Under GPU-CC, LLM serving losses come from a serialized VM–GPU bridge, not compute; simple scheduling and loader changes recover most of the gap on Blackwell.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Security analysis reconstructing NVIDIA GPU-CC blueprint, bootstrap, and bridge protections with targeted experiments on data transfer security under the stated threat model.
citing papers explorer
-
The Serialized Bridge: Understanding and Recovering LLM Serving Performance under Blackwell GPU Confidential Computing
Under GPU-CC, LLM serving losses come from a serialized VM–GPU bridge, not compute; simple scheduling and loader changes recover most of the gap on Blackwell.
-
Blueprint, Bootstrap, and Bridge: A Security Look at NVIDIA GPU Confidential Computing
Security analysis reconstructing NVIDIA GPU-CC blueprint, bootstrap, and bridge protections with targeted experiments on data transfer security under the stated threat model.