Initial MLP Speculative Decoding implementation#160
Open
christinaexyou wants to merge 2 commits intovllm-project:mainfrom
Open
Initial MLP Speculative Decoding implementation#160christinaexyou wants to merge 2 commits intovllm-project:mainfrom
christinaexyou wants to merge 2 commits intovllm-project:mainfrom
Conversation
Signed-off-by: Christina Xu <chrxu@redhat.com>
christinaexyou
force-pushed
the
add-mlp-speculator
branch
from
4050ae5 to
34558d4
Compare
Collaborator
|
Has this been tested? Are you still interested in getting this landed? We will be looking into MTP fine tuning if you’d like to help with that instead? |
Collaborator
|
@Mergifyio refresh |
✅ Pull request refreshed |
Author
|
Hi @dsikka ! No, I haven't tested it extensively i.e there are benchmark performance tests that I would like to contribute. I'll continue on working on this but I totally understand if this is de-prioritized. Would love to help out with MTP fine tuning in the meantime ! |
Collaborator
|
FYi: #267 |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
NOTE: This is currently a draft since I have a question
This PR addresses #41 by adding:
MLPSpeculatorConfigMLPSpeculatorQuestions
forwardmethod generates logits for all possible candidate sequences, should I be choosing the top candidates here through Tree Attention ?