Sign InOpen Brain
arXivPaperNeeds Review

Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training

Rollplex overlaps VLM prefix work with rollout decoding and shares weights across training phases. On 32 H800 GPUs, it reports higher throughput without changing synchronous on-policy updates.

arXiv
Open Source Open MarkdownOpen JSON
Source Summary

Rollplex moves response-independent prefix computation into the rollout decode window. Phase-aware HBM management and parallelism-aware weight sharing address a naive Qwen2.5-VL-32B footprint of roughly **165 GiB per GPU**.

Practical Implication

Teams post-training vision-language agents can inspect phase boundaries for independent prefix work and share compatible tensor storage across differing parallel layouts. The reported schedule preserves synchronous on-policy updates under the same GPU budget.

Agent-Ready Context
Rollplex moves response-independent prefix computation into the rollout decode window. Phase-aware HBM management and parallelism-aware weight sharing address a naive Qwen2.5-VL-32B footprint of roughly **165 GiB per GPU**.

Teams post-training vision-language agents can inspect phase boundaries for independent prefix work and share compatible tensor storage across differing parallel layouts. The reported schedule preserves synchronous on-policy updates under the same GPU budget.

On **32 H800 GPUs**, Rollplex reports **1.23×–1.30×** speedup over serial colocation and **1.57×–2.24×** over disaggregation. The material provides results for this hardware and workload setup, not broader cost or scaling evidence.
Context Map
infraimagevideo
Uncertainty
On **32 H800 GPUs**, Rollplex reports **1.23×–1.30×** speedup over serial colocation and **1.57×–2.24×** over disaggregation. The material provides results for this hardware and workload setup, not broader cost or scaling evidence.