Suvinay Subramanian
Home ·
Work ·
Publications ·
Interests ·
Podcast
Planned Diffusion ICLR 2026 Web site
| X (Twitter) Thread
Characterizing VLA Models: Identifying the Action
Generation Bottleneck for Edge AI Architectures
Spark Transformer: Reactivating Sparsity in FFN and Attention NeurIPS 2025
FG-Attn: Leveraging Fine-Grained Sparsity In Diffusion Transformers arXiv , September 2025
Learning to Keep a Promise: Scaling Language Model
Decoding Parallelism with Learned Asynchronous Decoding ICML 2025
[X (Twitter) Thread ]
RAGO: Systematic Performance Optimization
for Retrieval-Augmented Generation Serving ISCA 2025
Leveraging LLMs to Improve Hardware-Software
Co-Design Workflow Productivity and Accessibility
MIST: A Co-Design Framework for Heterogeneous,
Multi-Stage LLM Inference arXiv
Effective Interplay
between Sparsity and Quantization: From Theory to Practice ICLR 2025 (Spotlight)
The Journey Matters:
Average Parameter Count over Pre-training Unifies Sparse and
Dense Scaling Laws ICLR 2025
Progressive Gradient
Flow for Robust N:M Sparsity Training in Transformers CPAL 2025
Demystifying AI Platform Design for Distributed Inference of
Next-Generation LLM Models arXiv , June 2024
TPU v4: An Optically Reconfigurable Supercomputer for Machine
Learning with Hardware Support for Embeddings ISCA 2023 (Industry Track)
FLAT: An Optimized Dataflow for Mitigating
Attention Bottlenecks ASPLOS 2023
STEP: Learning N:M Structured Sparsity Masks from
Scratch with Precondition ICML 2023
Training Recipe for
N:M Structured Sparsity with Decaying Pruning Mask SNN 2022
Harmonizing Speculative
and Non-Speculative Execution in Architectures for Ordered Parallelism MICRO 2018
SAM: Optimizing Multithreaded Cores for Speculative Parallelism PACT 2017
Fractal: An Execution Model
for Fine-Grain Nested Speculative Parallelism ISCA 2017
[Slides ]MIT News Article ,
Hacker News Discussion
Data-Centric Execution of Speculative Parallel Programs MICRO 2016
Programmable Packet Scheduling at Line Rate SIGCOMM 2016 Web site
Unlocking Ordered Parallelism with the Swarm Architecture IEEE Micro 2016 Top Picks from the Computer Architecture Conferences MIT News Article ,
EE Journal Article
A Scalable Architecture for Ordered Parallelism MICRO 2015 Selected for IEEE Micro's Top Picks special issue of "most significant papers in computer architecture
based on novelty and long-term impact" from 2015
Towards Programmable Packet Scheduling HotNets 2015
SCORPIO: A 36-core Research Chip Demonstrating Snoopy Coherence on a Scalable Mesh NoC with In-Network Ordering HotChips 2014
SCORPIO: A 36-core Research Chip Demonstrating Snoopy Coherence on a Scalable Mesh NoC with In-Network Ordering ISCA 2014 MIT News Article
No Silver Bullet: Extending SDN to the Data Plane HotNets 2013
[Slides ]Selected for the final round of the Qualcomm Innovation Fellowship Web site
Single-Cycle Multihop Asynchronous Repeated Traversal: A SMART Future for Reconfigurable On-Chip Networks IEEE Computer, October 2013
SMART: A Single-Cycle Reconfigurable NoC for SoC Applications DATE 2013
Theses