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Outdated suggestions cannot be applied.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.
Description
In #3230 vllm was added to requirements/common.txt.
Installation of vllm automatically installs an exact version of pytorch and overwrites our version.
We propose to add a parameter to install dependencies from a separate configuration for hpu.
Alternatively, moving vllm away from the common requirements file should also be considered.
Type of change
requirements/hpu.txt with gaudi dependencies was added,
--hpu
flag was added to ts_scripts/install_dependencies.py instead of--skip_torch_install
as torch was eventually installed by vllm anyway.Bug fix (non-breaking change which fixes an issue)
Checklist: