Add moe router module with hierarchical gating support for DeepSeek Models #191
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
to be consistent with Shift Parallelism paper.
sfc-gh-reyazda
requested review from
sfc-gh-aqiao,
sfc-gh-goliaro,
sfc-gh-jrasley,
sfc-gh-mhidayetoglu and
sfc-gh-yewang
as code owners
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Outdated suggestions cannot be applied.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.
cc: @sfc-gh-jrasley @sfc-gh-aqiao
I have bypassed some functions in the arctic-inference to make this branch runnable with the newest version of Vllm.
In order to run the serving system, we need to set
ARCTIC_INFERENCE_SKIP_VERSION_CHECKenvironment variable.@sfc-gh-mhidayetoglu, this branch is now ready to be tested on your benchmarks.