SiPipe claims 1.6x to 2.1x throughput gains over vLLM for pipeline-parallel LLM inference by using idle CPUs for sampling, double-buffered CUDA graphs, and structure-aware transmission.
OpenAI API Documentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference
SiPipe claims 1.6x to 2.1x throughput gains over vLLM for pipeline-parallel LLM inference by using idle CPUs for sampling, double-buffered CUDA graphs, and structure-aware transmission.