[Unity] Bump fpA_intB_gemm #16244
Merged
[Unity] Bump fpA_intB_gemm #16244
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
masahi
approved these changes
Dec 14, 2023
vinx13
force-pushed
the
unity-bump-mixgemm-dec13
branch
2 times, most recently
from
5911cc0 to
e545429
Compare
vinx13
force-pushed
the
unity-bump-mixgemm-dec13
branch
from
e545429 to
47c0f9c
Compare
junrushao
pushed a commit
that referenced
this pull request
Dec 18, 2023
Updated preprocessing and submodule the support 3D weight for MoE. * update * update * update
Lunderberg
added a commit
to Lunderberg/tvm
that referenced
this pull request
Dec 29, 2023
The updates to the cutlass kernels made in TVM PR apache#16244 require symbols provided in cuda 7.5+. While the cuda architecture is specified by setting `NVCC_FLAGS` in the `CMakeLists.txt` for each kernel, cmake 3.18+ also sets it based on the `CMAKE_CUDA_ARCHITECTURES` value. If not set, cmake will explicitly pass the compute capability as nvidia's default of 5.2, *EVEN IF* it has already been specified in `NVCC_FLAGS`. Because the kernels cannot compile with compute capability of 5.2, this causes compilation errors. By setting `CMAKE_CUDA_ARCHITECTURES` to `OFF`, cmake does not add 5.2 as a target architecture. See https://cmake.org/cmake/help/latest/policy/CMP0104.html for details on CMake's policy for CUDA architecture flags. See https://cmake.org/cmake/help/latest/policy/CMP0104.html for the default CUDA architecture for each version of CUDA.
Lunderberg
added a commit
that referenced
this pull request
Jan 2, 2024
The updates to the cutlass kernels made in TVM PR #16244 require symbols provided in cuda 7.5+. While the cuda architecture is specified by setting `NVCC_FLAGS` in the `CMakeLists.txt` for each kernel, cmake 3.18+ also sets it based on the `CMAKE_CUDA_ARCHITECTURES` value. If not set, cmake will explicitly pass the compute capability as nvidia's default of 5.2, *EVEN IF* it has already been specified in `NVCC_FLAGS`. Because the kernels cannot compile with compute capability of 5.2, this causes compilation errors. By setting `CMAKE_CUDA_ARCHITECTURES` to `OFF`, cmake does not add 5.2 as a target architecture. See https://cmake.org/cmake/help/latest/policy/CMP0104.html for details on CMake's policy for CUDA architecture flags. See https://cmake.org/cmake/help/latest/policy/CMP0104.html for the default CUDA architecture for each version of CUDA.
|
@vinx13 how can I build with fpA_intB_gemm in V100，is there a on-off build for fpA_intB_gemm， I come across build error when compile tvm in V100(SM 70) |
Member
Author
|
@JiaqingFu what error did you meet? sm70 should be supported. Build of fpA_intB_gemm is controlled by option |
|
@vinx13 3Q for reply, same config.cmake ,echo set(CMAKE_CUDA_ARCHITECTURES 86) >> config.cmake work for 3060; makefile: |
|
@vinx13 I solve it by update cutlass commit id and cutaass_fpA_intB_gemm commit id |
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.
Updated preprocessing and submodule the support 3D weight for MoE.
cc @masahi