Add Doubleword blog post on speculative decoding trade-offs to QuickStart#3
Open
jaedmunt wants to merge 1 commit into
Open
Add Doubleword blog post on speculative decoding trade-offs to QuickStart#3jaedmunt wants to merge 1 commit into
jaedmunt wants to merge 1 commit into
Conversation
…tart Signed-off-by: Jaedon Munton <jaedon.munton@doubleword.ai>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a technical blog post from Doubleword to the QuickStart resources section.
Width vs. depth: speculating on the margin
The post explores speculative-decoding trade-offs — why speculating multiple tokens deeper on a single sequence can yield more output tokens/sec than batching additional independent sequences, including the interaction with MoE expert routing. It fits alongside the existing decoding-strategy blog posts in QuickStart.