13 citations · 13 across the 6 of their papers we have counts for
6 papers
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
Han Guo, Jack Zhang, Arjun Menon +4
Transformer training systems are built around dense linear algebra, yet a nontrivial fraction of end-to-end time is spent on surrounding memory-bound operators. Normalization, acti…
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…
AI+HW 2035: Shaping the Next Decade
Deming Chen, Jason Cong, Azalia Mirhoseini +27
Artificial intelligence (AI) and hardware (HW) are advancing at unprecedented rates, yet their trajectories have become inseparably intertwined. The global research community lacks…
Speculative Speculative Decoding
Tanishq Kumar, Tri Dao, Avner May
Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upco…
BitDelta: Your Fine-Tune May Only Be Worth One Bit
James Liu, Guangxuan Xiao, Kai Li +4
Large Language Models (LLMs) are typically trained in two phases: pre-training on large internet-scale datasets, and fine-tuning for downstream tasks. Given the higher computationa…
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Tianle Cai, Yuhong Li, Zhengyang Geng +4
Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as…