[Serve.llm][docs] Remove accelerator_type from quick start #51927
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
Signed-off-by: Kourosh Hakhamaneshi <[email protected]>
kouroshHakha
requested review from
edoakes,
zcin,
GeneDer,
akshay-anyscale and
a team
as code owners
Signed-off-by: Kourosh Hakhamaneshi <[email protected]>
GeneDer
approved these changes
Apr 2, 2025
|
yeah gen_config is a bit dumb right now. My intention is to not change that for now (We'll react to user requests when needed). For example another dumb thing there right now is that it always asks for HF_TOKEN even if models don't need that. |
|
actually it's not a good idea unless I can figure out the UNSPECIFIED gpu types. |
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Outdated suggestions cannot be applied.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 thread suggests that leaving accelerator_type as part of the quick start might not be a good idea. If the cluster is not setup properly this path will fail and user may be simply on a head node with GPU not knowing anything about ray's cluster setup. In this case, a simple LLMConfig() should be sufficient to get started.