conftrace_

prefill

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

decoding (2) llm-optimized npu (1) nvidia gpus (1) colocation (1) multiplexing (1) slo (1) throughput (1) mixed precision (1) quantization (1)

Papers

Progressive Mixed-Precision Decoding for Efficient LLM Inference ICLR 2025 MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving ICML 2024