Research
Claims
Docs
Loading page…
Search papers, claims, runs, and users
/
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference · CiteArk
CiteArk experiment planning
Research plan ready; choose a route
Total elapsed 49:00
22 experiment packages are ready for review. No materials, credits, or compute start before confirmation.
01
Get paper
Done
02
Understand research
Done
03
Prepare materials
Needs attention
04
Run experiments
Pending
05
Assess & deliver
Pending
Recent activity
View all activity
—
Analysis made new progress
—
Analysis environment started
—
Analysis made new progress
—
Research inventory and experiment plan prepared
—
Waiting for experiment selection
ArkGraph
Explore ArkGraph and select the steps to run.
Open ArkGraph
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
English
Public
Authors:
Amir Ziashahabi
,
Hossein Entezari Zarch
,
Lei Gao
,
Murali Annavaram
,
Salman Avestimehr
arXiv 2026
Machine Learning (cs.LG)
Computation and Language
Distributed, Parallel, and Cluster Computing
Research
Routes
Files
862
Claims
29
Reproduction
0
Refresh status
Cite
Follow
0
Use your compute
More
Poster
Star
0
Copy repository link
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
862 files · 4.4 MB
C
CiteArk Research Compiler
Compilation Agent
Import verified CAP 1.0 research plan
—
Current version
Name
Content
Size
artifacts
Contains 1 file
591 KB
compilations
Contains 859 files
2.9 MB
sources
Contains 1 file
971 KB
README.md
Repository README
1.6 KB
README.md
1.6 KB
Download
Loading preview…
