ZenDNN library, which includes APIs for basic neural network building blocks optimized for AMD CPU architecture, enables deep learning application and framework developers to improve deep learning inference performance on AMD CPUs.
For the current version, refer to the ZenDNN page.
Support
For support options, refer to Technical Support.
- 5.2.1
- 5.2
- 5.1
- 5.0.2
- 5.0.1
- 5.0
- 4.2
- 4.1
- 4.0
- 3.3
5.2.1 Release Highlights
ZenDNN 5.2.1 is an incremental update built on the ZenDNN 5.2 runtime architecture, focusing on expanded LOWOHA (Low Overhead APIs) and advanced quantization capabilities, along with performance improvements for matmul and GEMV workloads across multiple backends.
This release strengthens production readiness through reduced reorder overhead, enhanced profiling and regression benchmarking, and richer BenchDNN test coverage.
Key enhancements include expanded WOQ/U4 quantization with new DLP (Deep Learning Primitives) APIs, deeper integration of dynamic and static quantization into matmul and reorder flows, optimized LOWOHA normalization with fused add + RMS norm and AVX 512 kernels, ISA dependent FP16 matmul enablement via AOCL DLP and oneDNN, LIBXSMM BF16 BRGEMM improvements, and AutoTuner enhancements for improved kernel selection.
The underlying ZenDNN 5.2 platform remains unchanged, retaining its modular multi backend architecture, AutoTuner driven dispatch, unified caching, improved threading for key primitives, and low overhead APIs for small GEMM and fused BF16/FP32/INT8 workloads.
ZenDNN Plugin for PyTorch (zentorch)
Overview
- Incremental release built on the zentorch 5.2.0 foundation.
- Adds PyTorch 2.11.0 support, extends vLLM compatibility (0.15.0–0.18.0), and strengthens asymmetric WOQ and INT8 dynamic quantization capabilities.
Key Improvements
- Framework Support
- Support for PyTorch 2.11.0 (in addition to 2.10.0).
- Extended vLLM compatibility: 0.16.0, 0.17.0, 0.17.1, and 0.18.0.
- Performance & Quantization Enhancements
- Optimized vLLM RMSNorm using C++ CPU kernels.
- Asymmetric WOQ support via TorchAO:
- Int4 weight only quantization (Int4WeightOnlyOpaqueTensorConfig).
- Bias support for asymmetric quantized ops.
- Int4OpaqueTensor support using zentorch.
- Fusion support for quantized linear operators.
- NT8 dynamic quantization:
- Integrated dynamic qlinear operator in zentorch backend.
- Enabled execution of dynamically quantized models via vLLM with zentorch.
- Improved WOQ linear operator performance.
- Infrastructure, Testing & Tooling
- Expanded Hypothesis based testing for qlinear and BMM operations.
- Accuracy benchmarking using the LM Eval framework.
- New zentorch weekly PyPI package for development builds.
- Recommended jemalloc via LD_PRELOAD for DLRMv2 quantized model execution.
- Bug Fixes & Accuracy
- Fixed unit tests for qlinear_mul_add, fused WOQ linear, and BMM hypothesis tests.
Compatibility & Known Issues
- Validated only with torchao==0.16.0 for quantized models.
- No breaking changes; fully backward compatible with zentorch 5.2.0.
- Known issues:
- Possible GLIBCXX conflicts (may require LD_PRELOAD).
- Experimental Python versions (3.13T, 3.14, 3.14T) are not supported.
ZenDNN Plugin for TensorFlow (zentf)
Overview
- Minor incremental release on top of zentf 5.2.0..
- Continues focus on inference performance for Recommender Systems and Large Language Models on AMD EPYC™ CPUs.
TensorFlow & Python Support
- TensorFlow 2.21.0 as the primary supported version with optimal performance.
- Distributed via PyPI (Python wheel) and as a C++ package.
- TensorFlow Java main (75402bef) supported via source build only.
- Python 3.10–3.13 fully supported (Python 3.9 dropped).
Key Improvements
- TF 2.21 Integration
- Built for and validated against TensorFlow v2.21.0.
- Upgraded build system from Bazel 7.4.1 to 7.7.0.
- Aligned Python support with TensorFlow (3.10–3.13).
- TensorFlow Java supported via main branch due to lack of official 2.21 release.
- Backward Build Compatibility (TF 2.16–2.21)
- Single unified codebase supports TensorFlow 2.16.0 through 2.21.0.
- ./configure automatically detects TensorFlow version and applies the correct build setup.
- Version specific configs maintained under version_configs/ (TF 2.19–2.21); TF 2.16–2.18 reuse TF 2.19 settings.
- Bazel and third party dependencies (protobuf, abseil, rules_cc) auto adjust per TensorFlow version.
- Standard build workflow remains unchanged and fully transparent to users.
| Version | Resources |
| 5.2.1 | ZenDNN 5.2.1 User Guide ZenDNN 5.2.1 Support Matrix |
Archive v5.2.1
| ZenDNN Plug-in for PyTorch (Built with PyTorch 2.11.0) |
Description | MD5SUM |
| ZENTORCH_v5.2.1_Python_v3.10.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.10 | 4aa21a5ff400ac6d41bc6cfe5149b31f |
| ZENTORCH_v5.2.1_Python_v3.11.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.11 | 6aa94d2064b8ef10ff9b7232bd192247 |
| ZENTORCH_v5.2.1_Python_v3.12.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.12 | f2ae0bacf0c24dcd19df778184943df6 |
| ZENTORCH_v5.2.1_Python_v3.13.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.13 | b4a4926273950b731369d04a87a4d3ec |
| Note: Above packages can be used for non LLM executions | ||
| ZenDNN Plug-in for PyTorch (Built with PyTorch 2.10.0) |
Description | MD5SUM |
| ZENTORCH_v5.2.1_Python_v3.10.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.10 | 92fa8592cbaaa5314863ac2baa55fb12 |
| ZENTORCH_v5.2.1_Python_v3.11.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.11 | f5073c974aff541e93548421ae6da0a0 |
| ZENTORCH_v5.2.1_Python_v3.12.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.12 | d9d325c2fe558211fd0ff9794e579189 |
| ZENTORCH_v5.2.1_Python_v3.13.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.13 | 0a673ff2d9ed063da85b68589a0dfd9b |
| Note: Above packages can be used for LLM executions with vLLM and non LLM executions | ||
| ZenDNN Plug-in for TensorFlow (Built with TensorFlow 2.21.0) |
Description | MD5SUM |
| ZENTF_v5.2.1_Python_v3.10.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.10 | 14085bffc7bff47f1d53090527847896 |
| ZENTF_v5.2.1_Python_v3.11.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.11 | 1d0a7d4370fbc4249aa69620b46c6458 |
| ZENTF_v5.2.1_Python_v3.12.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.12 | 4a1bef3cc78e5dac7312d162a543670d |
| ZENTF_v5.2.1_Python_v3.13.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.13 | cc1a34607e46e138d2c99beb78989354 |
| ZENTF_v5.2.1_C++_API.zip | This zip file contains the ZenDNN TensorFlow Plug-in with C++ APIs Note: This C++ package cannot be used for TF Java executions |
6a06734604a3b29490a27c547faf0413 |
| ZenDNN Plug-in for TensorFlow (Built with TensorFlow 2.20.0) |
Description | MD5SUM |
| ZENTF_v5.2.1_C++_API.zip | This zip file contains the ZenDNN TensorFlow Plug-in with C++ APIs Note: This C++ package should be used for TensorFlow Java execution |
69d24544b3a577ab37213a9bd4e4a773 |
5.2 Release Highlights
ZenDNN Extension for PyTorch (zentorch):
PyTorch Version Support
- PyTorch 2.10.0: Primary support with optimal performance (available via PyPI)
- Python 3.10 - 3.13: Full compatibility with the supported Python versions of PyTorch
Improvements
1. vLLM Integration
- vLLM-ZenTorch Plugin: Zero-code-changes Plug-and-play automatic acceleration for vLLM V1 inference engine
- vLLM Version Support: vLLM 0.12.0 to 0.15.1
2. Quantized Inference Support
LLM Quantization (Weight-Only Quantization) (Experimental):INT4 quantized inference functional support
RecSys Quantization (DLRM-v2):
- Embedding tables: UINT4 asymmetric per-channel weight-only quantization
- Linear layers: W8A8 quantization (INT8 symmetric per-channel for weights, UINT8 asymmetric per-tensor for activations)
- PyTorch 2 Export (PT2E) quantization framework with performance optimizations
- Custom EmbeddingBagUInt4Quantizer for embedding quantization
- X86InductorQuantizer for linear layer quantization
3. Performance Optimizations
- Improved bfloat16 Performance: AMD EPYC™ specific enhancements for bfloat16 operations
- Enhanced Operations with LOA: Low Overhead API optimizations for improved performance
- Optimized Embedding Kernels: Enhanced embedding bag operations with group op support
- Graph Optimizations: Advanced pattern identification and replacement, concat operation folding support
4. Infrastructure and Testing
- Hypothesis Testing Framework: Expanded test coverage with property-based testing
- NumPy 2.x Compatibility: Updated scripts for NumPy 2.x support
- TORCH_COMPILE_DEBUG Support: Full compatibility with PyTorch debugging tools
- Integrated with New ZenDNN Library: Updated to new ZenDNN library with self-managed dependency building
5. Documentation
- Updated README: Comprehensive documentation updates including:
- vLLM plugin usage instructions
- Weight-only quantization guide
- Profiler output interpretation
- Updated examples and usage patterns
- Example Scripts: Added DLRM-v2 quantization example scripts
ZenDNN Extension for TensorFlow (zentf):
TensorFlow Version Support
- TensorFlow 2.20.0: Primary support with optimal performance (available via PyPI and CPP package)
- TensorFlow-Java main(75402bef): Java User interface - Fully supported (available via source build only)
- Python 3.9 - 3.13: Full compatibility with the supported Python versions of TensorFlow
Improvements
1. TensorFlow 2.20.0 Integration
- zentf 5.2.0 is built for and validated against TensorFlow v2.20.0.
- Bazel 7.4.1: Upgraded from Bazel 5.3-6.5 range to a single supported version (7.4.1).
- Python 3.9 - 3.13: Extended Python version support to include Python 3.13.
- As TF JAVA is not released with 2.20.0 version, zentf is supported with main(75402bef) branch from TensorFlow-Java through source build only.
2. Migrate from legacy ZenDNN library to ZenDNNL
- CMake-based ZenDNNL integration using rules_foreign_cc.
- All operator kernels (MatMul, Conv2D, BatchMatMul, Softmax, Pooling) have been rewritten to use the ZenDNNL Low Overhead API (LOA), replacing the legacy ZenDNN primitives.
- Old third-party dependencies on zen_dnn and amd_blis (BLIS) have been removed, replaced by ZenDNNL with integrated AOCL-DLP.
3. Removed Legacy Components
- Mempool optimization has been completely removed and equivalent performance has been achieved using jemalloc as the memory allocator instead.
- INT8 support has been removed.
- Removal of non-performant ops: ZenTranspose, ZenReshape, Binary ops.
4. Performance Optimizations
- Enhanced Operations with LOA: Low Overhead API optimizations for improved performance
Resources
| Version | Resources |
| 5.2 | ZenDNN 5.2 User Guide ZenDNN 5.2 Support Matrix |
Archive v5.2
| ZenDNN Plug-in for PyTorch | Description | MD5SUM |
| ZENTORCH_v5.2.0_Python_v3.10.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.10 | 01824257b50c1dae2d43bc120d731634 |
| ZENTORCH_v5.2.0_Python_v3.11.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.11 | 17d1524dc923a6bba5220fc576227379 |
| ZENTORCH_v5.2.0_Python_v3.12.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.12 | 3cd58ddf52352e66f48b4d18ccfa4365 |
| ZENTORCH_v5.2.0_Python_v3.13.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.13 | 6cca83b569f36f791bd5a421387ec8c2 |
| ZenDNN Plug-in for TensorFlow | Description | MD5SUM |
| ZENTF_v5.2.0_Python_v3.10.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.10 | 507512ca2cd5f24b32fb595cea4c0b24 |
| ZENTF_v5.2.0_Python_v3.11.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.11 | 5a0f784585ebb3441ef892841befb333 |
| ZENTF_v5.2.0_Python_v3.12.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.12 | 3c2b0e2e16e6634cfe1fe7bee6363991 |
| ZENTF_v5.2.0_Python_v3.13.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.13 | ca1965bd065587c1397b199dce29ba45 |
| ZENTF_v5.2.0_Python_v3.9.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.9 | 5e827f66ed4afff6c84396d9596a4aff |
| ZENTF_v5.2.0_C++_API.zip | This zip file contains the ZenDNN TensorFlow Plug-in with C++ APIs | d4c0888f9037ede2d83f05449009222b |
5.1 Release Highlights
- Framework Compatibility
- PyTorch & TensorFlow: We've added full compatibility with PyTorch 2.7 and TensorFlow 2.19, ensuring seamless integration with the latest versions of these leading AI frameworks.
- vLLM + zentorch Plugin: The new zentorch plugin for vLLM delivers a significant performance uplift of up to 21% on a variety of models compared to vLLM-IPEX.
- Java® Integration: We've enabled support for PluggableDevice in TensorFlow-Java, a feature essential for zentf functionality. This feature has been officially contributed and upstreamed to the TensorFlow-Java repository, strengthening its core capabilities. For more details, please see the TensorFlow-Java integration Blog.
- Performance Optimizations
- Recommender Systems: We've introduced several key optimizations to boost the performance of recommender models, such as DLRMv2.
- EmbeddingBag Improvements: EmbeddingBag Improvements: New "out" variants of EmbeddingBag and related operators now write directly to a shared output buffer, eliminating the need for a separate concatenation operation and improving efficiency.
- Concat Optimization: We've introduced a new optimization that fuses the concatenation operation after Bottom MLP and EmbeddingBag, for the DLRMv2 model.
- New Operator Fusions: We've added new operator fusions to accelerate common computational patterns, resulting in a 25% performance uplift for the DIEN BF16 model.
- MatMul + BiasAdd + Tanh
- MatMul + BiasAdd + Sigmoid
- Kernel Optimizations:
- BF16/FP32 MatMul: A new kernel for BF16/FP32 matrix multiplication has been introduced that eliminates overheads in less compute-intensive GEMM operations, leading to improved performance of the DIEN model.
- Ahead of Time (AOT) Reorder: We now support AOT reordering for MatMul kernels across INT8, BF16, and FP32 data types.
- ZenDNN Enhancements: Added support for MatMul(+fused) Low Overhead API (LOA) to improve performance of small matrix shapes, further improving performance and efficiency.
- Ecosystem Contribution
- We are actively contributing our optimization work directly to the core PyTorch codebase, as well as the PluggableDevice feature to the TensorFlow-Java repository. These regular upstream contributions strengthen the native performance and capabilities of both frameworks, benefiting the entire community.
Resources
Version |
Resources |
| 5.1 | ZenDNN 5.1 User Guide ZenDNN 5.1 Support Matrix |
Archives v5.1
| ZenDNN Plug-in for PyTorch | Description | MD5SUM |
| ZENTORCH_v5.1.0_Python_v3.10.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.10 | da8bf1d3d4f5975ef17d8bffab790f55 |
| ZENTORCH_v5.1.0_Python_v3.11.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.11 | 608699f120980469bd2fc8c5cfb6395f |
| ZENTORCH_v5.1.0_Python_v3.12.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.12 | d119f6e6551083663486367170ebca4d |
| ZENTORCH_v5.1.0_Python_v3.13.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.13 | f8abf43aff5af4790a2977972fbffca0 |
| ZENTORCH_v5.1.0_Python_v3.9.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.9 | 0f858c78272de09b95719c76ab68d1b4 |
| ZenDNN Plug-in for TensorFlow | Description | MD5SUM |
| ZENTF_v5.1.0_Python_v3.10.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.10 | 885c7df96ec9b3f2b3302ab3f7bfdef1 |
| ZENTF_v5.1.0_Python_v3.11.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.11 | 2a77a62d110ae96244f1dc34ddcbda64 |
| ZENTF_v5.1.0_Python_v3.12.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.12 | 81799cd80331155555105efdf10f10aa |
| ZENTF_v5.1.0_Python_v3.9.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.9 | 745fbefd95f761a0fd0cac3bd2339289 |
| ZENTF_v5.1.0_C++_API.zip | This zip file contains the ZenDNN TensorFlow Plug-in with C++ APIs | 1824f52455c76888fca433028f943414 |
5.0.2 Release Highlights
- Framework Compatibility: Fully compatible with PyTorch 2.6 and TensorFlow 2.18.
- Java® Integration: Introduces a Java interface to the TensorFlow plugin (zentf) via TensorFlow Java.
- Optimized Quantized Model Support: Enhanced performance for INT8/INT4-quantized DLRM models.
Resources
| Version | Resources |
| 5.0.2 |
Archives v5.0.2
| Title | Description | MD5SUM |
| ZenDNN Plug-in for PyTorch | ||
| ZENTORCH_v5.0.2_Python_v3.10.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.10 | ad694dae86c827c5069f370a76680c4e |
| ZENTORCH_v5.0.2_Python_v3.11.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.11 | 3a768db8d8e72e14260530b865d4affd |
| ZENTORCH_v5.0.2_Python_v3.12.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.12 | dc4af7dfa8a3223f8f1939e1727c9daa |
| ZENTORCH_v5.0.2_Python_v3.13.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.13 | 5f7cca5a9e8161321bac81c5a4061672 |
| ZENTORCH_v5.0.2_Python_v3.9.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.9 | e67593eeb51e22d3451839aef9b3f9c2 |
| ZenDNN Plug-in for TensorFlow |
||
| ZENTF_v5.0.2_Python_v3.10.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.10 | a5668caa29fffcd4d8dfabb845228e7b |
| ZENTF_v5.0.2_Python_v3.11.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.11 | 6fb4765983a4c9f27d18cd4d670a3d2d |
| ZENTF_v5.0.2_Python_v3.12.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.12 | bbbd9bcccccd87b4f65b515f4076993e |
| ZENTF_v5.0.2_Python_v3.9.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.9 | f99467d7bfd034d6ec4ccb3e2c9998f7 |
| ZENTF_v5.0.2_C++_API.zip | This zip file contains the ZenDNN TensorFlow Plug-in with C++ APIs | 387ce4f857936132d4ca410d66270836 |
5.0.1 Release Highlights
- Compatible with deep-learning frameworks: Aligned closely with PyTorch 2.5 and TensorFlow 2.18, helping ensure smooth upgrades and interoperability.
- Efficient Model Execution: Added support for INT8/INT4-quantized DLRM models in zentorch, unlocking faster inference with lower memory usage compared to BF16-precision. This release supports the MLPerf® version of DLRMv2; support for generic models are planned for the next release.
Resources
| Version | Resources |
| 5.0.1 | ZenDNN 5.0.1 User Guide Support Matrix |
Archives v5.0.1
| Title | Description | MD5SUM |
| ZenDNN Plug-in for PyTorch | ||
| ZENTORCH_v5.0.1_Python_v3.10.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.10 | 8a0fb79874dcfe4537db8e7b898fb3ad |
| ZENTORCH_v5.0.1_Python_v3.11.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.11 | 3452c37545cd7d1748e01d3ba2022810 |
| ZENTORCH_v5.0.1_Python_v3.12.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.12 | 988260afb5ed25d0f2f11b22d08d11f9 |
| ZENTORCH_v5.0.1_Python_v3.9.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.9 | ed674d7526ab244fa31fad57f3b34413 |
| ZenDNN Plug-in for TensorFlow |
||
| ZENTF_v5.0.1_Python_v3.10.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.10 | 227b1bd6680493e683ef51bbc09df007 |
| ZENTF_v5.0.1_Python_v3.11.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.11 | 792b90b68bdc9eb2bbc15d5158bb724c |
| ZENTF_v5.0.1_Python_v3.12.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.12 | 75016fa0d2f05681eac047ec2931a629 |
| ZENTF_v5.0.1_Python_v3.9.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.9 | c134e7da17b6a6e7c89370440a8905ba |
| ZENTF_v5.0.1_C++_API.zip | This zip file contains the ZenDNN TensorFlow Plug-in with C++ APIs | 56687fb93f3fd87e742b49a621b7d050 |
| MLPerf DLRM V2 Benchmark Binaries | ||
| dlrmv2-mlperf-binary-updated.zip | This zip file contains the zentorch wheel file and the necessary scripts to run MLPerf DLRM v2 benchmarking on AMD EPYC. The binary is intended solely for MLPerf DLRM v2 benchmarking purposes on AMD EPYC CPU. For optimized inference performance on AMD EPYC CPUs, please use the ZenDNN software stack. | a94a33a7be43e994def63d3ad5a3d5b1 |
5.0 Release Highlights
- Support for 5th Gen AMD EPYC™ processors, formerly codenamed “Turin”
- Framework Support: PyTorch 2.4.0, TensorFlow 2.17 and ONNXRT 1.19.2
- New APIs in the ZenDNN Plugin for PyTorch (zentorch), such as zentorch.llm.optimize() and zentorch.load_woq_model(), for enhanced LLM performance
- Enhanced matmul operators and fusions and a new BF16 auto-tuning algorithm targeted for generative LLMs.
- An optimized Scalar Dot Product Attention operator including-KV cache performance optimizations tailored to AMD EPYC™ cache architectures
- Support for INT4 Weight-Only-Quantization (WOQ)
- Improved Model Support: Llama3.1 and 3.2, Phi3, ChatGLM3, Qwen2, GPT-J
Release Blog
ZenDNN 5.0: Supercharge AI on AMD EPYC™ Server CPUs
Resources
| Version | Resources |
| 5.0 | ZenDNN 5.0 User Guide Support Matrix |
Archives v5.0
| Title | Description | MD5SUM |
| ZenDNN Plug-in for PyTorch | ||
| ZENTORCH_v5.0.0_Python_v3.10.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.10 | f34e7b450fe0d6bb973db41838430bf0 |
| ZENTORCH_v5.0.0_Python_v3.11.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.11 | a49446852ab4b529e70b234b95a8c47f |
| ZENTORCH_v5.0.0_Python_v3.8.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.8 | c8c2deca8fefe6c7d6699bda20dd95a3 |
| ZENTORCH_v5.0.0_Python_v3.9.zip | This zip file contains the zentorch wheel file and the necessary scripts to set up the environment variables. Compatible with Python version 3.9 | ffdfa8a4b65cbf0547790fc60350761c |
| ZenDNN Plug-in for TensorFlow |
||
| ZENTF_v5.0.0_Python_v3.10.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.10 | f5624742f5e5a85aa2b43cc1706d1a6c |
| ZENTF_v5.0.0_Python_v3.11.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.11 | 043fccc676b20d10d7f7ba4719dd89cd |
| ZENTF_v5.0.0_Python_v3.12.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.12 | 6602d4ce1617bc05f0169d0c2f93e4ee |
| ZENTF_v5.0.0_Python_v3.9.zip | This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.9 | 4a33b8e27f4544f9e36421c56a6fdea3 |
| ZENTF_v5.0.0_C++_API.zip | This zip file contains the ZenDNN TensorFlow Plug-in with C++ APIs | fdb264a921a81f56965f4294d23e7abf |
| ZenDNN with ONNX Runtime | ||
| ONNXRT_v1.19.2_ZenDNN_v5.0_Python_v3.10.zip | This zip file contains the ONNX Runtime wheel and the necessary scripts to set up the environment variables. Compatible with Python 3.10 | 38f64749c2e3e6d249b0c38bad2b0400 |
| ONNXRT_v1.19.2_ZenDNN_v5.0_Python_v3.11.zip | This zip file contains the ONNX Runtime wheel and the necessary scripts to set up the environment variables. Compatible with Python 3.11 | 6368acd895504df095017d25dcba774e |
| ONNXRT_v1.19.2_ZenDNN_v5.0_Python_v3.8.zip | This zip file contains the ONNX Runtime wheel and the necessary scripts to set up the environment variables. Compatible with Python 3.8 | 2b2d0167497025c059bd8572e3c2ebd6 |
| ONNXRT_v1.19.2_ZenDNN_v5.0_Python_v3.9.zip | This zip file contains the ONNX Runtime wheel and the necessary scripts to set up the environment variables. Compatible with Python 3.9 | c996d54ecda4783ea5e78acb51026497 |
| ONNXRT_v1.19.2_ZenDNN_v5.0_C++_API.zip | This zip file contains the ZenDNN ONNX Runtime with C++ APIs | a3cb5654e7877db81abb1189b8bc3074 |
4.2 Release Highlights
- Plugins to native PyTorch and TensorFlow
- Framework Support for PyTorch 2.1, TensorFlow 2.16 and ONNXRT 1.17.0
- Enhancements with microkernels, mempool optimizations, and efficient multi-threading on the large number of AMD EPYC™ cores
- New INT8 support
- Improved algorithms for embedding bags
- Improved GEMM algorithms
Release Blog
ZenDNN 4.2: Introducing a New Plugin Architecture
Resources
| Version | Resources |
| 4.2 | ZenDNN 4.2 User Guide Support Matrix |
Archives v4.2
| Title | Description | MD5SUM |
| ZenDNN Plug-in for PyTorch | ||
| ZENTORCH_v4.2.0_Python_v3.10.zip | This zip file contains the zentorch wheel file compatible with Python version 3.10 | 36464127bb6d7d691d06662cdff667d7 |
| ZENTORCH_v4.2.0_Python_v3.11.zip |
This zip file contains the zentorch wheel file compatible with Python version 3.11 |
7873b9a54ccb258c985e79f1e59e4921 |
| ZENTORCH_v4.2.0_Python_v3.8.zip | This zip file contains the zentorch wheel file compatible with Python version 3.8 |
2c26985eb8d30d1daaf64380c5a7c92d |
| ZENTORCH_v4.2.0_Python_v3.9.zip |
This zip file contains the zentorch wheel file compatible with Python version 3.9 |
39cad1529e3d92109dfd29dde5542412 |
| ZenDNN Plug-in for TensorFlow |
||
| ZENTF_v4.2.0_Python_v3.10.zip |
This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.10 |
7819c979e1147861395634c29da2dbb0 |
| ZENTF_v4.2.0_Python_v3.11.zip |
This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.11 |
b34c6c7fda3579cdeb76756db23146fd |
| ZENTF_v4.2.0_Python_v3.12.zip |
This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.12 |
5a7aacda4f99dae485920e1d7cdf307b |
| ZENTF_v4.2.0_Python_v3.9.zip |
This zip file contains the zentf wheel file and the necessary scripts to set up the environment variables. Compatible with Python 3.9 |
365ef04189b615ecfc0a2e8c1481f013 |
| ZENTF_v4.2.0_C++_API.zip | This zip file contains the ZenDNN Plug-in with C++ APIs | 4802d21e31e2e8f9ca632e987889f7d4 |
| ZenDNN with ONNX Runtime | ||
| ONNXRT_v1.17.0_ZenDNN_v4.2_C++_API.zip | This zip file contains the ONNX Runtime with C++ APIs | 4b12aa577e8919b6e08a0758a8cc0fa1 |
| ONNXRT_v1.17.0_ZenDNN_v4.2_Python_v3.10.zip | This zip file contains the ONNX Runtime wheel and the necessary scripts to set up the environment variables. Compatible with Python 3.10 | ace337e60f130cb7d8e0a1fc6840848b |
| ONNXRT_v1.17.0_ZenDNN_v4.2_Python_v3.11.zip | This zip file contains the ONNX Runtime wheel and the necessary scripts to set up the environment variables. Compatible with Python 3.11 | fd6540178fa87c37048239107b4f4f4d |
| ONNXRT_v1.17.0_ZenDNN_v4.2_Python_v3.8.zip | This zip file contains the ONNX Runtime wheel and the necessary scripts to set up the environment variables. Compatible with Python 3.8 | 0a6b531c1ec709207c82dec7e4d0b98a |
| ONNXRT_v1.17.0_ZenDNN_v4.2_Python_v3.9.zip | This zip file contains the ONNX Runtime wheel and the necessary scripts to set up the environment variables. Compatible with Python 3.9 | d00350e76d4fc08486b5213e4c2181e4 |
Resources
| Version | Resources |
| 4.1 | ZenDNN 4.1 User Guide Support Matrix |
Archives v4.1
TensorFlow, PyTorch, and ONNX Runtime are available with different Python versions.
| File Name | Version | Size (MB) | Launch Date | OS | Bitness | Description |
|---|---|---|---|---|---|---|
| TensorFlow | ||||||
| TF_v2.12_ZenDNN_v4.1_Python_v3.8.zip | 4.1 | 251 | 9/25/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.12 + ZenDNN binary release package with python v3.8. MD5 Checksum: 460232df133cacda36ec5474cce09502 |
| TF_v2.12_ZenDNN_v4.1_Python_v3.9.zip | 4.1 | 251 | 9/25/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.12 + ZenDNN binary release package with python v3.9. MD5 Checksum: 92c74a43eb64854ad8398ca88f22b151 |
| TF_v2.12_ZenDNN_v4.1_Python_v3.10.zip | 4.1 | 251 | 9/25/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.12 + ZenDNN binary release package with python v3.10. MD5 Checksum: 52623e6708043f1fca9664c259757e03 |
| TF_v2.12_ZenDNN_v4.1_Python_v3.11.zip | 4.1 | 251 | 9/25/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.12 + ZenDNN binary release package with python v3.11. MD5 Checksum: 1c5afea80d5c5165c10069d413fb55b6 |
| TF_v2.12_ZenDNN_v4.1_C++_API.zip | 4.1 | 199 | 9/25/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.12 + ZenDNN binary release package for C++ API interface. MD5 Checksum: 3219d8d137c60d306c20668179bb188e |
| PyTorch | ||||||
| PT_v1.13_ZenDNN_v4.1_Python_v3.7.zip | 4.1 | 115 | 9/25/2023 | Ubuntu/RHEL | 64 | PyTorch v1.13 + ZenDNN binary release package with python v3.7. MD5 Checksum: 17a07cc5658ca90e094cb632af6cbf8a |
| PT_v1.13_ZenDNN_v4.1_Python_v3.8.zip | 4.1 | 115 | 9/25/2023 | Ubuntu/RHEL | 64 | PyTorch v1.13+ ZenDNN binary release package with python v3.8. MD5 Checksum: 0e386b480b3448ace8d09c312775a5af |
| PT_v1.13_ZenDNN_v4.1_Python_v3.9.zip | 4.1 | 114 | 9/25/2023 | Ubuntu/RHEL | 64 | PyTorch v1.13 + ZenDNN binary release package with python v3.9. MD5 Checksum: 89b479a65d2f6d51d517ea6322b6cd2f |
| PT_v1.13_ZenDNN_v4.1_Python_v3.10.zip | 4.1 | 114 | 9/25/2023 | Ubuntu/RHEL | 64 | PyTorch v1.13 + ZenDNN binary release package with python v3.10. MD5 Checksum: 0d817429f6b233e80d58af9bedb66708 |
| PT_v1.13_ZenDNN_v4.1_C++_API.zip | 4.1 | 74 | 9/25/2023 | Ubuntu/RHEL | 64 | PyTorch v1.13 + ZenDNN binary release package for C++ API interface. MD5 Checksum: 0584e8823ddbe2d76b0a507675715db5 |
| ONNX Runtime | ||||||
| ONNXRT_v1.15.1_ZenDNN_v4.1_Python_v3.8.zip | 4.1 | 21 | 9/25/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package with python v3.8. MD5 Checksum: 3f521d8174484d811c615e1657e8231a |
| ONNXRT_v1.15.1_ZenDNN_v4.1_Python_v3.9.zip | 4.1 | 21 | 9/25/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package with python v3.9. MD5 Checksum: 541fdf9ed5292ff15eafbec75520bb76 |
| ONNXRT_v1.15.1_ZenDNN_v4.1_Python_v3.10.zip | 4.1 | 21 | 9/25/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package with python v3.10. MD5 Checksum: 9ed490d93f736bc251704f8a49f98c99 |
| ONNXRT_v1.15.1_ZenDNN_v4.1_Python_v3.11.zip | 4.1 | 21 | 9/25/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package with python v3.11. MD5 Checksum: 8b23cbb7f659a9806e8965495811862e |
| ONNXRT_v1.15.1_ZenDNN_v4.1_C++_API.zip | 4.1 | 30 | 9/25/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package for C++ API interface. MD5 Checksum: d977b9a223e128689741650e9709a0ed |
| ONNX Runtime Windows | ||||||
| ONNXRT_v1.15.1_ZenDNN_v4.1_Python_v3.8_Win.zip | 4.1 | 13 | 9/25/2023 | Windows | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package with python v3.8 for Windows OS. MD5 Checksum: 8cd35dc54c94b52725a0cd7c30796c9c |
| ONNXRT_v1.15.1_ZenDNN_v4.1_Python_v3.9_Win.zip | 4.1 | 13 | 9/25/2023 | Windows | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package with python v3.9 for Windows OS. MD5 Checksum: 58c13fe5851b85ab07ff9068dfb49955 |
| ONNXRT_v1.15.1_ZenDNN_v4.1_Python_v3.10_Win.zip | 4.1 | 13 | 9/25/2023 | Windows | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package with python v3.10 for Windows OS. MD5 Checksum: d3985ea8ffa5fdce938cb793b8b46ce4 |
| ONNXRT_v1.15.1_ZenDNN_v4.1_Python_v3.11_Win.zip | 4.1 | 13 | 9/25/2023 | Windows | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package with python v3.11 for Windows OS. MD5 Checksum: f64585efdc6144a1ab9ad7405f9cd1e6 |
| ONNXRT_v1.15.1_ZenDNN_v4.1_C++_API_Win.zip | 4.1 | 12 | 9/25/2023 | Windows | 64 | ONNX Runtime v1.15.1 + ZenDNN binary release package for C++ API interface for Windows OS. MD5 Checksum: 59f69a0aba8a86bbf3bb542163d13866 |
Resources
| Version | Resources |
| 4.0 | ZenDNN 4.0 – Documents |
Archives v4.0
| File Name | Version | Size | Launch Date | OS | Bitness | Description |
| TensorFlow | ||||||
| TF_v2.10_ZenDNN_v4.0_Python_v3.7.zip | 4 | 253 | 1/20/2023 | Ubuntu/ RHEL | 64 | TensorFlow v2.10 + ZenDNN binary release package with python v3.7. MD5 Checksum: 6dd12b66a58c2fcf0b72dd9b6334b4fe |
| TF_v2.10_ZenDNN_v4.0_Python_v3.8.zip | 4 | 253 | 1/20/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.10 + ZenDNN binary release package with python v3.8. MD5 Checksum: a5f2f72bf92c7c6a96bb79dcca8e6501 |
| TF_v2.10_ZenDNN_v4.0_Python_v3.9.zip | 4 | 253 | 1/20/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.10 + ZenDNN binary release package with python v3.9. MD5 Checksum: 85a5e173143087189be1e11118324c40 |
| TF_v2.10_ZenDNN_v4.0_Python_v3.10.zip | 4 | 253 | 1/20/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.10 + ZenDNN binary release package with python v3.10. MD5 Checksum: d0b17b669fe9385bc643d988fd075598 |
| TF_v2.10_ZenDNN_v4.0_C++_API.zip | 4 | 474 | 1/20/2023 | Ubuntu/RHEL | 64 | TensorFlow v2.10 F v2.10 + ZenDNN binary release package for C++ API interface. MD5 Checksum: bb05ff87083877bc00e14b42c16b8fe2 |
| TF_v2.10_ZenDNN_v4.0_source_code.tar.gz | 4 | 130 | 1/20/2023 | Ubuntu/RHEL | 64 | Integration source code of TensorFlow v2.10 with ZenDNN. The instruction file inside zip code describe how to use the integration source code and how to build TensorFlow v2.10 with ZenDNN. MD5 Checksum:bd9b704b9b3338ba98fa59047c23d373 |
| PyTorch | ||||||
| PT_v1.12_ZenDNN_v4.0_Python_v3.7.zip | 4 | 112 | 1/20/2023 | Ubuntu/RHEL | 64 | PyTorch v1.12 + ZenDNN binary release package with python v3.7. MD5 Checksum: 7659431337d5b15c2fe97d6a7407bc4f |
| PT_v1.12_ZenDNN_v4.0_Python_v3.8.zip | 4 | 112 | 1/20/2023 | Ubuntu/RHEL | 64 | PyTorch v1.12+ ZenDNN binary release package with python v3.8. MD5 Checksum: ce4fc1d5d780d2f279ad629fa11f32ff |
| PT_v1.12_ZenDNN_v4.0_Python_v3.9.zip | 4 | 112 | 1/20/2023 | Ubuntu/RHEL | 64 | PyTorch v1.12 + ZenDNN binary release package with python v3.9. MD5 Checksum: 0b6a45fd63483355714793794f1db990 |
| PT_v1.12_ZenDNN_v4.0_Python_v3.10.zip | 4 | 112 | 1/20/2023 | Ubuntu/RHEL | 64 | PyTorch v1.12 + ZenDNN binary release package with python v3.10. MD5 Checksum: 4006218ed41713c5025909443a440c08 |
| PT_v1.12_ZenDNN_v4.0_C++_API.zip | 4 | 74 | 1/20/2023 | Ubuntu/RHEL | 64 | PyTorch v1.12 + ZenDNN binary release package for C++ API interface. MD5 Checksum: 3cb2aae954993f8a93aa69f36f39399a |
| PT_v1.12_ZenDNN_v4.0_source_code.tar.gz | 4 | 124 | 1/20/2023 | Ubuntu/RHEL | 64 | Integration source code of PyTorch v1.12 with ZenDNN. The instruction file inside zip code describe how to use the integration source code and how to build PyTorch v1.12 with ZenDNN. MD5 Checksum:6318232592dd0d181a29ed0f1fef09fd |
| ONNX Runtime | ||||||
| ONNXRT_v1.12.1_ZenDNN_v4.0_Python_v3.7.zip | 4 | 22 | 1/20/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.12.1 + ZenDNN binary release package with python v3.7. MD5 Checksum: 7a809f6be3328e07e9aa45a790904825 |
| ONNXRT_v1.12.1_ZenDNN_v4.0_Python_v3.8.zip | 4 | 22 | 1/20/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.12.1 + ZenDNN binary release package with python v3.8. MD5 Checksum: 7ef3e7dc582b05f0326a7c186d410497 |
| ONNXRT_v1.12.1_ZenDNN_v4.0_Python_v3.9.zip | 4 | 22 | 1/20/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.12.1 + ZenDNN binary release package with python v3.9. MD5 Checksum: 79aa052d69fc36fe5f22cf6d7afbf258 |
| ONNXRT_v1.12.1_ZenDNN_v4.0_Python_v3.10.zip | 4 | 22 | 1/20/2023 | Ubuntu/RHEL | 64 | ONNX Runtime v1.12.1 + ZenDNN binary release package with python v3.10. MD5 Checksum: e167aaba7e3e8696d11a8e2f2ec2219b |
| ONNX Runtime Windows | ||||||
| ONNXRT_v1.12.1_ZenDNN_v4.0_Python_v3.7_Win.zip | 4 | 12 | 1/20/2023 | Windows | 64 | ONNX Runtime v1.12.1 + ZenDNN binary release package with python v3.7 for Windows OS. MD5 Checksum: 807113d743aa34329d5b31f5cb719881 |
| ONNXRT_v1.12.1_ZenDNN_v4.0_Python_v3.8_Win.zip | 4 | 12 | 1/20/2023 | Windows | 64 | ONNX Runtime v1.12.1 + ZenDNN binary release package with python v3.8 for Windows OS. MD5 Checksum: b2bf91c563a393451d5811ba248dfa17 |
| ONNXRT_v1.12.1_ZenDNN_v4.0_Python_v3.9_Win.zip | 4 | 12 | 1/20/2023 | Windows | 64 | ONNX Runtime v1.12.1 + ZenDNN binary release package with python v3.9 for Windows OS. MD5 Checksum: 0d7d0028d455d9fe1ffe87023dd8242e |
| ONNXRT_v1.12.1_ZenDNN_v4.0_Python_v3.10_Win.zip | 4 | 12 | 1/20/2023 | Windows | 64 | ONNX Runtime v1.12.1 + ZenDNN binary release package with python v3.10 for Windows OS. MD5 Checksum: 451cead3218693925f3a25d5021872fe |
Resources
| Version | Resources |
| 3.3 | TensorFlow-ZenDNN Plug-in User Guide |
| 3.3 | ZenDNN 3.3 – Documents |
Archives v3.3
| File Name | Version | Size | Launch Date | OS | Bitness | Description |
| TensorFlow | ||||||
| TF_v2.9_ZenDNN_v3.3_Python_v3.7.zip | 3.3 | 228 MB | 06/15/2022 | Ubuntu/RHEL | 64 | TF v2.9 + ZenDNN binary release package with python v3.7. MD5 Checksum: 9d1aa54e8a4aeb79a8688e46bc3dc235 |
| TF_v2.9_ZenDNN_v3.3_Python_v3.8.zip | 3.3 | 228 MB | 06/15/2022 | Ubuntu/RHEL | 64 | TF v2.9 + ZenDNN binary release package with python v3.8. MD5 Checksum: 75672df609140c010d4c36c7cd1ca5cf |
| TF_v2.9_ZenDNN_v3.3_Python_v3.9.zip | 3.3 | 228 MB | 06/15/2022 | Ubuntu/RHEL | 64 | TF v2.9 + ZenDNN binary release package with python v3.9. MD5 Checksum: ffbf00787378526c726fd1dbe3769c93 |
| TF_v2.9_ZenDNN_v3.3_Python_v3.10.zip | 3.3 | 228 MB | 06/15/2022 | Ubuntu/RHEL | 64 | TF v2.9 + ZenDNN binary release package with python v3.10. MD5 Checksum: af0fd75f4b76810d6ba8eb25bcb82058 |
| TF_v2.9_ZenDNN_v3.3_API.zip | 3.3 | 130 MB | 06/15/2022 | Ubuntu/RHEL | 64 | TF v2.9 + ZenDNN binary release package for C++ API interface. MD5 Checksum: 51b3b4093775ff2b67e06f18d01b41ac |
| PyTorch | ||||||
| PT_v1.11.0_ZenDNN_v3.3_Python_v3.7.zip | 3.3 | 98 MB | 06/15/2022 | Ubuntu/RHEL | 64 | PT v1.11.0 + ZenDNN binary release package with python v3.7. MD5 Checksum: 6f1da3b0420b1c1dd568fbaaae90e9ba |
| PT_v1.11.0_ZenDNN_v3.3_Python_v3.8.zip | 3.3 | 98 MB | 06/15/2022 | Ubuntu/RHEL | 64 | PT v1.11.0 + ZenDNN binary release package with python v3.8. MD5 Checksum: f76a62e9eb6e352ecc2a2ab2b68e9f38 |
| PT_v1.11.0_ZenDNN_v3.3_Python_v3.9.zip | 3.3 | 98 MB | 06/15/2022 | Ubuntu/RHEL | 64 | PT v1.11.0 + ZenDNN binary release package with python v3.9. MD5 Checksum: 318408befd3e5d099d0a1f7644c9d80d |
| PT_v1.11.0_ZenDNN_v3.3_Python_v3.10.zip | 3.3 | 98 MB | 06/15/2022 | Ubuntu/RHEL | 64 | PT v1.11.0 + ZenDNN binary release package with python v3.10. MD5 Checksum: d447a9a99d4481e92aba78a840238ed3 |
| PT_v1.11.0_ZenDNN_v3.3_API.zip | 3.3 | 56 MB | 06/15/2022 | Ubuntu/RHEL | 64 | PT v1.11.0 + ZenDNN binary release package for C++ API interface. MD5 Checksum: a191f2305f1cae6e00c82a1071df9708 |