feat: add multi-GPU–friendly default for vLLM/Unsloth engine setup #483
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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
Default vLLM/Unsloth tensor_parallel_size to the number of visible GPUs (respects CUDA_VISIBLE_DEVICES) so multi-GPU setups don’t start with an unset/invalid TP world size.
Still allows explicit overrides via _internal_config["engine_args"].
Motivation
On multi-GPU H100 machines, vLLM was crashing during init when TP wasn’t configured; setting a sensible default prevents a TP=0/None startup.
Details
In get_model_config, set engine_args["tensor_parallel_size"] = torch.cuda.device_count() (or 1 if CUDA unavailable) before merging user overrides.