Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference
Paper
•
2405.18628
•
Published
•
1
Hao Mark Chen
hmarkc
AI & ML interests
None yet
Recent Activity
published
a model
17 days ago
hmarkc/test
authored
a paper
7 months ago
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient
Acceleration of LLM Inference
upvoted
a
paper
7 months ago
Rethinking Optimal Verification Granularity for Compute-Efficient
Test-Time Scaling
Organizations
authored
2
papers
7 months ago