William Brandon

14 papers A* 2Journal 8Unranked 4
YearRankTypeTitle / Venue / Authors
2025 J jnl
FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference.
CoRR
Aniruddha Nrusimha, William Brandon, Mayank Mishra, Yikang Shen, Rameswar Panda, Jonathan Ragan-Kelley, Yoon Kim
2025 A* conf
Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping.
ICML
Muru Zhang, Mayank Mishra, Zhongzhu Zhou, William Brandon, Jue Wang, Yoon Kim, Jonathan Ragan-Kelley, Shuaiwen Leon Song, Ben Athiwaratkun, Tri Dao
2025 J jnl
Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping.
CoRR
Muru Zhang, Mayank Mishra, Zhongzhu Zhou, William Brandon, Jue Wang, Yoon Kim, Jonathan Ragan-Kelley, Shuaiwen Leon Song, Ben Athiwaratkun, Tri Dao
2024 — conf
Fast Matrix Multiplications for Lookup Table-Quantized LLMs.
EMNLP (Findings)
Han Guo, William Brandon, Radostin Cholakov, Jonathan Ragan-Kelley, Eric P. Xing, Yoon Kim
2024 J jnl
Fast Matrix Multiplications for Lookup Table-Quantized LLMs.
CoRR
Han Guo, William Brandon, Radostin Cholakov, Jonathan Ragan-Kelley, Eric P. Xing, Yoon Kim
2024 J jnl
Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding.
CoRR
Zachary Ankner, Rishab Parthasarathy, Aniruddha Nrusimha, Christopher Rinard, Jonathan Ragan-Kelley, William Brandon
2024 A* conf
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention.
NeurIPS
William Brandon, Mayank Mishra, Aniruddha Nrusimha, Rameswar Panda, Jonathan Ragan-Kelley
2024 J jnl
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention.
CoRR
William Brandon, Mayank Mishra, Aniruddha Nrusimha, Rameswar Panda, Jonathan Ragan-Kelley
2023 J jnl
Better Defunctionalization through Lambda Set Specialization.
Proc. ACM Program. Lang.
William Brandon, Benjamin Driscoll, Frank Dai, Wilson Berkow, Mae Milano
2023 J jnl
Striped Attention: Faster Ring Attention for Causal Transformers.
CoRR
William Brandon, Aniruddha Nrusimha, Kevin Qian, Zachary Ankner, Tian Jin, Zhiye Song, Jonathan Ragan-Kelley
2022 J jnl
Codes of conduct in Open Source Software - for warm and fuzzy feelings or equality in community?
Softw. Qual. J.
Vandana Singh, Brice Bongiovanni, William Brandon
2022 — conf
Discrimination, Misogyny and Harassment: Examples from OSS : Content Analysis of Women-focused Online Discussion Forums.
GE@ICSE
Vandana Singh, William Brandon
2020 — conf
How do the women of Open Source support each other?
HICSS
Vandana Singh, William Brandon
2019 — conf
Open Source Software Community Inclusion Initiatives to Support Women Participation.
OSS
Vandana Singh, William Brandon