saymrwulf/onnxruntime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-03 03:58:54 +00:00

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Find a file

luoyu-intel 5f00bc9931 Integrate high-performance x64 gemm library to MLAS (#17669 ) ### Description Improve MLAS to support high-performance x64 INT4 kernels ### Motivation and Context 1. improve LLM inference performance on Intel CPUs. 2. support more 4bit quantization types: nf4, fp4 3. support dynamic block size: block size aligned with kernel's tiling size(e.g. 4 for VNNI kernel), per channel on N dimension 4. support most Intel ISAs: avx2, avx_vnni, avx512f, avx512_vnni, amx_bf16, amx_int8, avx512_fp16 5. support MatMulNBits' data format ### Tasks - [x] support block_size: 32, 128, -1(per channel) - [x] get weight pack size without memory allocation - [x] use ort's thread pool for parallelism - [x] support ISAs: avx2, avx512f, avx_vnni, avx512_vnni, amx_int8 ### Benchmark Ubuntu 20.22 + Intel(R) Xeon(R) Platinum 8480+ 56 cores Benchmark \| Time \| CPU \| Iterations -- \| -- \| -- \| -- Q4GEMM_Jblas/Q4G32SymInt8/M:1/N:4096/K:4096/Threads:56/real_time \| 47613 \| 47401 \| 12970 Q4GEMM_Jblas/Q4G32SymInt8/M:1024/N:4096/K:4096/Threads:56/real_time \| 6347792 \| 6317562 \| 109 Q4GEMM_Jblas/Q4G32SymInt8/M:2048/N:4096/K:4096/Threads:56/real_time \| 11814014 \| 11757847 \| 59 Q4GEMM_Jblas/Q4G128SymInt8/M:1/N:4096/K:4096/Threads:56/real_time \| 50222 \| 50031 \| 13759 Q4GEMM_Jblas/Q4G128SymInt8/M:1024/N:4096/K:4096/Threads:56/real_time \| 2038222 \| 2028743 \| 341 Q4GEMM_Jblas/Q4G128SymInt8/M:2048/N:4096/K:4096/Threads:56/real_time \| 3792832 \| 3774485 \| 191 Q4GEMM_Jblas/Q4GPerNSymInt8/M:1/N:4096/K:4096/Threads:56/real_time \| 58717 \| 58501 \| 11467 Q4GEMM_Jblas/Q4GPerNSymInt8/M:1024/N:4096/K:4096/Threads:56/real_time \| 1360846 \| 1354598 \| 543 Q4GEMM_Jblas/Q4GPerNSymInt8/M:2048/N:4096/K:4096/Threads:56/real_time \| 2564232 \| 2551365 \| 266 Q4GEMM_Jblas/Q4G32SymFp32/M:1/N:4096/K:4096/Threads:56/real_time \| 57929 \| 57694 \| 12047 Q4GEMM_Jblas/Q4G32SymFp32/M:1024/N:4096/K:4096/Threads:56/real_time \| 5495330 \| 5465810 \| 126 Q4GEMM_Jblas/Q4G32SymFp32/M:2048/N:4096/K:4096/Threads:56/real_time \| 10676240 \| 10617817 \| 66 Q4GEMM_Jblas/Q4G128SymFp32/M:1/N:4096/K:4096/Threads:56/real_time \| 68305 \| 68047 \| 10026 Q4GEMM_Jblas/Q4G128SymFp32/M:1024/N:4096/K:4096/Threads:56/real_time \| 5504862 \| 5476215 \| 126 Q4GEMM_Jblas/Q4G128SymFp32/M:2048/N:4096/K:4096/Threads:56/real_time \| 11758623 \| 11697337 \| 66 Q4GEMM_Jblas/Q4GPerNSymFp32/M:1/N:4096/K:4096/Threads:56/real_time \| 67713 \| 67451 \| 10298 Q4GEMM_Jblas/Q4GPerNSymFp32/M:1024/N:4096/K:4096/Threads:56/real_time \| 5508325 \| 5480237 \| 126 Q4GEMM_Jblas/Q4GPerNSymFp32/M:2048/N:4096/K:4096/Threads:56/real_time \| 10738528 \| 10681656 \| 64 Q4GEMM_Jblas/Q4G32AsymFp32/M:1/N:4096/K:4096/Threads:56/real_time \| 60708 \| 60486 \| 11321 Q4GEMM_Jblas/Q4G32AsymFp32/M:1024/N:4096/K:4096/Threads:56/real_time \| 5523784 \| 5495736 \| 126 Q4GEMM_Jblas/Q4G32AsymFp32/M:2048/N:4096/K:4096/Threads:56/real_time \| 10829633 \| 10772161 \| 67 Reference: Benchmark \| Time \| CPU \| Iterations -- \| -- \| -- \| -- Q4GEMM/Q4Sym/M:1/N:4096/K:4096/Threads:56/real_time \| 53088 \| 52911 \| 13364 Q4GEMM/Q4Sym/M:1024/N:4096/K:4096/Threads:56/real_time \| 6268981 \| 6230335 \| 110 Q4GEMM/Q4Sym/M:2048/N:4096/K:4096/Threads:56/real_time \| 11701237 \| 11632339 \| 59 Win11+12900K 8 cores: Benchmark \| Time \| CPU \| Iterations -- \| -- \| -- \| -- Q4GEMM_Jblas/Q4G32SymInt8/M:1/N:4096/K:4096/Threads:8/real_time \| 215976 \| 211295 \| 2884 Q4GEMM_Jblas/Q4G32SymInt8/M:1024/N:4096/K:4096/Threads:8/real_time \| 60960590 \| 60937500 \| 10 Q4GEMM_Jblas/Q4G32SymInt8/M:2048/N:4096/K:4096/Threads:8/real_time \| 1.18E+08 \| 1.19E+08 \| 5 Q4GEMM_Jblas/Q4G32SymInt8/M:1/N:11008/K:4096/Threads:8/real_time \| 470377 \| 453059 \| 1414 Q4GEMM_Jblas/Q4G32SymInt8/M:1024/N:11008/K:4096/Threads:8/real_time \| 1.54E+08 \| 1.53E+08 \| 5 Q4GEMM_Jblas/Q4G32SymInt8/M:2048/N:11008/K:4096/Threads:8/real_time \| 3.18E+08 \| 3.13E+08 \| 2 Q4GEMM_Jblas/Q4G32SymInt8/M:1/N:4096/K:11008/Threads:8/real_time \| 569072 \| 559398 \| 1229 Q4GEMM_Jblas/Q4G32SymInt8/M:1024/N:4096/K:11008/Threads:8/real_time \| 1.54E+08 \| 1.52E+08 \| 4 Q4GEMM_Jblas/Q4G32SymInt8/M:2048/N:4096/K:11008/Threads:8/real_time \| 3.22E+08 \| 3.28E+08 \| 2 Q4GEMM_Jblas/Q4G32SymInt8/M:1/N:11008/K:11008/Threads:8/real_time \| 1486055 \| 1473325 \| 403 Q4GEMM_Jblas/Q4G32SymInt8/M:1024/N:11008/K:11008/Threads:8/real_time \| 4.14E+08 \| 4.14E+08 \| 2 Q4GEMM_Jblas/Q4G32SymInt8/M:2048/N:11008/K:11008/Threads:8/real_time \| 8.88E+08 \| 8.59E+08 \| 1 --------- Signed-off-by: Mengni Wang <mengni.wang@intel.com> Co-authored-by: Mengni Wang <mengni.wang@intel.com>		2023-12-19 09:36:31 -08:00
.config	Update tsaoptions.json: update the email alias (#13448 )	2022-10-26 15:56:16 -07:00
.devcontainer
.gdn	Update win-ci-pipeline.yml: enable xnnpack tests (#16244 )	2023-06-14 19:12:42 -07:00
.github	Bump actions/stale from 8.0.0 to 9.0.0 (#18774 )	2023-12-18 14:59:03 -08:00
.pipelines	Update windowsai-steps.yml: enable "/profile" linker flag (#18022 )	2023-12-13 19:47:04 -08:00
.vscode	Setup default python formatter for new python plugin (#18563 )	2023-11-24 18:04:48 +08:00
cgmanifests	Update absl and googletest (#18827 )	2023-12-14 16:15:07 -08:00
cmake	Integrate high-performance x64 gemm library to MLAS (#17669 )	2023-12-19 09:36:31 -08:00
csharp	Readd basetargets in Microsoft.ML.OnnxRuntime.csproj (#18789 )	2023-12-14 14:44:11 +08:00
dockerfiles	Update dockerfiles/Dockerfile.source to avoid installing onnx (#17975 )	2023-10-20 09:24:21 -07:00
docs	Integrate high-performance x64 gemm library to MLAS (#17669 )	2023-12-19 09:36:31 -08:00
include/onnxruntime/core	Allow layer-wise recompute (#18566 )	2023-12-12 08:44:05 +08:00
java	[java] Make the backing byte buffer in an OrtValue accessible (#16578 )	2023-10-17 10:03:49 -07:00
js	[REACT NATIVE] Bugfix -> casing Podfile (#18861 )	2023-12-19 10:20:46 +10:00
objectivec	Objective-C API updates (#18738 )	2023-12-07 16:47:46 -08:00
onnxruntime	Integrate high-performance x64 gemm library to MLAS (#17669 )	2023-12-19 09:36:31 -08:00
orttraining	Improve perf for stage3 training (#18099 )	2023-12-15 13:32:19 +08:00
rust	Fix rust compile issues and add GH action to run build validations and tests (#18346 )	2023-11-09 04:26:02 -08:00
samples	Removed all the deprecated python training code and related tests and utils (#18333 )	2023-11-17 18:19:21 -08:00
tools	Fix nightly pipeline failure (#18867 )	2023-12-19 09:18:00 -08:00
winml	Update winml to use #cores - #soc cores by Default as the number of intraopthreads (#18384 )	2023-11-28 09:26:48 -08:00
.clang-format	Prevent GSL_SUPPRESS arguments from being modified by clang-format (#17242 )	2023-08-22 18:26:53 -07:00
.clang-tidy
.dockerignore
.gitattributes
.gitignore	Build onnxruntime.dll as arm64x (#18633 )	2023-12-06 16:49:00 -08:00
.gitmodules	Remove onnxruntime extensions from list of gitmodules (#17615 )	2023-09-19 17:12:14 -07:00
.lintrunner.toml	FP16 optimizer automatically detect DeepSpeed compatibility (#18084 )	2023-10-25 15:11:02 +08:00
build.bat	try to find patch.exe in git default installation folder (#17106 )	2023-08-10 21:48:13 -07:00
build.sh	Upgrade old Python version in packaging pipeline (#16667 )	2023-07-17 08:24:47 -07:00
build_arm64x.bat	Build onnxruntime.dll as arm64x (#18633 )	2023-12-06 16:49:00 -08:00
CITATION.cff
CODEOWNERS	Add owners for public facing API files (#15288 )	2023-03-30 17:16:15 -07:00
CONTRIBUTING.md	Fix link to High Level Design (#11786 )	2023-02-28 11:05:54 -08:00
lgtm.yml	Fix lgtm C++ error (#13613 )	2022-11-10 10:06:22 -08:00
LICENSE
NuGet.config
ort.wprp
ORT_icon_for_light_bg.png
packages.config	Bump DirectML version from 1.12.0 to 1.12.1 (#17225 )	2023-08-20 09:55:38 -07:00
pyproject.toml	[ORTModule] ATen Efficient Attention and Triton Flash Attention (#17959 )	2023-10-27 10:29:27 +08:00
README.md	Remove "Python Checks" pipeline status from readme as that pipeline no longer exists. (#18697 )	2023-12-04 13:38:36 -08:00
requirements-dev.txt	ONNX 1.15 integration (#17125 )	2023-09-26 14:44:48 -07:00
requirements-doc.txt
requirements-lintrunner.txt	Bump linter versions (#18341 )	2023-11-08 13:04:40 -08:00
requirements-training.txt	ONNX 1.15 integration (#17125 )	2023-09-26 14:44:48 -07:00
requirements.txt.in
SECURITY.md
setup.py	Improve perf for stage3 training (#18099 )	2023-12-15 13:32:19 +08:00
ThirdPartyNotices.txt	Flash Attention v2 MHA (#17227 )	2023-08-31 13:52:21 -07:00
VERSION_NUMBER	Bump Up Version to 1.17.0 (#17587 )	2023-09-20 11:02:58 +08:00

README.md

ONNX Runtime is a cross-platform inference and training machine-learning accelerator.

ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms. Learn more →

ONNX Runtime training can accelerate the model training time on multi-node NVIDIA GPUs for transformer models with a one-line addition for existing PyTorch training scripts. Learn more →

Get Started & Resources

General Information: onnxruntime.ai
Usage documention and tutorials: onnxruntime.ai/docs
YouTube video tutorials: youtube.com/@ONNXRuntime
Upcoming Release Roadmap
Companion sample repositories:
- ONNX Runtime Inferencing: microsoft/onnxruntime-inference-examples
- ONNX Runtime Training: microsoft/onnxruntime-training-examples

Builtin Pipeline Status

System	Inference	Training
Windows
Linux
Mac
Android
iOS
Web
Other

Third-party Pipeline Status

System	Inference	Training
Linux

Data/Telemetry

Windows distributions of this project may collect usage data and send it to Microsoft to help improve our products and services. See the privacy statement for more details.

Contributions and Feedback

We welcome contributions! Please see the contribution guidelines.

For feature requests or bug reports, please file a GitHub Issue.

For general discussion or questions, please use GitHub Discussions.

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

License

This project is licensed under the MIT License.