PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters
Paper
•
2504.08791
•
Published
•
134
•
7
Nitish Pandey
nitishpandey04
AI & ML interests
LLMs, Translation
Recent Activity
updated
a collection
13 days ago
Reading List
upvoted
a
paper
about 1 month ago
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
upvoted
a
paper
about 1 month ago
AutoTriton: Automatic Triton Programming with Reinforcement Learning in
LLMs
Organizations
commented
2
papers
4 months ago