XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
Paper
•
2508.10395
•
Published
•
40
Minjae Lee
FuriosaMJLEE
AI & ML interests
None yet
Recent Activity
authored
a paper
11 days ago
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for
State Space Models
authored
a paper
11 days ago
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
authored
a paper
11 days ago
Draft-based Approximate Inference for LLMs
Organizations
upvoted
a
paper
19 days ago