Search Graph CLI Topics Blogs Events Posts Papers Patents Feed Talks Photos Add your work My graph

Loading devreal.ai…

Community index online

Built for the people who make technology make sense.

© 2026 devreal.ai

New on DevRealMojo 1.0 and open source: our ModCon 2026 videosRead and watch ↗

New on FunctionalTVVideos from DataFusion meetup at LangChain are upWatch the videos ↗

Upcoming eventApache Spark NYC Meetup · Aug 26Read announcement ↗

The First Spark1st Spark meetup in the worldRelive the miracle of discovering Spark! ↗

New on FunctionalTVRust AI Begins recordings are liveWatch all 12 ↗

Recently verified

@jesusvilelaJesús Vilela JatoClaimed profile ↗@jameswardJames WardClaimed profile ↗@schwentkerRobert SchwentkerClaimed profile ↗@etorreborreEric TorreborreClaimed profile ↗@mileschintwTsungWei ChinClaimed profile ↗@newfrontScott HainesClaimed profile ↗@devtyTyler SingletaryClaimed profile ↗@nyghtowlMelanie WarrickClaimed profile ↗@alexyAlexy KhrabrovClaimed profile ↗

Break the Sequential Dependency of LLM Inference Using Lookahead Decoding — devreal.ai

← Back to papers

paper · community record

Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

A connected record in the developer community graph.

Read paper ↗Add or suggest a connection ↗

01

Connections

1 relationship

authored · incomingPeter Bailisperson ↗

02

Provenance

Type: paper
Status: Imported / unclaimed
doi: 10.48550/arxiv.2402.02057
year: 2024
venue: arXiv (Cornell University)
source: bythebay
pdf_url: https://arxiv.org/pdf/2402.02057
citation_count: 3