SplitReason: Learning To Offload Reasoning
Paper
•
2504.16379
•
Published
AI & ML interests
None defined yet.
akhauriyash
authored
8
papers
5 months ago
xKV: Cross-Layer SVD for KV-Cache Compression
Paper
•
2503.18893
•
Published
•
5
Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion
Paper
•
2505.21467
•
Published
•
1
Esoteric Language Models
Paper
•
2506.01928
•
Published
•
9
Performance Prediction for Large Systems via Text-to-Text Regression
Paper
•
2506.21718
•
Published
•
6
SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs
Paper
•
2502.12444
•
Published
Encodings for Prediction-based Neural Architecture Search
Paper
•
2403.02484
•
Published
Regression Language Models for Code
Paper
•
2509.26476
•
Published
•
17