Krishna Teja Chitty-Venkata

28 papers A 1B 1C 1Journal 16Unranked 9
YearRankTypeTitle / Venue / Authors
2026 — conf
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference.
EACL (Findings)
Krishna Teja Chitty-Venkata, Jie Ye, Siddhisanket Raskar, Anthony Kougkas, Xian-He Sun, Murali Emani, Venkatram Vishwanath, Bogdan Nicolae
2026 J jnl
Swimba: Switch Mamba Model Scales State Space Models.
CoRR
Zhixu Du, Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Hai Helen Li, Yiran Chen
2025 J jnl
BaKlaVa - Budgeted Allocation of KV cache for Long-context Inference.
CoRR
Ahmed Burak Gulhan, Krishna Teja Chitty-Venkata, Murali Emani, Mahmut T. Kandemir, Venkatram Vishwanath
2025 J jnl
ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language Models.
CoRR
Krishna Teja Chitty-Venkata, Murali Emani
2025 J jnl
LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference.
CoRR
Krishna Teja Chitty-Venkata, Sandeep Madireddy, Murali Emani, Venkatram Vishwanath
2025 J jnl
LangVision-LoRA-NAS: Neural Architecture Search for Variable LoRA Rank in Vision Language Models.
CoRR
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath
2025 — conf
MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models.
SC Workshops
Krishna Teja Chitty-Venkata, Sylvia Howland, Golara Azar, Daria Soboleva, Natalia Vassilieva, Siddhisanket Raskar, Murali Emani, Venkatram Vishwanath
2025 J jnl
MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models.
CoRR
Krishna Teja Chitty-Venkata, Sylvia Howland, Golara Azar, Daria Soboleva, Natalia Vassilieva, Siddhisanket Raskar, Murali Emani, Venkatram Vishwanath
2025 — conf
MoPEQ: Mixture of Mixed Precision Quantized Experts.
ICCVW
Krishna Teja Chitty-Venkata, Jie Ye, Murali Emani
2025 J jnl
MoPEQ: Mixture of Mixed Precision Quantized Experts.
CoRR
Krishna Teja Chitty-Venkata, Jie Ye, Murali Emani
2025 J jnl
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference.
CoRR
Krishna Teja Chitty-Venkata, Jie Ye, Xian-He Sun, Anthony Kougkas, Murali Emani, Venkatram Vishwanath, Bogdan Nicolae
2025 J jnl
PreLoRA: Hybrid Pre-training of Vision Transformers with Full Training and Low-Rank Adapters.
CoRR
Krishu K. Thapa, Reet Barik, Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath
2024 — conf
LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators.
SC Workshops
Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Bharat Kale, Farah Ferdaus, Aditya Tanikanti, Ken Raffenetti, Valerie Taylor, Murali Emani, Venkatram Vishwanath
2024 J jnl
LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators.
CoRR
Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Bharat Kale, Farah Ferdaus, Aditya Tanikanti, Ken Raffenetti, Valerie Taylor, Murali Emani, Venkatram Vishwanath
2024 — conf
WActiGrad: Structured Pruning for Efficient Finetuning and Inference of Large Language Models on AI Accelerators.
Euro-Par (2)
Krishna Teja Chitty-Venkata, Varuni Katti Sastry, Murali Emani, Venkatram Vishwanath, Sanjif Shanmugavelu, Sylvia Howland
2023 J jnl
A Survey of Techniques for Optimizing Transformer Inference.
CoRR
Krishna Teja Chitty-Venkata, Sparsh Mittal, Murali Emani, Venkatram Vishwanath, Arun K. Somani
2023 J jnl
A survey of techniques for optimizing transformer inference.
J. Syst. Archit.
Krishna Teja Chitty-Venkata, Sparsh Mittal, Murali Emani, Venkatram Vishwanath, Arun K. Somani
2023 J jnl
Differentiable Neural Architecture, Mixed Precision and Accelerator Co-Search.
IEEE Access
Krishna Teja Chitty-Venkata, Yiming Bian, Murali Emani, Venkatram Vishwanath, Arun K. Somani
2023 J jnl
Neural Architecture Search Benchmarks: Insights and Survey.
IEEE Access
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Arun K. Somani
2023 J jnl
Neural Architecture Search Survey: A Hardware Perspective.
ACM Comput. Surv.
Krishna Teja Chitty-Venkata, Arun K. Somani
2022 A conf
Efficient Design Space Exploration for Sparse Mixed Precision Neural Architectures.
HPDC
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Arun K. Somani
2022 J jnl
Neural Architecture Search for Transformers: A Survey.
IEEE Access
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Arun K. Somani
2021 — conf
Array-Aware Neural Architecture Search.
ASAP
Krishna Teja Chitty-Venkata, Arun K. Somani
2021 B conf
Searching Architecture and Precision for U-net based Image Restoration Tasks.
ICIP
Krishna Teja Chitty-Venkata, Arun K. Somani, Sreenivas Kothandaraman
2020 — conf
Array Aware Training/Pruning: Methods for Efficient Forward Propagation on Array-based Neural Network Accelerators.
ASAP
Krishna Teja Chitty-Venkata, Arun K. Somani
2020 — conf
Calibration Data-based CNN Filter Pruning for Efficient Layer Fusion.
HPCC/DSS/SmartCity
Krishna Teja Chitty-Venkata, Arun K. Somani
2020 C conf
Model Compression on Faulty Array-based Neural Network Accelerator.
PRDC
Krishna Teja Chitty-Venkata, Arun K. Somani
2019 — conf
Impact of Structural Faults on Neural Network Performance.
ASAP
Krishna Teja Chitty-Venkata, Arun K. Somani