activity
20242026
collaborators

6 papers

cs.AR2026

Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models

Jungwoo Kim, Rubens Lacouture, Genghan Zhang +5

Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models (LLMs). However, the execution characteristics of MoE inference are changing rapidly a…

cs.DC2026

Regulating Branch Parallelism in LLM Serving

Swapnil Gandhi, Siva Hari, William J. Dally +1

Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute these branches eagerly or und…

cs.DC2026

Sparse Checkpointing for Fast and Reliable MoE Training

Swapnil Gandhi, Christos Kozyrakis

As large language models scale, training them requires thousands of GPUs over extended durations--making frequent failures an inevitable reality. While checkpointing remains the pr…

cs.DC2025

FailSafe: High-performance Resilient Serving

Ziyi Xu, Zhiqiang Xie, Swapnil Gandhi +1

Tensor parallelism (TP) enables large language models (LLMs) to scale inference efficiently across multiple GPUs, but its tight coupling makes systems fragile: a single GPU failure…

cs.DC2025

SYMI: Efficient Mixture-of-Experts Training via Model and Optimizer State Decoupling

Athinagoras Skiadopoulos, Mark Zhao, Swapnil Gandhi +3

Mixture-of-Experts (MoE) models have become a widely-adopted solution to continue scaling model sizes without a corresponding linear increase in compute. During MoE model training,…

cs.DC2024

ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation

Swapnil Gandhi, Mark Zhao, Athinagoras Skiadopoulos +1

Training large Deep Neural Network (DNN) models requires thousands of GPUs over the course of several days or weeks. At this scale, failures are frequent and can have a big impact…