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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 2years
2026 2roles
background 1polarities
background 1representative citing papers
TEERepair uses a DSL to define repair templates and LLMs to create context-specific patches for TEE partitioning issues, reporting 87.6% success on a new benchmark and merged fixes in real projects.
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.
-
Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching
TEERepair uses a DSL to define repair templates and LLMs to create context-specific patches for TEE partitioning issues, reporting 87.6% success on a new benchmark and merged fixes in real projects.