Ditto quantizes Code LLMs with K-Means codebooks and compiles inference via LLVM-BLAS replacement to deliver up to 10.5x faster, 6.4x smaller, and 10.5x lower-energy execution on commodity hardware while losing only 0.27% pass@1 accuracy.
arXiv preprint arXiv:2309.14021 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
TIDE augments standard transformers with per-layer token embedding injection via an ensemble of memory blocks and a depth-conditioned router to mitigate rare-token undertraining and contextual collapse.
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
citing papers explorer
-
Compiling Code LLMs into Lightweight Executables
Ditto quantizes Code LLMs with K-Means codebooks and compiles inference via LLVM-BLAS replacement to deliver up to 10.5x faster, 6.4x smaller, and 10.5x lower-energy execution on commodity hardware while losing only 0.27% pass@1 accuracy.
-
TIDE: Every Layer Knows the Token Beneath the Context
TIDE augments standard transformers with per-layer token embedding injection via an ensemble of memory blocks and a depth-conditioned router to mitigate rare-token undertraining and contextual collapse.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.