Alibaba International Intelligent Technology
Mar 5, 2026 · Artificial Intelligence
Engineering Exploration of Generative Recall: Leveraging Large Models for Next‑Gen Recommendation Retrieval
The article analyzes the limitations of traditional ID‑based and vector recall, proposes a generative Semantic‑ID‑based recall framework (ASGR), details a series of inference‑time optimizations—including a custom SDPA‑enabled optimizer, novel beam search, static‑cache compilation, tree‑aware attention, sliding‑window attention, quantization, ONNX/Optimum conversion, and TensorRT‑LLM integration—and reports concrete latency and throughput gains that enable large‑scale, low‑latency recommendation serving.
Large Language Modelbeam searchgenerative recall
0 likes · 25 min read
