R.I.P.
๐ป
Ghosted
HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
April 20, 2026 ยท Grace Period ยท + Add venue
Authors
Mao Lin, Xi Wang, Guilherme Cox, Dong Li, Hyeran Jeon
arXiv ID
2604.18529
Category
cs.PF: Performance
Cross-listed
cs.DC
Citations
0
Abstract
As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware by relying solely on either GPU or CPU for attention computing, and considering yet limited CPU local memory for KV cache storage. We propose HybridGen, an efficient hybrid attention framework for long-context LLM inference. HybridGen enables CPU-GPU collaborative attention on systems with expanded tiered memory (e.g., CXL memory), addressing three key challenges: (1) multi-dimensional attention dependencies, (2) intensifying CPU-GPU load imbalance with longer sequences, and (3) NUMA penalty of tiered memories. HybridGen tackles these by introducing attention logit parallelism, a feedback-driven scheduler, and semantic-aware KV cache mapping. Experiments with three LLM models with eleven different sizes on three GPU platforms with a CXL-expanded memory show that HybridGen outperforms six state-of-the-art KV cache management methods by 1.41x--3.2x on average while maintaining superior accuracy.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Performance
R.I.P.
๐ป
Ghosted
A General Formula for the Stationary Distribution of the Age of Information and Its Application to Single-Server Queues
R.I.P.
๐ป
Ghosted
AI Benchmark: All About Deep Learning on Smartphones in 2019
R.I.P.
๐ป
Ghosted
BestConfig: Tapping the Performance Potential of Systems via Automatic Configuration Tuning
R.I.P.
๐ป
Ghosted
CLTune: A Generic Auto-Tuner for OpenCL Kernels
R.I.P.
๐ป
Ghosted