TThe release includes five new tutorials specifically designed for AI developers, which cover topics such as inference, ChatQnA vLLM deployment and performance evaluation, text-to-video generation with ComfyUI, DeepSeek Janus Pro on CPU or GPU, DeepSeek-R1 with vLLM V1, and GPU development and optimization. AMD ROCm offers a robust ecosystem for deep learning development, featuring support for Taichi, a streamlined library designed for mixture-of-experts training, along with updated information on hardware and library support. The support for the operating system and hardware remains consistent in this release.
ROCm has experienced notable transformations, such as the transfer of AMD SMI from the ROCm organization repository to a newly established AMDTools repository. Additionally, there has been the discontinuation of ROCm SMI, the phase-out of ROCTracer, ROCProfiler, rocprof, and rocprofv2, as well as the deprecation of AMDGPU wavefront size compiler macros, HIPCC Perl scripts, and ROCm Object Tooling tools. The proposed modifications are designed to enhance the alignment between HIP and CUDA APIs or behaviors, streamline header files, eliminate namespace collisions, and establish a distinct separation between hipRTC and the HIP runtime.
The ROCm software stack is anticipated to experience multiple changes in the near future, including the discontinuation of ROCm SMI, ROCTracer, ROCProfiler, rocprof, and rocprofv2, as well as the removal of AMDGPU wavefront size compiler macros and HIPCC Perl scripts. The ROCm Object Tooling tools roc-obj-ls, roc-obj-extract, and roc-obj will be deprecated in an upcoming release, with their functionality integrated into the llvm-objdump --offloading tool option.
Here is the full announcement:
ROCm 6.4.3 Release
The release notes provide a summary of notable changes since the previous ROCm release.
If you’re using AMD RadeonPRO or Radeon GPUs in a workstation setting with a display connected, see the [Use ROCm on Radeon GPUs](https://rocm.docs.amd.com/projects/radeon/en/latest/docs/compatibility/native_linux/native_linux_compatibility.html) documentation to verify compatibility and system requirements.
Release highlights
ROCm 6.4.3 is a quality release that resolves the following issues. For changes to individual components, see Detailed component changes.
AMDGPU driver updates
- Resolved an issue causing performance degradation in communication operations, caused by increased latency in certain RCCL applications. The fix prevents unnecessary queue eviction during the fork process.
- Fixed an issue in the AMDGPU driver’s scheduler constraints that could cause queue preemption to fail during workload execution.
ROCm SMI update
- Fixed the failure to load GPU data like System Clock (SCLK) by adjusting the logic for retrieving GPU board voltage.
ROCm documentation updates
ROCm documentation continues to be updated to provide clearer and more comprehensive guidance for a wider variety of user needs and use cases.
Tutorials for AI developers have been expanded with the following five new tutorials:
- Inference tutorials
- GPU development and optimization tutorial: MLA decoding kernel of AITER library
For more information about the changes, see Changelog for the AI Developer Hub.
ROCm provides a comprehensive ecosystem for deep learning development. For more details, see Deep learning frameworks for ROCm. AMD ROCm adds support for the following deep learning frameworks:
- Taichi is an open-source, imperative, and parallel programming language designed for high-performance numerical computation. Embedded in Python, it leverages just-in-time (JIT) compilation frameworks such as LLVM to accelerate compute-intensive Python code by compiling it to native GPU or CPU instructions. It is currently supported on ROCm 6.3.2. For more information, see Taichi compatibility.
- Megablocks is a light-weight library for mixture-of-experts (MoE) training. The core of the system is efficient "dropless-MoE" and standard MoE layers. Megablocks is integrated with Megatron-LM, where data and pipeline parallel training of MoEs is supported. It is currently supported on ROCm 6.3.0. For more information, see Megablocks compatibility.
The Data types and precision support topic now includes new hardware and library support information.
Operating system and hardware support changes
Operating system and hardware support remain unchanged in this release.
See the Compatibility
matrixfor more information about operating system and hardware compatibility.ROCm components
The following table lists the versions of ROCm components for ROCm 6.4.3.
Click {fab}githubto go to the component's source code on GitHub.
Category Group Name Version Libraries Machine learning and computer vision Composable Kernel 1.1.0 MIGraphX 2.12.0 MIOpen 3.4.0 MIVisionX 3.2.0 rocAL 2.2.0 rocDecode 0.10.0 rocJPEG 0.8.0 rocPyDecode 0.3.1 RPP 1.9.10 Communication RCCL 2.22.3 rocSHMEM 2.0.1 Math hipBLAS 2.4.0 hipBLASLt 0.12.1 hipFFT 1.0.18 hipfort 0.6.0 hipRAND 2.12.0 hipSOLVER 2.4.0 hipSPARSE 3.2.0 hipSPARSELt 0.2.3 rocALUTION 3.2.3 rocBLAS 4.4.1 rocFFT 1.0.32 rocRAND 3.3.0 rocSOLVER 3.28.2 rocSPARSE 3.4.0 rocWMMA 1.7.0 Tensile 4.43.0 Primitives hipCUB 3.4.0 hipTensor 1.5.0 rocPRIM 3.4.1 rocThrust 3.3.0 Tools System management AMD SMI 25.5.1 ROCm Data Center Tool 0.3.0 rocminfo 1.0.0 ROCm SMI 7.5.0 ⇒ 7.7.0 ROCm Validation Suite 1.1.0 Performance ROCm Bandwidth Test 1.4.0 ROCm Compute Profiler 3.1.1 ROCm Systems Profiler 1.0.2 ROCProfiler 2.0.0 ROCprofiler-SDK 0.6.0 ROCTracer 4.1.0 Development HIPIFY 19.0.0 ROCdbgapi 0.77.2 ROCm CMake 0.14.0 ROCm Debugger (ROCgdb) 15.2 ROCr Debug Agent 2.0.4 Compilers HIPCC 1.1.1 llvm-project 19.0.0 Runtimes HIP 6.4.3 ROCr Runtime 1.15.0 Detailed component changes
The following sections describe key changes to ROCm components.
For a historical overview of ROCm component updates, see the {doc}`ROCm consolidated changelog </release/changelog>`.ROCm SMI (7.7.0)
Added
- Support for getting the GPU Board voltage.
See the full [ROCm SMI changelog](https://github.com/ROCm/rocm_smi_lib/blob/release/rocm-rel-6.4/CHANGELOG.md) for details, examples, and in-depth descriptions.ROCm known issues
ROCm known issues are noted on {fab}
githubGitHub. For known
issues related to individual components, review the Detailed component changes.ROCm upcoming changes
The following changes to the ROCm software stack are anticipated for future releases.
AMD SMI migration to AMDGPU driver repository
In a future release, AMD SMI will be relocated from the ROCm organization repository to a new AMDTools repository to better align with its system-level functionality.
amd-smi-libwill no longer be included in therocm-developer-toolsmeta-package included with your standard ROCm installation. Instead, it will be packaged with the AMDGPU driver installation.ROCm SMI deprecation
ROCm SMI will be phased out in an
upcoming ROCm release and will enter maintenance mode. After this transition,
only critical bug fixes will be addressed and no further feature development
will take place.It's strongly recommended to transition your projects to AMD
SMI, the successor to ROCm SMI. AMD SMI
includes all the features of the ROCm SMI and will continue to receive regular
updates, new functionality, and ongoing support. For more information on AMD
SMI, see the AMD SMI documentation.ROCTracer, ROCProfiler, rocprof, and rocprofv2 deprecation
Development and support for ROCTracer, ROCProfiler,
rocprof, androcprofv2are being phased out in favor of ROCprofiler-SDK in upcoming ROCm releases. Starting with ROCm 6.4, only critical defect fixes will be addressed for older versions of the profiling tools and libraries. All users are encouraged to upgrade to the latest version of the ROCprofiler-SDK library and the (rocprofv3) tool to ensure continued support and access to new features. ROCprofiler-SDK is still in beta today and will be production-ready in a future ROCm release.It's anticipated that ROCTracer, ROCProfiler,
rocprof, androcprofv2will reach end-of-life by future releases, aligning with Q1 of 2026.AMDGPU wavefront size compiler macro deprecation
Access to the wavefront size as a compile-time constant via the
__AMDGCN_WAVEFRONT_SIZE
and__AMDGCN_WAVEFRONT_SIZE__macros or theconstexpr warpSizevariable is deprecated
and will be disabled in a future release.
- The
__AMDGCN_WAVEFRONT_SIZE__macro and__AMDGCN_WAVEFRONT_SIZEalias will be removed in an upcoming release.
It is recommended to remove any use of this macro. For more information, see
AMDGPU support.warpSizewill only be available as a non-constexprvariable. Where required,
the wavefront size should be queried via thewarpSizevariable in device code,
or viahipGetDevicePropertiesin host code. Neither of these will result in a compile-time constant. For more information, see warpSize.- For cases where compile-time evaluation of the wavefront size cannot be avoided,
uses of__AMDGCN_WAVEFRONT_SIZE,__AMDGCN_WAVEFRONT_SIZE__, orwarpSize
can be replaced with a user-defined macro orconstexprvariable with the wavefront
size(s) for the target hardware. For example:#if defined(__GFX9__) #define MY_MACRO_FOR_WAVEFRONT_SIZE 64 #else #define MY_MACRO_FOR_WAVEFRONT_SIZE 32 #endifHIPCC Perl scripts deprecation
The HIPCC Perl scripts (
hipcc.plandhipconfig.pl) will be removed in an upcoming release.Changes to ROCm Object Tooling
ROCm Object Tooling tools
roc-obj-ls,roc-obj-extract, androc-objare
deprecated in ROCm 6.4, and will be removed in a future release. Functionality
has been added to thellvm-objdump --offloadingtool option to extract all
clang-offload-bundles into individual code objects found within the objects
or executables passed as input. Thellvm-objdump --offloadingtool option also
supports the--arch-nameoption, and only extracts code objects found with
the specified target architecture. See llvm-objdumpfor more information.HIP runtime API changes
There are a number of upcoming changes planned for HIP runtime API in an upcoming major release
that are not backward compatible with prior releases. Most of these changes increase
alignment between HIP and CUDA APIs or behavior. Some of the upcoming changes are to
clean up header files, remove namespace collision, and have a clear separation betweenhipRTCand HIP runtime. For more information, see HIP 7.0 Is Coming: What You Need to Know to Stay Ahead.
