[Fix] Export TORCH_CUDA_ARCH_LIST in install.sh #133
Merged
Conversation
This file contains 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
We like to not use PTX compilation for now.
|
@LeiWang1999 Thanks! LGTM. I removed PTX flag since we don't want JIT of the cuda codes for now. We observed slightly faster code with PTX disabled. |
DeJoker
pushed a commit
to DeJoker/GPTQModel
that referenced
this pull request
Jul 19, 2024
* chore: update TORCH_CUDA_ARCH_LIST in install.sh * chore: remove importlib from requirements.txt * chore: Fix multi-gpu environment check in bitblas_target_detector.py * chore: Update logger.info message in qlinear_bitblas.py * Update install.sh We like to not use PTX compilation for now. --------- Co-authored-by: Qubitium-ModelCloud <qubitium@modelcloud.ai>
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Outdated suggestions cannot be applied.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.
This pull request includes a change to the
install.shscript to export theTORCH_CUDA_ARCH_LISTvariables in install.sh scripts. Otherwise, the build pipeline of cuda backend will crash.Also remove
importlibfrom requirements.txt ref to #132