Bifrost achieves significant latency reductions in privacy-preserving transformer inference through a hybrid CPU TEE and accelerator FHE design, with Bifrost+ further optimizing via prefill/decode split.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
WHET applies fine-grained coefficient-to-slot transforms, plaintext compression, and modulus raising plus lightweight hardware tweaks to FHE accelerators, delivering 1.38-8.74x per-area gains and sub-millisecond CKKS bootstrapping.
SpenseGPT introduces a hybrid sparse-dense weight format and one-shot pruning that delivers 1.2x end-to-end LLM decoding speedup on B200 GPUs with FP8 while preserving accuracy on Qwen3-32B and Seed-OSS-36B.
citing papers explorer
-
Bifrost: Hybrid TEE-FHE Inference for Privacy-Preserving Transformer and LLM Serving
Bifrost achieves significant latency reductions in privacy-preserving transformer inference through a hybrid CPU TEE and accelerator FHE design, with Bifrost+ further optimizing via prefill/decode split.
-
WHET: Welding Homomorphic Encryption to Accelerator Architectures
WHET applies fine-grained coefficient-to-slot transforms, plaintext compression, and modulus raising plus lightweight hardware tweaks to FHE accelerators, delivering 1.38-8.74x per-area gains and sub-millisecond CKKS bootstrapping.