# continuous-batching
2 articlestagged with “continuous-batching”
Inference Optimization Attacks
Speculative decoding attacks, batching vulnerabilities, continuous batching exploitation, and how optimization for speed creates security gaps in LLM inference.
inferencespeculative-decodingbatchingcontinuous-batchingoptimizationside-channel
推論最佳化攻擊
推測解碼攻擊、批次處理漏洞、持續批次利用，以及速度最佳化如何於 LLM 推論中造就安全缺口。
inferencespeculative-decodingbatchingcontinuous-batchingoptimizationside-channel