1 citations · 2 across the 8 of their papers we have counts for
9 papers
Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
Mingyu Lee, Akshat Ramachandran, Souvik Kundu +1
The inference efficiency of diffusion large language models (dLLMs) is constrained by two challenges: bidirectional attention precludes efficient KV-cache reuse, while increasing d…
ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models
Akshat Ramachandran, Marina Neseem, Charbel Sakr +3
The long-output context generation of large reasoning models enables extended chain of thought (CoT) but also drives rapid growth of the key-value (KV) cache, quickly overwhelming…
OneDSE: Metric-Conditioned Inverse Modeling and Active Search for Sample-Efficient DSE
Ritik Raj, Akshat Ramachandran, Danny Samuel +3
We identify two key challenges in prior CPU design space exploration (DSE) approaches: (a) short-horizon prediction is forward-only: modeling PPA metrics from design parameters whi…
Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator
Akshat Ramachandran, Souvik Kundu, Arnab Raha +3
Large language model (LLM) pruning with fixed N:M structured sparsity significantly limits the expressivity of the sparse model, yielding sub-optimal performance. In contrast, supp…
OuroMamba: A Data-Free Quantization Framework for Vision Mamba
Akshat Ramachandran, Mingyu Lee, Huan Xu +2
We present OuroMamba, the first data-free post-training quantization (DFQ) method for vision Mamba-based models (VMMs). We identify two key challenges in enabling DFQ for VMMs, (1)…
AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified Representations
Jamin Seo, Akshat Ramachandran, Yu-Chuan Chuang +2
Design space exploration (DSE) plays a crucial role in enabling custom hardware architectures, particularly for emerging applications like AI, where optimized and specialized desig…
MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization
Akshat Ramachandran, Souvik Kundu, Tushar Krishna
Quantization of foundational models (FMs) is significantly more challenging than traditional DNNs due to the emergence of large magnitude values called outliers. Existing outlier-a…
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
Akshat Ramachandran, Souvik Kundu, Tushar Krishna
We present CLAMP-ViT, a data-free post-training quantization method for vision transformers (ViTs). We identify the limitations of recent techniques, notably their inability to lev…
Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference
Akshat Ramachandran, Zishen Wan, Geonhwa Jeong +2
Traditional Deep Neural Network (DNN) quantization methods using integer, fixed-point, or floating-point data types struggle to capture diverse DNN parameter distributions at low p…