fused moe fix #4534
Open
fused moe fix #4534
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: D78679653 |
xw285cornell
force-pushed
the
export-D78679653
branch
from
613abeb to
632bfe2
Compare
xw285cornell
added a commit
to xw285cornell/FBGEMM
that referenced
this pull request
Jul 22, 2025
Summary: X-link: facebookresearch/FBGEMM#1579 A number of changes on CK header that we need downstream fixes: * local token was added to MoeSortingProblemEx: https://github.com/ROCm/composable_kernel/blob/develop/include/ck_tile/ops/fused_moe/kernel/moe_sorting_problem.hpp#L48 * MeshType_ was added to MoeSortingProblemMp: https://github.com/ROCm/composable_kernel/blob/develop/include/ck_tile/ops/fused_moe/kernel/moe_sorting_problem.hpp#L56 * MOE_SORTING_FMOE_2D_BUF was added which I just turn off for now ``` In file included from buck-out/v2/gen/fbcode/de5ab6968d300cd2/deeplearning/fbgemm/fbgemm_gpu/experimental/gen_ai/src/quantize/ck_extensions/__ck_fused_moe_hipify_gen__/out/fused_moe/instances/fused_moesorting_api.hip:4: In file included from fbcode/deeplearning/fbgemm/fbgemm_gpu/experimental/gen_ai/src/quantize/ck_extensions/fused_moe/fused_moesorting.hpp:8: In file included from third-party/rocm_composable_kernel/include/ck_tile/ops/fused_moe.hpp:9: third-party/rocm_composable_kernel/include/ck_tile/ops/fused_moe/kernel/moe_sorting_kernel.hpp:2100:11: error: no member named 'moe_buf_elem_bytes' in 'ck_tile::MoeSortingMultiPhaseKernel_P2<ck_tile::MoeSortingProblemMp<int, float, int, 1, false, false>>::Kargs' 2100 | k.moe_buf_elem_bytes = h.moe_buf_elem_bytes; | ~ ^ ``` Reviewed By: zjing14 Differential Revision: D78679653
|
This pull request was exported from Phabricator. Differential Revision: D78679653 |
xw285cornell
added a commit
to xw285cornell/FBGEMM
that referenced
this pull request
Jul 22, 2025
Summary: Pull Request resolved: pytorch#4534 X-link: facebookresearch/FBGEMM#1579 A number of changes on CK header that we need downstream fixes: * local token was added to MoeSortingProblemEx: https://github.com/ROCm/composable_kernel/blob/develop/include/ck_tile/ops/fused_moe/kernel/moe_sorting_problem.hpp#L48 * MeshType_ was added to MoeSortingProblemMp: https://github.com/ROCm/composable_kernel/blob/develop/include/ck_tile/ops/fused_moe/kernel/moe_sorting_problem.hpp#L56 * MOE_SORTING_FMOE_2D_BUF was added which I just turn off for now ``` In file included from buck-out/v2/gen/fbcode/de5ab6968d300cd2/deeplearning/fbgemm/fbgemm_gpu/experimental/gen_ai/src/quantize/ck_extensions/__ck_fused_moe_hipify_gen__/out/fused_moe/instances/fused_moesorting_api.hip:4: In file included from fbcode/deeplearning/fbgemm/fbgemm_gpu/experimental/gen_ai/src/quantize/ck_extensions/fused_moe/fused_moesorting.hpp:8: In file included from third-party/rocm_composable_kernel/include/ck_tile/ops/fused_moe.hpp:9: third-party/rocm_composable_kernel/include/ck_tile/ops/fused_moe/kernel/moe_sorting_kernel.hpp:2100:11: error: no member named 'moe_buf_elem_bytes' in 'ck_tile::MoeSortingMultiPhaseKernel_P2<ck_tile::MoeSortingProblemMp<int, float, int, 1, false, false>>::Kargs' 2100 | k.moe_buf_elem_bytes = h.moe_buf_elem_bytes; | ~ ^ ``` Reviewed By: zjing14 Differential Revision: D78679653
xw285cornell
force-pushed
the
export-D78679653
branch
from
632bfe2 to
c9affaa
Compare
Summary: Pull Request resolved: pytorch#4534 X-link: facebookresearch/FBGEMM#1579 A number of changes on CK header that we need downstream fixes: * local token was added to MoeSortingProblemEx: https://github.com/ROCm/composable_kernel/blob/develop/include/ck_tile/ops/fused_moe/kernel/moe_sorting_problem.hpp#L48 * MeshType_ was added to MoeSortingProblemMp: https://github.com/ROCm/composable_kernel/blob/develop/include/ck_tile/ops/fused_moe/kernel/moe_sorting_problem.hpp#L56 * MOE_SORTING_FMOE_2D_BUF was added which I just turn off for now ``` In file included from buck-out/v2/gen/fbcode/de5ab6968d300cd2/deeplearning/fbgemm/fbgemm_gpu/experimental/gen_ai/src/quantize/ck_extensions/__ck_fused_moe_hipify_gen__/out/fused_moe/instances/fused_moesorting_api.hip:4: In file included from fbcode/deeplearning/fbgemm/fbgemm_gpu/experimental/gen_ai/src/quantize/ck_extensions/fused_moe/fused_moesorting.hpp:8: In file included from third-party/rocm_composable_kernel/include/ck_tile/ops/fused_moe.hpp:9: third-party/rocm_composable_kernel/include/ck_tile/ops/fused_moe/kernel/moe_sorting_kernel.hpp:2100:11: error: no member named 'moe_buf_elem_bytes' in 'ck_tile::MoeSortingMultiPhaseKernel_P2<ck_tile::MoeSortingProblemMp<int, float, int, 1, false, false>>::Kargs' 2100 | k.moe_buf_elem_bytes = h.moe_buf_elem_bytes; | ~ ^ ``` Reviewed By: zjing14 Differential Revision: D78679653
|
This pull request was exported from Phabricator. Differential Revision: D78679653 |
xw285cornell
force-pushed
the
export-D78679653
branch
from
c9affaa to
39868ba
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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:
A number of changes on CK header that we need downstream fixes:
Differential Revision: D78679653