SiDP distributes model weights across a DP group with WaS and CaS modes to increase KV cache capacity by up to 1.8x and end-to-end throughput by up to 1.5x over vLLM on H20/H200/B200 GPUs for offline LLM inference.
Improving the end-to-end efficiency of offline inference for multi-llm applications based on sampling and simu- lation.arXiv preprint arXiv:2503.16893, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SiDP: Memory-Efficient Data Parallelism for Offline LLM Inference
SiDP distributes model weights across a DP group with WaS and CaS modes to increase KV cache capacity by up to 1.8x and end-to-end throughput by up to 1.5x over vLLM on H20/H200/B200 GPUs for offline LLM inference.