mirror of
https://github.com/ROCm/ROCm.git
synced 2026-02-12 07:25:22 -05:00
[docs/7.11.0] Fix some release notes documentation and remove unneeded SLES packages (#5960)
* fix release date and known issue * add llama.cpp known issue and fix link to amdgpu 31.10.0 * docs: minor fixes * fx * clean up known issues * clean up
This commit is contained in:
55
RELEASE.md
55
RELEASE.md
@@ -861,7 +861,7 @@ distributes.
|
||||
<p>
|
||||
<strong>AMD GPU Driver (amdgpu)</strong><br>
|
||||
<a
|
||||
href="https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-31.10.0/documentation/release-notes.html"
|
||||
href="https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/documentation/release-notes.html"
|
||||
target="_blank"
|
||||
>31.10.0</a><br>
|
||||
<a
|
||||
@@ -968,7 +968,7 @@ distributes.
|
||||
<p>
|
||||
<strong>AMD GPU Driver (amdgpu)</strong><br>
|
||||
<a
|
||||
href="https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-31.10.0/documentation/release-notes.html"
|
||||
href="https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/documentation/release-notes.html"
|
||||
target="_blank"
|
||||
>31.10.0</a><br>
|
||||
<a
|
||||
@@ -1082,7 +1082,7 @@ distributes.
|
||||
<p>
|
||||
<strong>AMD GPU Driver (amdgpu)</strong><br>
|
||||
<a
|
||||
href="https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-31.10.0/documentation/release-notes.html"
|
||||
href="https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/documentation/release-notes.html"
|
||||
target="_blank"
|
||||
>31.10.0</a><br>
|
||||
<a
|
||||
@@ -1692,7 +1692,7 @@ support for your specific setup.
|
||||
|
||||
The following are known issues identified in ROCm 7.11.0.
|
||||
|
||||
### DistilBERT model performance regression on Instinct MI350 Series
|
||||
### DistilBERT model performance regression on AMD Instinct MI350 Series
|
||||
|
||||
The [DistilBERT](https://huggingface.co/distilbert/distilbert-base-uncased)
|
||||
base model experiences reduced GPU kernel performance on Instinct MI350 Series
|
||||
@@ -1700,17 +1700,17 @@ GPUs (gfx950). This issue is under investigation.
|
||||
|
||||
### ROCgdb GPU core dump limitation
|
||||
|
||||
ROCgdb currently has a limitation that preventing proper GPU core dump
|
||||
generation. This blocks effective root‑cause analysis of GPU faults.
|
||||
ROCgdb has a limitation that prevents proper GPU core dumps from being
|
||||
generated. This blocks effective root‑cause analysis of GPU faults.
|
||||
[ROCm/rocm-systems PR #2851](https://github.com/ROCm/rocm-systems/pull/2851)
|
||||
introduces a fix to the ROCr runtime's core dump generation and will be
|
||||
introduces a fix to the ROCr Runtime's core dump generation and will be
|
||||
included in a future release.
|
||||
|
||||
### Clang illegal instruction error on Radeon GPUs
|
||||
|
||||
Using Clang with the `-O0` optimization level on certain supported Radeon PRO
|
||||
Using Clang with the `-O0` optimization level on certain supported AMD Radeon PRO
|
||||
and Radeon GPUs might trigger an illegal instructions detected error. This
|
||||
failure typically occurs in code paths using `ockl_wfred_*` functions, which
|
||||
failure typically occurs in code paths that use `ockl_wfred_*` functions, which
|
||||
handle wavefront operations and synchronization. Projects like llama.cpp are
|
||||
known to be affected. As a workaround, use `-Og` optimization level instead of
|
||||
`-O0` for debug builds:
|
||||
@@ -1724,11 +1724,16 @@ known to be affected. As a workaround, use `-Og` optimization level instead of
|
||||
-DCMAKE_CXX_FLAGS_DEBUG="-Og -g -Xclang -gcodeview -D_DEBUG -D_DLL -D_MT -Xclang --dependent-lib=msvcrtd"
|
||||
```
|
||||
|
||||
### llama.cpp runtime failures on Instinct MI350 Series
|
||||
|
||||
llama.cpp builds successfully but might fail at runtime with the error "HIP
|
||||
kernel mul_mat_q has no device code". This issue is under investigation.
|
||||
|
||||
### PyTorch model training validation issues
|
||||
|
||||
The following models failed validation on PyTorch for ROCm 7.11.0 due to
|
||||
compilation errors and other issues: Llama 3.1 8B, Llama 3.1 70B, and DeepSpeed
|
||||
Megatron-LM GPT2.
|
||||
compilation errors and other issues: Llama 3.1 8B, Llama 3.1 70B, Llama
|
||||
2 70B-chat-hf, and DeepSpeed Megatron-LM GPT2.
|
||||
|
||||
### Apex fails to build using TheRock
|
||||
|
||||
@@ -1736,16 +1741,16 @@ Megatron-LM GPT2.
|
||||
errors, and segmentation faults related to the HIP runtime during testing with
|
||||
the TheRock build system. This will be fixed in a future release.
|
||||
|
||||
### PyTorch unit tests freeze on Windows
|
||||
### PyTorch unit tests freeze on Microsoft Windows
|
||||
|
||||
The `test_cublas_config_nondeterministic_alert_cuda` and `test_graph_error`
|
||||
PyTorch tests fail and hang indefinitely on Windows. This issue will be fixed
|
||||
in a future release.
|
||||
|
||||
### hipRTC rocWMMA unknown type name compilation errors
|
||||
### HIPRTC rocWMMA unknown type name compilation errors
|
||||
|
||||
Any hipRTC program using the `rocwmma.hpp` header will fail to compile and
|
||||
produce a number of "unknown type name" errors. This issue will be fixed in
|
||||
Any HIPRTC program using the `rocwmma.hpp` header will fail to compile and
|
||||
produce "unknown type name" errors. This issue will be fixed in
|
||||
a future release. As a workaround, add the following code before including the
|
||||
`rocwmma.hpp` header:
|
||||
|
||||
@@ -1770,12 +1775,13 @@ The `rocprim.device_adjacent_find` unit test on Windows on Radeon RX 9060 XT
|
||||
LP, 9060 XT, and 9060 GPUs might hang intermittently. This issue will be fixed
|
||||
in a future release.
|
||||
|
||||
### MIOpen unit test header include failures
|
||||
### MIOpen unit test runtime compilation failures
|
||||
|
||||
MIOpen unit tests fail to find the `rocrand_xorwow.h` header during runtime
|
||||
compilation of certain kernels. This occurs because ROCm can be installed in
|
||||
various locations and the include path is not automatically resolved. There's
|
||||
minimal impact to users. This issue will be fixed in a future release.
|
||||
various locations and the include path is not automatically resolved. Impact is
|
||||
minimal as the affected kernel (softmax attention) is not used in production
|
||||
workloads. This issue will be fixed in a future release.
|
||||
|
||||
### CRIU checkpoint fails on Instinct MI300X with Debian 13
|
||||
|
||||
@@ -1788,7 +1794,7 @@ experience CRIU failures. This issue will be fixed in a future release.
|
||||
Multi-node RCCL tests are experiencing intermittent segmentation faults on
|
||||
Instinct GPUs with ROCm 7.11.0. This issue will be fixed in a future release.
|
||||
|
||||
### hipify-clang errors with CUDA 12.x
|
||||
### hipify-clang errors with NVIDIA CUDA 12.x
|
||||
|
||||
Users running `hipify-clang` with CUDA 12.x or later will encounter errors when
|
||||
processing CUDA source files:
|
||||
@@ -1804,16 +1810,9 @@ hipify-clang --cuda-gpu-arch=sm_70...
|
||||
```
|
||||
This issue will be fixed in a future release.
|
||||
|
||||
### HIP Graph memory leak tests report invalid reads
|
||||
### HIP Graph API tutorial code build fails
|
||||
|
||||
The `memLeak_Phase2` HIP Graph test suite fails with `hipGraphInstantiate_leak`
|
||||
and `hipGraph_AddMemAlloc` tests reporting invalid memory reads. Impact is
|
||||
minimal as the issue only occurs during shutdown after the workload is
|
||||
complete. This issue will be fixed in a future release.
|
||||
|
||||
### ROCm examples HIP Graph tutorial code build fails
|
||||
|
||||
The HIP Graph tutorial code fails to build on Linux due to a missing `-fPIC`
|
||||
The HIP Graph API tutorial code fails to build on Linux due to a missing `-fPIC`
|
||||
compiler flag. To resolve this issue, enable position-independent code in the
|
||||
main `CMakeLists.txt` by adding `set(CMAKE_POSITION_INDEPENDENT_CODE ON)` as in the
|
||||
fix in [ROCm/rocm-examples PR
|
||||
|
||||
@@ -161,7 +161,7 @@
|
||||
|
||||
.. matrix-cell::
|
||||
|
||||
`31.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-31.10.0/documentation/release-notes.html>`__
|
||||
`31.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/documentation/release-notes.html>`__
|
||||
|
||||
`30.20.1 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.20.1/documentation/release-notes.html>`__
|
||||
|
||||
|
||||
@@ -100,7 +100,7 @@
|
||||
|
||||
.. matrix-cell::
|
||||
|
||||
`31.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-31.10.0/documentation/release-notes.html>`__
|
||||
`31.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/documentation/release-notes.html>`__
|
||||
|
||||
`30.20.1 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.20.1/documentation/release-notes.html>`__
|
||||
|
||||
|
||||
@@ -90,7 +90,7 @@
|
||||
|
||||
.. matrix-cell::
|
||||
|
||||
`31.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-31.10.0/documentation/release-notes.html>`__
|
||||
`31.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/documentation/release-notes.html>`__
|
||||
|
||||
`30.20.1 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.20.1/documentation/release-notes.html>`__
|
||||
|
||||
|
||||
@@ -10,7 +10,7 @@ import sys
|
||||
from pathlib import Path
|
||||
|
||||
ROCM_VERSION = "7.11.0"
|
||||
GA_DATE = "2025-02-11"
|
||||
GA_DATE = "2026-02-11"
|
||||
|
||||
DOCS_DIR = Path(__file__).parent.resolve()
|
||||
ROOT_DIR = DOCS_DIR.parent
|
||||
@@ -153,7 +153,7 @@ html_theme_options = {
|
||||
"GitHub": "https://github.com/ROCm/ROCm",
|
||||
"Community": "https://github.com/ROCm/ROCm/discussions",
|
||||
"Blogs": "https://rocm.blogs.amd.com/",
|
||||
"Instinct™ Docs": "https://instinct.docs.amd.com/",
|
||||
"System and Infra Docs": "https://instinct.docs.amd.com/",
|
||||
"Support": "https://github.com/ROCm/ROCm/issues/new/choose",
|
||||
},
|
||||
"link_main_doc": False,
|
||||
|
||||
@@ -32,42 +32,42 @@ see the :doc:`Compatibility matrix </compatibility/compatibility-matrix>`.
|
||||
|
||||
For instructions on installing the AMD GPU Driver (amdgpu), see `Ubuntu native
|
||||
installation
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/install/detailed-install/package-manager/package-manager-ubuntu.html>`__
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/install/detailed-install/package-manager/package-manager-ubuntu.html>`__
|
||||
in the AMD Instinct Data Center GPU Documentation.
|
||||
|
||||
.. selected:: os=debian
|
||||
|
||||
For instructions on installing the AMD GPU Driver (amdgpu), see `Debian native
|
||||
installation
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/install/detailed-install/package-manager/package-manager-debian.html>`__
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/install/detailed-install/package-manager/package-manager-debian.html>`__
|
||||
in the AMD Instinct Data Center GPU Documentation.
|
||||
|
||||
.. selected:: os=rhel
|
||||
|
||||
For instructions on installing the AMD GPU Driver (amdgpu), see `RHEL native
|
||||
installation
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/install/detailed-install/package-manager/package-manager-rhel.html>`__
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/install/detailed-install/package-manager/package-manager-rhel.html>`__
|
||||
in the AMD Instinct Data Center GPU Documentation.
|
||||
|
||||
.. selected:: os=oracle-linux
|
||||
|
||||
For instructions on installing the AMD GPU Driver (amdgpu), see `Oracle Linux native
|
||||
installation
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/install/detailed-install/package-manager/package-manager-ol.html>`__
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/install/detailed-install/package-manager/package-manager-ol.html>`__
|
||||
in the AMD Instinct Data Center GPU Documentation.
|
||||
|
||||
.. selected:: os=rocky-linux
|
||||
|
||||
For instructions on installing the AMD GPU Driver (amdgpu), see `Rocky Linux native
|
||||
installation
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/install/detailed-install/package-manager/package-manager-rl.html>`__
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/install/detailed-install/package-manager/package-manager-rl.html>`__
|
||||
in the AMD Instinct Data Center GPU Documentation.
|
||||
|
||||
.. selected:: os=sles
|
||||
|
||||
For instructions on installing the AMD GPU Driver (amdgpu), see `SLES
|
||||
native installation
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/install/detailed-install/package-manager/package-manager-sles.html>`__
|
||||
<https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.10.0-preview/install/detailed-install/package-manager/package-manager-sles.html>`__
|
||||
in the AMD Instinct Data Center GPU Documentation.
|
||||
|
||||
.. selected:: fam=ryzen
|
||||
|
||||
@@ -314,33 +314,6 @@ Prerequisites
|
||||
|
||||
sudo crb enable
|
||||
|
||||
.. selected:: i=tar i=pip
|
||||
|
||||
.. selected:: os=sles
|
||||
:heading: Add additional package repositories
|
||||
:heading-level: 3
|
||||
|
||||
ROCm installation packages depend on packages that aren’t included in
|
||||
the default package repositories. Use the following command to add the
|
||||
necessary repositories.
|
||||
|
||||
.. selected:: os-version=16.0
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
sudo SUSEConnect -p sle-module-desktop-applications/16.0/x86_64
|
||||
sudo SUSEConnect -p sle-module-development-tools/16.0/x86_64
|
||||
sudo SUSEConnect -p PackageHub/16.0/x86_64
|
||||
|
||||
.. selected:: os-version=15.7
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
sudo SUSEConnect -p sle-module-desktop-applications/15.7/x86_64
|
||||
sudo SUSEConnect -p sle-module-development-tools/15.7/x86_64
|
||||
sudo SUSEConnect -p PackageHub/15.7/x86_64
|
||||
|
||||
|
||||
.. ============================================== INSTALL ADDITIONAL PACKAGES ==
|
||||
|
||||
.. selected:: os=ubuntu os=debian os=rhel os=oracle-linux os=rocky-linux os=sles
|
||||
|
||||
@@ -200,7 +200,6 @@ showcasing AI-powered image generation.
|
||||
|
||||
.. selector-option:: Linux
|
||||
:value: linux
|
||||
:icon: fab fa-linux fa-lg
|
||||
:width: 12
|
||||
|
||||
.. selector:: Operating system
|
||||
@@ -209,12 +208,10 @@ showcasing AI-powered image generation.
|
||||
|
||||
.. selector-option:: Linux
|
||||
:value: linux
|
||||
:icon: fab fa-linux fa-lg
|
||||
:width: 6
|
||||
|
||||
.. selector-option:: Windows
|
||||
:value: windows
|
||||
:icon: fab fa-windows fa-lg
|
||||
:width: 6
|
||||
:disable-when: fam=instinct
|
||||
|
||||
|
||||
Reference in New Issue
Block a user