11 citations · 11 across the 4 of their papers we have counts for
4 papers
FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
Ted Zadouri, Markus Hoehnerbach, Jay Shah +3
Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. While FlashAttention-3 optimized a…
Hardware-Efficient Attention for Fast Decoding
Ted Zadouri, Hubert Strauss, Tri Dao
LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequent…
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
Ted Zadouri, Ahmet Üstün, Arash Ahmadian +3
The Mixture of Experts (MoE) is a widely known neural architecture where an ensemble of specialized sub-models optimizes overall performance with a constant computational cost. How…
High Probability Bounds for Stochastic Continuous Submodular Maximization
Evan Becker, Jingdong Gao, Ted Zadouri +1
We consider maximization of stochastic monotone continuous submodular functions (CSF) with a diminishing return property. Existing algorithms only guarantee the performance \textit…