When KV Meets Embeddings: Dynamic GPU Memory Allocation for Accelerating Generative Recommender Serving
Generative Recommender (GR) inference places embedding hot caches (EMB) and KV caches in direct competition for limited GPU HBM: allocating more memory to one improves its efficiency but degrades the other. Existing systems optimize them in isolation, overlooking that the optimal EMB-KV allocation ratio can shift by up to 0.35 across workload regimes, leaving 20-30\% latency improvement unrealized. While online reallocation is required to close this gap, naive approaches introduce H2D refill traffic on the critical path, causing P99 SLO violations. To address this, we present RACER, which jointly manages HBM allocation and request routing at runtime through two key components: (1) Adaptiv...
| Authors | Wenjun Yu, Shuguang Han, Amelie Chi Zhou |
|---|---|
| Primary category | cs.DC |
| Published | 6 May 2026 |
| Last updated at source | 24 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.