OSS the TorchRec MPZCH CPU kernel functions #4295
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
This pull request was exported from Phabricator. Differential Revision: D76233478 |
lizhouyu
added a commit
to lizhouyu/FBGEMM-1
that referenced
this pull request
Jun 9, 2025
Summary: X-link: facebookresearch/FBGEMM#1371 ### Major changes In `FbgemmGpu.cmake`: - Remove the skip ROCM lines for CPU build ``` if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_ROCM) list(APPEND fbgemm_gpu_sources_cpu_static src/faster_hash_ops/faster_hash.cpp) endif() ``` - Add CPP source file into the `fbgemm_gpu_sources_cpu_static` list Differential Revision: D76233478
lizhouyu
force-pushed
the
export-D76233478
branch
from
c33083e to
4cff315
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76233478 |
lizhouyu
added a commit
to lizhouyu/FBGEMM-1
that referenced
this pull request
Jun 9, 2025
Summary: X-link: facebookresearch/FBGEMM#1371 ### Major changes In `FbgemmGpu.cmake`: - Remove the skip ROCM lines for CPU build ``` if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_ROCM) list(APPEND fbgemm_gpu_sources_cpu_static src/faster_hash_ops/faster_hash.cpp) endif() ``` - Add CPP source file into the `fbgemm_gpu_sources_cpu_static` list Differential Revision: D76233478
lizhouyu
force-pushed
the
export-D76233478
branch
from
4cff315 to
928ad4c
Compare
lizhouyu
added a commit
to lizhouyu/FBGEMM-1
that referenced
this pull request
Jun 9, 2025
Summary: X-link: facebookresearch/FBGEMM#1371 ### Major changes In `FbgemmGpu.cmake`: - Remove the skip ROCM lines for CPU build ``` if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_ROCM) list(APPEND fbgemm_gpu_sources_cpu_static src/faster_hash_ops/faster_hash.cpp) endif() ``` - Add CPP source file into the `fbgemm_gpu_sources_cpu_static` list Differential Revision: D76233478
lizhouyu
force-pushed
the
export-D76233478
branch
from
928ad4c to
b50ca8b
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76233478 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D76233478 |
lizhouyu
added a commit
to lizhouyu/FBGEMM-1
that referenced
this pull request
Jun 9, 2025
Summary: Pull Request resolved: pytorch#4295 X-link: facebookresearch/FBGEMM#1371 ### Major changes In `FbgemmGpu.cmake`: - Remove the skip ROCM lines for CPU build ``` if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_ROCM) list(APPEND fbgemm_gpu_sources_cpu_static src/faster_hash_ops/faster_hash.cpp) endif() ``` - Add CPP source file into the `fbgemm_gpu_sources_cpu_static` list Differential Revision: D76233478
lizhouyu
force-pushed
the
export-D76233478
branch
from
b50ca8b to
8119e36
Compare
lizhouyu
added a commit
to lizhouyu/FBGEMM-1
that referenced
this pull request
Jun 9, 2025
Summary: X-link: facebookresearch/FBGEMM#1371 ### Major changes In `FbgemmGpu.cmake`: - Remove the skip ROCM lines for CPU build ``` if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_ROCM) list(APPEND fbgemm_gpu_sources_cpu_static src/faster_hash_ops/faster_hash.cpp) endif() ``` - Add CPP source file into the `fbgemm_gpu_sources_cpu_static` list Differential Revision: D76233478
lizhouyu
force-pushed
the
export-D76233478
branch
from
8119e36 to
249c7a2
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76233478 |
lizhouyu
force-pushed
the
export-D76233478
branch
from
249c7a2 to
d70ad1f
Compare
lizhouyu
added a commit
to lizhouyu/FBGEMM-1
that referenced
this pull request
Jun 9, 2025
Summary: X-link: facebookresearch/FBGEMM#1371 ### Motivation - The `faster_hash_ops` related kernel functions are not picked up in the CPU build of the FBGEMM library. - To resolve this, we rewrite the cmake file to make these functions available in packages built for CPU environment. ### Major changes In `FbgemmGpu.cmake`: - Move the skip ROCM lines for CPU build from inside the `if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_CPU)` condition to before this condition check ``` if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_ROCM) list(APPEND fbgemm_gpu_sources_cpu_static src/faster_hash_ops/faster_hash.cpp) endif() ``` - Add DocStrings to header files in `fbgemm_gpu/include/febgemm_gpu`, and add document configurations in `fbgemm_gpu/docs/src/fbgemm_gpu/cpp-api`. ### ToDo - Separate the shared CPU and GPU header file `common_utils.cuh` to two files used for CPU and GPU, respectively. Differential Revision: D76233478
|
This pull request was exported from Phabricator. Differential Revision: D76233478 |
Summary: X-link: facebookresearch/FBGEMM#1371 ### Motivation - The `faster_hash_ops` related kernel functions are not picked up in the CPU build of the FBGEMM library. - To resolve this, we rewrite the cmake file to make these functions available in packages built for CPU environment. ### Major changes In `FbgemmGpu.cmake`: - Move the skip ROCM lines for CPU build from inside the `if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_CPU)` condition to before this condition check ``` if(NOT FBGEMM_BUILD_VARIANT STREQUAL BUILD_VARIANT_ROCM) list(APPEND fbgemm_gpu_sources_cpu_static src/faster_hash_ops/faster_hash.cpp) endif() ``` - Add DocStrings to header files in `fbgemm_gpu/include/febgemm_gpu`, and add document configurations in `fbgemm_gpu/docs/src/fbgemm_gpu/cpp-api`. ### ToDo - Separate the shared CPU and GPU header file `common_utils.cuh` to two files used for CPU and GPU, respectively. Differential Revision: D76233478
lizhouyu
force-pushed
the
export-D76233478
branch
from
d70ad1f to
f75d0a8
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76233478 |
|
This pull request has been merged in 7b221dd. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
X-link: https://github.com/facebookresearch/FBGEMM/pull/1371
Major changes
In
FbgemmGpu.cmake:fbgemm_gpu_sources_cpu_staticlistDifferential Revision: D76233478