conftrace_

hybrid inference

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) test-time compute (1) hard blocking (1) soft blocking (1) cache policy (1) hybrid probabilistic inference (1) algebraic constraint (1) neuron balancing (1) neuron prefetching (1) logical constraint (1)

Papers

Kairox: Adaptive GPU-CPU Hybrid LLM Inference via Online Neuron Balancing OSDI 2026 Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute EACL 2026 Firewall Routing: Blocking Leads to Better Hybrid Inference for LLMs EMNLP 2025 Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference ACL 2024 Hybrid Probabilistic Inference with Logical and Algebraic Constraints: a Survey IJCAI 2021