Skip to content
conftrace_

llm serving

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) kv cache (2) model compression (2) generative inference (1) end-to-end latency (1) prefetching hint (1) agentic program (1) 1-bit quantization (1) johnson-lindenstrauss transform (1) batch scheduling (1)

Papers

Agentix: An Efficient Serving Engine for LLM Agents as General Programs NSDI 2026 SYMPHONY: Enabling Compute-Memory Disaggregation in LLM Serving Systems NSDI 2026 QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead AAAI 2025 StitchLLM: Serving LLMs, One Block at a Time ACL 2025 S^3: Increasing GPU Utilization during Generative Inference for Higher Throughput NeurIPS 2023