Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/William Won

William Won

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Distributed×3ML×3AI×2Networking×1

Frequent co-authors

Hanjiang Wu3×
Tushar Krishna3×
Abhimanyu Rajeshkumar Bambhaniya2×
Sarbartha Banerjee2×
Tuhin Khare2×
Sudarshan Srinivasan2×

Research Timeline

2026
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughput under strict latency constraints.

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughput under strict latency constraints.

ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling

This paper updates the ASTRA-sim simulator for distributed machine learning with new features and a standardized infrastructure representation.

Highlighted terms show continued research focus across papers

Papers

cs.DCcs.LGcs.NIEmpiricalRecentJun 9, 2026

ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling

William Won, Jinsun Yoo, Tuan Ta, Moumita Dey +15 more

This paper updates the ASTRA-sim simulator for distributed machine learning with new features and a standardized infrastructure representation.

View →
cs.LGcs.AIcs.DCRecent
May 27, 2026

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee, Tuhin Khare +8 more

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughpu…

View →
cs.LGcs.AIcs.DCRecentMay 27, 2026

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee, Tuhin Khare +8 more

The paper systematically analyzes the benefits and limits of Attention-FFN Disaggregation (AFD) for Mixture-of-Experts (MoE) LLM serving, demonstrating that AFD is crucial for achieving high throughpu…

View →