conftrace_

prefill-decode disaggregation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

cpu gpu hybrid (1) inference instance (1) large language model serving (1) large language model (1) expert parallelism (1) gpu cluster (1) request scheduling (1) inference acceleration (1) inference optimization (1) mixture of expert (1)

Papers

Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU–GPU Hybrid Design OSDI 2026 Efficient LLM Serving on Commodity GPU Clusters with Data-Reduced Cross-Instance Orchestration OSDI 2026 PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference ACL 2026