A token-wise pruner with a learned router and a genetic-algorithm sparsity scheduler claims near-lossless LLM inference at 22-40% token sparsity.
Depth-adaptive transformer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing
A token-wise pruner with a learned router and a genetic-algorithm sparsity scheduler claims near-lossless LLM inference at 22-40% token sparsity.