APaperADay@alien.topB to Machine Learning@academy.gardenEnglish · 10 months ago

[R] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

1

1

[R] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

APaperADay@alien.topB to Machine Learning@academy.gardenEnglish · 10 months ago

1

Code: https://github.com/hao-ai-lab/LookaheadDecoding

Blog post: https://lmsys.org/blog/2023-11-21-lookahead-decoding/

Description:

We introduce lookahead decoding, a new, exact, and parallel decoding algorithm to accelerate LLM inference. Lookahead decoding breaks the sequential dependency in autoregressive decoding by concurrently extracting and verifying n-grams directly with the LLM, utilizing the Jacobi iteration method. Lookahead decoding functions without the need for a draft model or a data store. It linearly decreases the number of decoding steps directly correlating with the log(FLOPs) used per decoding step. Below is a demo of lookahead decoding accelerating LLaMa-2-Chat 7B generation:

https://i.redd.it/k61qtr4zz22c1.gif

You must log in or register to comment.

Chat

too_long_story@alien.topB
link
fedilink
English
arrow-up
1·
10 months ago
Well, but how to merry it with batching so that flash attention kernels can work with it?

Any complicated masks for attention imply hard times of making possible supporting batching.

Machine Learning@academy.garden

machinelearning@academy.garden

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !machinelearning@academy.garden

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
1 user / week
1 user / month
1 user / 6 months
1 local subscriber
1 subscriber
786 Posts
3.03K Comments
Modlog

mods:
communick@academy.garden