Xinjie Guo | Searcharxiv

arXiv2026

VPP: Virtual Pipeline Parallelism for Efficient Chunked Prefill in Long-Context LLM Inference

Chunked prefill pipeline parallelism (CPP) is a key technique for LLM inference. However, equal-size chunks exhibit imbalanced latency, as later chunks attend longer prefix KV caches and incur higher attention costs, leading to pipeline bubbles. Existing approaches mitigate this imbalance through dynamic chunk resizing (Dynamic CPP, DCPP), but our measurements show that this trades scheduling overhead for load balancing, which becomes unfavorable on long sequences. In this study, we propose Virtual Pipeline Parallelism (VPP), which keeps chunk sizes fixed and optimizes the pipeline layout through virtual stages. A V-shaped virtual-stage traversal overlaps each chunk's expensive middle stages with the lighter head and tail stages of its neighbors, while asynchronous communication and pipelined packing further reduce communication stalls and cross-request drain bubbles. We implement VPP in vLLM-Ascend and evaluate it on three MoE-based LLMs with sequences up to 1M tokens on 16 Ascend 910C NPUs. VPP improves throughput by up to 13.1% over DCPP on long sequences and 6.7% on mixed workloads, while preserving performance on short sequences. On a 512K-token DeepSeek-V3.1 prefill workload, VPP reduces the pipeline bubble ratio from 6.4% to 0.1%, achieving a 98.0% reduction compared with DCPP.

cs.DC↗

arXiv2025

MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster

Reinforcement learning (RL) is a paradigm increasingly used to align large language models. Popular RL algorithms utilize multiple workers and can be modeled as a graph, where each node is the status of a worker and each edge represents dataflow between nodes. Owing to the heavy cross-node dependencies, the RL training system usually suffers from poor cluster scalability and low memory utilization. In this article, we introduce MindSpeed RL, an effective and efficient system for large-scale RL training. Unlike existing centralized methods, MindSpeed RL organizes the essential data dependencies in RL training, i.e., sample flow and resharding flow, from a distributed view. On the one hand, a distributed transfer dock strategy, which sets controllers and warehouses on the basis of the conventional replay buffer, is designed to release the dispatch overhead in the sample flow. A practical allgather--swap strategy is presented to eliminate redundant memory usage in resharding flow. In addition, MindSpeed RL further integrates numerous parallelization strategies and acceleration techniques for systematic optimization. Compared with existing state-of-the-art systems, comprehensive experiments on the RL training of popular Qwen2.5-Dense-7B/32B, Qwen3-MoE-30B, and DeepSeek-R1-MoE-671B show that MindSpeed RL increases the throughput by 1.42 ~ 3.97 times. Finally, we open--source MindSpeed RL and perform all the experiments on a super pod of Ascend with 384 neural processing units (NPUs) to demonstrate the powerful performance and reliability of Ascend.

cs.LG↗