conftrace_

throughput optimization

46 papers

Explore in graph

Co-occurring keywords

latency optimization (119) inference optimization (219) large language model (13587) model compression (3302) latency reduction (77) tail latency (25) resource allocation (251) efficient inference (233) congestion control (43) datacenter networking (18)

Papers

Sparse Attention Across Multiple-Context KV Cache AAAI 2026
Accelerating LLM Inference Throughput via Asynchronous KV Cache Prefetching AAAI 2026
Efficient Multi-WAN Transport for 5G with OTTER NSDI 2025
Multi-Branch Self-Drafting for LLM Inference Acceleration AAAI 2025
TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding ACL 2025
Building Massive MIMO Baseband Processing on a Single-Node Supercomputer NSDI 2025
Enhancing Network Failure Mitigation with Performance-Aware Ranking NSDI 2025
Region-based Content Enhancement for Efficient Video Analytics at the Edge NSDI 2025
Efficient Inference for Large Language Models –Algorithm, Model, and System EMNLP 2025
Efficient LLM Scheduling by Learning to Rank NIPS 2024
Orthcatter: High-throughput In-band OFDM Backscatter with Over-the-Air Code Division NSDI 2024
Traffic Flow Optimisation for Lifelong Multi-Agent Path Finding AAAI 2024
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving OSDI 2024
dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving OSDI 2024
DRust: Language-Guided Distributed Shared Memory with Fine Granularity, Full Transparency, and Ultra Efficiency OSDI 2024
Toward Efficient Inference for Mixture of Experts NIPS 2024
Sifter: An Inversion-Free and Large-Capacity Programmable Packet Scheduler NSDI 2024
Pipeline Parallelism with Controllable Memory NIPS 2024
Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters NIPS 2024
MOSEL: Inference Serving Using Dynamic Modality Selection EMNLP 2024
eZNS: An Elastic Zoned Namespace for Commodity ZNS SSDs OSDI 2023
SelfTune: Tuning Cluster Managers NSDI 2023
MUX-PLMs: Pre-training Language Models with Data Multiplexing ACL 2023
Skyplane: Optimizing Transfer Cost and Throughput Using Cloud-Aware Overlays NSDI 2023
$S^3$: Increasing GPU Utilization during Generative Inference for Higher Throughput NIPS 2023