This work delivers the first measurements of performance-energy trade-offs across four multi-request LLM workflow patterns on A100 GPUs using vLLM and Parrot.
Flashattention: Fast and memory-efficient exact attention with io-awareness
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
HexiSeq optimizes sequence and head partitioning across mixed GPUs to improve long-context LLM training throughput by up to 1.72x in simulations.
Large-chunk online updates during inference let test-time training scale state capacity to 40% of model size and handle contexts up to 1M tokens without custom kernels.
citing papers explorer
-
Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows
This work delivers the first measurements of performance-energy trade-offs across four multi-request LLM workflow patterns on A100 GPUs using vLLM and Parrot.
-
HexiSeq: Accommodating Long Context Training of LLMs over Heterogeneous Hardware
HexiSeq optimizes sequence and head partitioning across mixed GPUs to improve long-context LLM training throughput by up to 1.72x in simulations.
-
Test-Time Training Done Right
Large-chunk online updates during inference let test-time training scale state capacity to 40% of model size and handle contexts up to 1M tokens without custom kernels.