mirror of
https://github.com/ROCm/ROCm.git
synced 2026-01-17 02:28:04 -05:00
Compare commits
4 Commits
develop
...
deep-frame
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
8d183c2e95 | ||
|
|
3a7cfd3958 | ||
|
|
833fdf4c95 | ||
|
|
28f028d304 |
@@ -32,6 +32,7 @@ parameters:
|
|||||||
- name: aptPackages
|
- name: aptPackages
|
||||||
type: object
|
type: object
|
||||||
default:
|
default:
|
||||||
|
- cmake
|
||||||
- gfortran
|
- gfortran
|
||||||
- git
|
- git
|
||||||
- libboost-program-options-dev
|
- libboost-program-options-dev
|
||||||
@@ -41,7 +42,6 @@ parameters:
|
|||||||
- name: rocmDependencies
|
- name: rocmDependencies
|
||||||
type: object
|
type: object
|
||||||
default:
|
default:
|
||||||
- aomp
|
|
||||||
- clr
|
- clr
|
||||||
- llvm-project
|
- llvm-project
|
||||||
- rocminfo
|
- rocminfo
|
||||||
@@ -51,7 +51,6 @@ parameters:
|
|||||||
- name: rocmTestDependencies
|
- name: rocmTestDependencies
|
||||||
type: object
|
type: object
|
||||||
default:
|
default:
|
||||||
- aomp
|
|
||||||
- clr
|
- clr
|
||||||
- llvm-project
|
- llvm-project
|
||||||
- hipBLAS-common
|
- hipBLAS-common
|
||||||
@@ -104,7 +103,6 @@ jobs:
|
|||||||
parameters:
|
parameters:
|
||||||
aptPackages: ${{ parameters.aptPackages }}
|
aptPackages: ${{ parameters.aptPackages }}
|
||||||
packageManager: ${{ job.packageManager }}
|
packageManager: ${{ job.packageManager }}
|
||||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
|
|
||||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||||
parameters:
|
parameters:
|
||||||
@@ -130,7 +128,6 @@ jobs:
|
|||||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
|
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
|
||||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
|
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
|
||||||
-DCMAKE_Fortran_COMPILER=gfortran
|
|
||||||
-DCMAKE_BUILD_TYPE=Release
|
-DCMAKE_BUILD_TYPE=Release
|
||||||
-DBUILD_CLIENTS_TESTS=ON
|
-DBUILD_CLIENTS_TESTS=ON
|
||||||
-DBUILD_CLIENTS_SAMPLES=OFF
|
-DBUILD_CLIENTS_SAMPLES=OFF
|
||||||
|
|||||||
@@ -24,7 +24,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
- GitHub
|
- GitHub
|
||||||
|
|
||||||
* - :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`
|
* - :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/pytorch-install>`
|
- :doc:`Pytorch install <rocm-install-on-linux:install/3rd-party/pytorch-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- Wheels package
|
- Wheels package
|
||||||
@@ -35,7 +35,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
<a href="https://github.com/ROCm/pytorch"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/pytorch"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`
|
* - :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
|
- :doc:`TensorFlow install <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- Wheels package
|
- Wheels package
|
||||||
@@ -45,7 +45,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
<a href="https://github.com/ROCm/tensorflow-upstream"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/tensorflow-upstream"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`
|
* - :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/jax-install>`
|
- :doc:`JAX install <rocm-install-on-linux:install/3rd-party/jax-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- .. raw:: html
|
- .. raw:: html
|
||||||
@@ -53,7 +53,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
<a href="https://github.com/ROCm/jax"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/jax"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>`
|
* - :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/verl-install>`
|
- :doc:`verl install <rocm-install-on-linux:install/3rd-party/verl-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- .. raw:: html
|
- .. raw:: html
|
||||||
@@ -61,7 +61,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
<a href="https://github.com/ROCm/verl"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/verl"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
|
* - :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
|
- :doc:`Stanford Megatron-LM install <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- .. raw:: html
|
- .. raw:: html
|
||||||
@@ -69,7 +69,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
<a href="https://github.com/ROCm/Stanford-Megatron-LM"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/Stanford-Megatron-LM"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`
|
* - :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/dgl-install>`
|
- :doc:`DGL install <rocm-install-on-linux:install/3rd-party/dgl-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- .. raw:: html
|
- .. raw:: html
|
||||||
@@ -77,15 +77,24 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
<a href="https://github.com/ROCm/dgl"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/dgl"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`
|
* - :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/megablocks-install>`
|
- :doc:`Megablocks install <rocm-install-on-linux:install/3rd-party/megablocks-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- .. raw:: html
|
- .. raw:: html
|
||||||
|
|
||||||
<a href="https://github.com/ROCm/megablocks"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/megablocks"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
|
* - :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>`
|
||||||
|
- `Taichi install <https://rocm.docs.amd.com/projects/taichi/en/latest/install/taichi-install.html>`__
|
||||||
|
-
|
||||||
|
- Docker image
|
||||||
|
- Wheels package
|
||||||
|
- .. raw:: html
|
||||||
|
|
||||||
|
<a href="https://github.com/ROCm/taichi"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>`
|
* - :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/ray-install>`
|
- :doc:`Ray install <rocm-install-on-linux:install/3rd-party/ray-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- Wheels package
|
- Wheels package
|
||||||
@@ -95,7 +104,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
<a href="https://github.com/ROCm/ray"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/ray"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>`
|
* - :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/llama-cpp-install>`
|
- :doc:`llama.cpp install <rocm-install-on-linux:install/3rd-party/llama-cpp-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- ROCm Base Docker image
|
- ROCm Base Docker image
|
||||||
@@ -104,7 +113,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
|
|||||||
<a href="https://github.com/ROCm/llama.cpp"><i class="fab fa-github fa-lg"></i></a>
|
<a href="https://github.com/ROCm/llama.cpp"><i class="fab fa-github fa-lg"></i></a>
|
||||||
|
|
||||||
* - :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>`
|
* - :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>`
|
||||||
- :doc:`link <rocm-install-on-linux:install/3rd-party/flashinfer-install>`
|
- :doc:`FlashInfer install <rocm-install-on-linux:install/3rd-party/flashinfer-install>`
|
||||||
-
|
-
|
||||||
- Docker image
|
- Docker image
|
||||||
- ROCm Base Docker image
|
- ROCm Base Docker image
|
||||||
|
|||||||
@@ -5,7 +5,7 @@
|
|||||||
GPU hardware specifications
|
GPU hardware specifications
|
||||||
===========================================
|
===========================================
|
||||||
|
|
||||||
The following tables provide an overview of the hardware specifications for AMD Instinct™ GPUs, AMD Radeon™ PRO and Radeon™ GPUs, and AMD Ryzen™ APUs.
|
The following tables provide an overview of the hardware specifications for AMD Instinct™ GPUs, and AMD Radeon™ PRO and Radeon™ GPUs.
|
||||||
|
|
||||||
For more information about ROCm hardware compatibility, see the ROCm `Compatibility matrix <https://rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html>`_.
|
For more information about ROCm hardware compatibility, see the ROCm `Compatibility matrix <https://rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html>`_.
|
||||||
|
|
||||||
@@ -18,7 +18,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
|
|||||||
:name: instinct-arch-spec-table
|
:name: instinct-arch-spec-table
|
||||||
|
|
||||||
*
|
*
|
||||||
- Name
|
- Model
|
||||||
- Architecture
|
- Architecture
|
||||||
- LLVM target name
|
- LLVM target name
|
||||||
- VRAM (GiB)
|
- VRAM (GiB)
|
||||||
@@ -297,7 +297,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
|
|||||||
:name: radeon-pro-arch-spec-table
|
:name: radeon-pro-arch-spec-table
|
||||||
|
|
||||||
*
|
*
|
||||||
- Name
|
- Model
|
||||||
- Architecture
|
- Architecture
|
||||||
- LLVM target name
|
- LLVM target name
|
||||||
|
|
||||||
@@ -539,7 +539,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
|
|||||||
:name: radeon-arch-spec-table
|
:name: radeon-arch-spec-table
|
||||||
|
|
||||||
*
|
*
|
||||||
- Name
|
- Model
|
||||||
- Architecture
|
- Architecture
|
||||||
- LLVM target name
|
- LLVM target name
|
||||||
- VRAM (GiB)
|
- VRAM (GiB)
|
||||||
@@ -953,127 +953,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
|
|||||||
- 9
|
- 9
|
||||||
- 0
|
- 0
|
||||||
|
|
||||||
.. tab-item:: AMD Ryzen APUs
|
|
||||||
|
|
||||||
.. list-table::
|
|
||||||
:header-rows: 1
|
|
||||||
:name: ryzen-arch-spec-table
|
|
||||||
|
|
||||||
*
|
|
||||||
- Name
|
|
||||||
- Graphics model
|
|
||||||
- Architecture
|
|
||||||
- LLVM target name
|
|
||||||
- VRAM (GiB)
|
|
||||||
- Compute Units
|
|
||||||
- Wavefront Size
|
|
||||||
- LDS (KiB)
|
|
||||||
- Infinity Cache (MiB)
|
|
||||||
- L2 Cache (MiB)
|
|
||||||
- Graphics L1 Cache (KiB)
|
|
||||||
- L0 Vector Cache (KiB)
|
|
||||||
- L0 Scalar Cache (KiB)
|
|
||||||
- L0 Instruction Cache (KiB)
|
|
||||||
- VGPR File (KiB)
|
|
||||||
- SGPR File (KiB)
|
|
||||||
- GFXIP Major version
|
|
||||||
- GFXIP Minor version
|
|
||||||
*
|
|
||||||
- AMD Ryzen 7 7840U
|
|
||||||
- Radeon 780M
|
|
||||||
- RDNA3
|
|
||||||
- gfx1103
|
|
||||||
- Dynamic + carveout
|
|
||||||
- 12
|
|
||||||
- 32 or 64
|
|
||||||
- 128
|
|
||||||
- N/A
|
|
||||||
- 2
|
|
||||||
- 256
|
|
||||||
- 32
|
|
||||||
- 16
|
|
||||||
- 32
|
|
||||||
- 512
|
|
||||||
- 32
|
|
||||||
- 11
|
|
||||||
- 0
|
|
||||||
*
|
|
||||||
- AMD Ryzen 9 270
|
|
||||||
- Radeon 780M
|
|
||||||
- RDNA3
|
|
||||||
- gfx1103
|
|
||||||
- Dynamic + carveout
|
|
||||||
- 12
|
|
||||||
- 32 or 64
|
|
||||||
- 128
|
|
||||||
- N/A
|
|
||||||
- 2
|
|
||||||
- 256
|
|
||||||
- 32
|
|
||||||
- 16
|
|
||||||
- 32
|
|
||||||
- 512
|
|
||||||
- 32
|
|
||||||
- 11
|
|
||||||
- 0
|
|
||||||
*
|
|
||||||
- AMD Ryzen AI 9 HX 375
|
|
||||||
- Radeon 890M
|
|
||||||
- RDNA3.5
|
|
||||||
- gfx1150
|
|
||||||
- Dynamic + carveout
|
|
||||||
- 16
|
|
||||||
- 32 or 64
|
|
||||||
- 128
|
|
||||||
- N/A
|
|
||||||
- 2
|
|
||||||
- 256
|
|
||||||
- 32
|
|
||||||
- 16
|
|
||||||
- 32
|
|
||||||
- 512
|
|
||||||
- 32
|
|
||||||
- 11
|
|
||||||
- 5
|
|
||||||
*
|
|
||||||
- AMD Ryzen AI Max+ PRO 395
|
|
||||||
- Radeon 8060S
|
|
||||||
- RDNA3.5
|
|
||||||
- gfx1151
|
|
||||||
- Dynamic + carveout
|
|
||||||
- 40
|
|
||||||
- 32 or 64
|
|
||||||
- 128
|
|
||||||
- 32
|
|
||||||
- 2
|
|
||||||
- 256
|
|
||||||
- 32
|
|
||||||
- 16
|
|
||||||
- 32
|
|
||||||
- 768
|
|
||||||
- 32
|
|
||||||
- 11
|
|
||||||
- 5
|
|
||||||
*
|
|
||||||
- AMD Ryzen Al 7 350
|
|
||||||
- Radeon 860M
|
|
||||||
- RDNA3.5
|
|
||||||
- gfx1152
|
|
||||||
- Dynamic + carveout
|
|
||||||
- 8
|
|
||||||
- 32 or 64
|
|
||||||
- 128
|
|
||||||
- N/A
|
|
||||||
- 1
|
|
||||||
- 256
|
|
||||||
- 32
|
|
||||||
- 16
|
|
||||||
- 32
|
|
||||||
- 512
|
|
||||||
- 32
|
|
||||||
- 11
|
|
||||||
- 5
|
|
||||||
|
|
||||||
Glossary
|
Glossary
|
||||||
========
|
========
|
||||||
|
|
||||||
|
|||||||
@@ -29,25 +29,27 @@ subtrees:
|
|||||||
title: Deep learning frameworks
|
title: Deep learning frameworks
|
||||||
subtrees:
|
subtrees:
|
||||||
- entries:
|
- entries:
|
||||||
- file: compatibility/ml-compatibility/pytorch-compatibility.rst
|
- file: compatibility/ml-compatibility/pytorch-compatibility
|
||||||
title: PyTorch compatibility
|
title: PyTorch compatibility
|
||||||
- file: compatibility/ml-compatibility/tensorflow-compatibility.rst
|
- file: compatibility/ml-compatibility/tensorflow-compatibility
|
||||||
title: TensorFlow compatibility
|
title: TensorFlow compatibility
|
||||||
- file: compatibility/ml-compatibility/jax-compatibility.rst
|
- file: compatibility/ml-compatibility/jax-compatibility
|
||||||
title: JAX compatibility
|
title: JAX compatibility
|
||||||
- file: compatibility/ml-compatibility/verl-compatibility.rst
|
- file: compatibility/ml-compatibility/verl-compatibility
|
||||||
title: verl compatibility
|
title: verl compatibility
|
||||||
- file: compatibility/ml-compatibility/stanford-megatron-lm-compatibility.rst
|
- file: compatibility/ml-compatibility/stanford-megatron-lm-compatibility
|
||||||
title: Stanford Megatron-LM compatibility
|
title: Stanford Megatron-LM compatibility
|
||||||
- file: compatibility/ml-compatibility/dgl-compatibility.rst
|
- file: compatibility/ml-compatibility/dgl-compatibility
|
||||||
title: DGL compatibility
|
title: DGL compatibility
|
||||||
- file: compatibility/ml-compatibility/megablocks-compatibility.rst
|
- file: compatibility/ml-compatibility/megablocks-compatibility
|
||||||
title: Megablocks compatibility
|
title: Megablocks compatibility
|
||||||
- file: compatibility/ml-compatibility/ray-compatibility.rst
|
- file: compatibility/ml-compatibility/taichi-compatibility
|
||||||
|
title: Taichi compatibility
|
||||||
|
- file: compatibility/ml-compatibility/ray-compatibility
|
||||||
title: Ray compatibility
|
title: Ray compatibility
|
||||||
- file: compatibility/ml-compatibility/llama-cpp-compatibility.rst
|
- file: compatibility/ml-compatibility/llama-cpp-compatibility
|
||||||
title: llama.cpp compatibility
|
title: llama.cpp compatibility
|
||||||
- file: compatibility/ml-compatibility/flashinfer-compatibility.rst
|
- file: compatibility/ml-compatibility/flashinfer-compatibility
|
||||||
title: FlashInfer compatibility
|
title: FlashInfer compatibility
|
||||||
- file: how-to/build-rocm.rst
|
- file: how-to/build-rocm.rst
|
||||||
title: Build ROCm from source
|
title: Build ROCm from source
|
||||||
@@ -75,14 +77,8 @@ subtrees:
|
|||||||
- entries:
|
- entries:
|
||||||
- file: how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
|
- file: how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
|
||||||
title: Train a model with Primus and Megatron-LM
|
title: Train a model with Primus and Megatron-LM
|
||||||
entries:
|
|
||||||
- file: how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst
|
|
||||||
title: Train a model with Megatron-LM
|
|
||||||
- file: how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
|
- file: how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
|
||||||
title: Train a model with Primus and PyTorch
|
title: Train a model with Primus and PyTorch
|
||||||
entries:
|
|
||||||
- file: how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
|
|
||||||
title: Train a model with PyTorch
|
|
||||||
- file: how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
|
- file: how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
|
||||||
title: Train a model with JAX MaxText
|
title: Train a model with JAX MaxText
|
||||||
- file: how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry
|
- file: how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry
|
||||||
@@ -121,8 +117,6 @@ subtrees:
|
|||||||
title: SGLang inference performance testing
|
title: SGLang inference performance testing
|
||||||
- file: how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
|
- file: how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
|
||||||
title: SGLang distributed inference with Mooncake
|
title: SGLang distributed inference with Mooncake
|
||||||
- file: how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst
|
|
||||||
title: xDiT diffusion inference
|
|
||||||
- file: how-to/rocm-for-ai/inference/deploy-your-model.rst
|
- file: how-to/rocm-for-ai/inference/deploy-your-model.rst
|
||||||
title: Deploy your model
|
title: Deploy your model
|
||||||
|
|
||||||
@@ -140,8 +134,6 @@ subtrees:
|
|||||||
title: Profile and debug
|
title: Profile and debug
|
||||||
- file: how-to/rocm-for-ai/inference-optimization/workload.rst
|
- file: how-to/rocm-for-ai/inference-optimization/workload.rst
|
||||||
title: Workload optimization
|
title: Workload optimization
|
||||||
- file: how-to/rocm-for-ai/inference-optimization/vllm-optimization.rst
|
|
||||||
title: vLLM V1 performance optimization
|
|
||||||
|
|
||||||
- url: https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/
|
- url: https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/
|
||||||
title: AI tutorials
|
title: AI tutorials
|
||||||
@@ -188,7 +180,7 @@ subtrees:
|
|||||||
- file: conceptual/gpu-arch/mi300-mi200-performance-counters.rst
|
- file: conceptual/gpu-arch/mi300-mi200-performance-counters.rst
|
||||||
title: MI300 and MI200 performance counters
|
title: MI300 and MI200 performance counters
|
||||||
- file: conceptual/gpu-arch/mi350-performance-counters.rst
|
- file: conceptual/gpu-arch/mi350-performance-counters.rst
|
||||||
title: MI350 Series performance counters
|
title: MI350 series performance counters
|
||||||
- file: conceptual/gpu-arch/mi250.md
|
- file: conceptual/gpu-arch/mi250.md
|
||||||
title: MI250 microarchitecture
|
title: MI250 microarchitecture
|
||||||
subtrees:
|
subtrees:
|
||||||
@@ -222,8 +214,6 @@ subtrees:
|
|||||||
title: ROCm tools, compilers, and runtimes
|
title: ROCm tools, compilers, and runtimes
|
||||||
- file: reference/gpu-arch-specs.rst
|
- file: reference/gpu-arch-specs.rst
|
||||||
- file: reference/gpu-atomics-operation.rst
|
- file: reference/gpu-atomics-operation.rst
|
||||||
- file: reference/env-variables.rst
|
|
||||||
title: Environment variables
|
|
||||||
- file: reference/precision-support.rst
|
- file: reference/precision-support.rst
|
||||||
title: Data types and precision support
|
title: Data types and precision support
|
||||||
- file: reference/graph-safe-support.rst
|
- file: reference/graph-safe-support.rst
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
rocm-docs-core==1.31.3
|
rocm-docs-core==1.31.2
|
||||||
sphinx-reredirects
|
sphinx-reredirects
|
||||||
sphinx-sitemap
|
sphinx-sitemap
|
||||||
sphinxcontrib.datatemplates==0.11.0
|
sphinxcontrib.datatemplates==0.11.0
|
||||||
|
|||||||
@@ -188,7 +188,7 @@ requests==2.32.5
|
|||||||
# via
|
# via
|
||||||
# pygithub
|
# pygithub
|
||||||
# sphinx
|
# sphinx
|
||||||
rocm-docs-core==1.31.3
|
rocm-docs-core==1.31.2
|
||||||
# via -r requirements.in
|
# via -r requirements.in
|
||||||
rpds-py==0.30.0
|
rpds-py==0.30.0
|
||||||
# via
|
# via
|
||||||
@@ -214,7 +214,6 @@ sphinx==8.1.3
|
|||||||
# sphinx-design
|
# sphinx-design
|
||||||
# sphinx-external-toc
|
# sphinx-external-toc
|
||||||
# sphinx-last-updated-by-git
|
# sphinx-last-updated-by-git
|
||||||
# sphinx-multitoc-numbering
|
|
||||||
# sphinx-notfound-page
|
# sphinx-notfound-page
|
||||||
# sphinx-reredirects
|
# sphinx-reredirects
|
||||||
# sphinxcontrib-datatemplates
|
# sphinxcontrib-datatemplates
|
||||||
@@ -225,12 +224,10 @@ sphinx-copybutton==0.5.2
|
|||||||
# via rocm-docs-core
|
# via rocm-docs-core
|
||||||
sphinx-design==0.6.1
|
sphinx-design==0.6.1
|
||||||
# via rocm-docs-core
|
# via rocm-docs-core
|
||||||
sphinx-external-toc==1.1.0
|
sphinx-external-toc==1.0.1
|
||||||
# via rocm-docs-core
|
# via rocm-docs-core
|
||||||
sphinx-last-updated-by-git==0.3.8
|
sphinx-last-updated-by-git==0.3.8
|
||||||
# via sphinx-sitemap
|
# via sphinx-sitemap
|
||||||
sphinx-multitoc-numbering==0.1.3
|
|
||||||
# via sphinx-external-toc
|
|
||||||
sphinx-notfound-page==1.1.0
|
sphinx-notfound-page==1.1.0
|
||||||
# via rocm-docs-core
|
# via rocm-docs-core
|
||||||
sphinx-reredirects==0.1.6
|
sphinx-reredirects==0.1.6
|
||||||
|
|||||||
Reference in New Issue
Block a user