inference/standard_nc64as_t4_v3.yaml index 7624a86de..b9d57bfbc 100644 --- a/superbench/config/azure/inference/standard_nc64as_t4_v3.yaml +++ b/superbench/config/azure/inference/standard_nc64as_t4_v3.yaml @@ -1,4 +1,4 @@ -version: v0.10 +version: v0.11 superbench: enable: null monitor: diff --git a/superbench/config/azure/inference/standard_nc96ads_a100_v4.yaml b/superbench/config/azure/inference/standard_nc96ads_a100_v4.yaml index befcd1783..224508e0d 100644 --- a/superbench/config/azure/inference/standard_nc96ads_a100_v4.yaml +++ b/superbench/config/azure/inference/standard_nc96ads_a100_v4.yaml @@ -1,4 +1,4 @@ -version: v0.10 +version: v0.11 superbench: enable: null monitor: diff --git a/superbench/config/azure/inference/standard_nv18ads_a10_v5.yaml b/superbench/config/azure/inference/standard_nv18ads_a10_v5.yaml index af19e0a22..e44510b27 100644 --- a/superbench/config/azure/inference/standard_nv18ads_a10_v5.yaml +++ b/superbench/config/azure/inference/standard_nv18ads_a10_v5.yaml @@ -1,4 +1,4 @@ -version: v0.10 +version: v0.11 superbench: enable: null monitor: diff --git a/superbench/config/azure_ndmv4.yaml b/superbench/config/azure_ndmv4.yaml index 3ef0c399a..7d7a8f185 100644 --- a/superbench/config/azure_ndmv4.yaml +++ b/superbench/config/azure_ndmv4.yaml @@ -3,7 +3,7 @@ # Azure NDm A100 v4 # reference: https://docs.microsoft.com/en-us/azure/virtual-machines/ndm-a100-v4-series -version: v0.10 +version: v0.11 superbench: enable: null monitor: diff --git a/superbench/config/azure_ndv4.yaml b/superbench/config/azure_ndv4.yaml index 921a446b8..b095d5c23 100644 --- a/superbench/config/azure_ndv4.yaml +++ b/superbench/config/azure_ndv4.yaml @@ -1,5 +1,5 @@ # SuperBench Config -version: v0.10 +version: v0.11 superbench: enable: null monitor: diff --git a/superbench/config/default.yaml b/superbench/config/default.yaml index 9533806cd..601136e9f 100644 --- a/superbench/config/default.yaml +++ b/superbench/config/default.yaml @@ -1,5 +1,5 @@ # SuperBench Config -version: v0.10 +version: v0.11 superbench: enable: null monitor: diff --git a/website/blog/2024-09-20-release-0-11.md b/website/blog/2024-09-20-release-0-11.md new file mode 100644 index 000000000..308e78dc1 --- /dev/null +++ b/website/blog/2024-09-20-release-0-11.md @@ -0,0 +1,44 @@ +--- +slug: release-sb-v0.11 +title: Releasing SuperBench v0.11 +author: Peng Cheng +author_title: SuperBench Team +author_url: https://github.com/cp5555 +author_image_url: https://github.com/cp5555.png +tags: [superbench, announcement, release] +--- + +We are very happy to announce that **SuperBench 0.11.0 version** is officially released today! + +You can install and try superbench by following [Getting Started Tutorial](https://microsoft.github.io/superbenchmark/docs/getting-started/installation). + +## SuperBench 0.11.0 Release Notes + +### SuperBench Improvements + +- Add CUDA 12.4 dockerfile. +- Upgrade nccl version to v2.23.4 and install ucx v1.16.0 in cuda 12.4 dockefile. +- Fix MSCCL build error in CUDA12.4 docker build pipeline. +- Add ROCm6.2 dockerfile. +- Update hpcx link in cuda11.1 dockerfile to fix docker build failure. +- Improve document (Fix metrics name and typos in user tutorial, add BibTeX in README and repo). +- Limit protobuf version to be 3.20.x to fix onnxruntime dependency error. +- Update omegaconf version to 2.3.0 and fix issues caused by omegaconf version update. +- Fix MSCCL build error in CUDA12.4 docker build pipeline. +- Update Docker Exec Command for Persistent HPCX Environment. +- Fix cuda 12.2 dockerfile LD_LIBRARY_PATH issue. +- Use types-setuptools to replace types-pkg_resources. +- Add configuration for NDv5 H100 and AMD MI300x. + +### Micro-benchmark Improvements + +- Add hipblasLt tuning to dist-inference cpp implementation. +- Add support for NVIDIA L4/L40/L40s GPUs in gemm-flops. +- Upgrade mlc to v3.11. + +## Model-benchmark Improvements + +- Support FP8 transformer model training in ROCm6.2 dockerfile. + +### Result Analysis +- Fix bug of failure test and warning of pandas in data diagnosis. diff --git a/website/docusaurus.config.js b/website/docusaurus.config.js index a533084e3..41ed52665 100644 --- a/website/docusaurus.config.js +++ b/website/docusaurus.config.js @@ -101,7 +101,7 @@ module.exports = { announcementBar: { id: 'supportus', content: - '📢 v0.10.0 has been released! ' + + '📢 v0.11.0 has been released! ' + '⭐️ If you like SuperBench, give it a star on GitHub! ⭐️', }, algolia: { diff --git a/website/package-lock.json b/website/package-lock.json index b4652de12..ba0c41478 100644 --- a/website/package-lock.json +++ b/website/package-lock.json @@ -1,6 +1,6 @@ { "name": "superbench-website", - "version": "0.10.0", + "version": "0.11.0", "lockfileVersion": 1, "requires": true, "dependencies": { diff --git a/website/package.json b/website/package.json index f2bb9ed76..8aa4c78b8 100644 --- a/website/package.json +++ b/website/package.json @@ -1,6 +1,6 @@ { "name": "superbench-website", - "version": "0.10.0", + "version": "0.11.0", "private": true, "scripts": { "docusaurus": "docusaurus", @@ -38,4 +38,4 @@ "last 1 safari version" ] } -} \ No newline at end of file +}