[Neuron] Add an option to build with neuron #2065
Merged
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
5 tasks
WoosukKwon
reviewed
Dec 21, 2023
There was a problem hiding this comment.
Hi @liangfu, apologies for the late review and thanks for the PR! I like this PR in that you didn't submit a big PR at once but instead split it into small parts. :)
Overall, I think moving the import statements is not a good idea. Considering the architecture you showed last time, I think we can just skip loading the modules that try to import custom ops. WDYT?
WoosukKwon
approved these changes
Jan 17, 2024
There was a problem hiding this comment.
@liangfu Apologies for the late review and thanks for addressing my comments! Left some very minor comments on styles. Looking forward to the next PRs!
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Jan 18, 2024
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Feb 13, 2024
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Outdated suggestions cannot be applied.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 PR adds an option that setup vLLM to build with Neuron toolchain (include neuronx-cc and transformers-neuronx).
This would help us build
, where the neuron version comes out of the compiler version (neuronx-cc 2.12).
This is part of the effort to add support to accelerate LLM inference with Trainium/Inferentia (see #1866) .