Vipin Chaudhary
- Papers
- 7
Cite
Notes
Only stored in your browser.
7papers
Authored papers
770% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float
arXiv 2025
More for Keys, Less for Values: Adaptive KV Cache Quantization
arXiv 2025
Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
arXiv 2025
Thinking Preference Optimization
arXiv 2025
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
arXiv 2024
Forte : Finding Outliers with Representation Typicality Estimation
arXiv 2024
Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
winner-take-all-column-row-sampling-for
Affiliations
No known affiliations.
Frequent co-authors
10from 7 papers