conftrace_

latency optimization

119 papers

Explore in graph

Co-occurring keywords

model compression (3302) neural architecture search (666) simultaneous translation (136) large language model (13587) throughput optimization (46) tail latency (25) congestion control (43) simultaneous machine translation (48) translation quality (224) convolutional neural network (4226)

Papers

POSEIDON: A Consolidated Virtual Network Controller that Manages Millions of Tenants via Config Tree NSDI 2024
CHISEL: An optical slice of the wide-area network NSDI 2024
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving OSDI 2024
Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning NIPS 2024
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation NIPS 2024
ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency EMNLP 2024
Load is not what you should balance: Introducing Prequal NSDI 2024
Threshold-driven Pruning with Segmented Maximum Term Weights for Approximate Cluster-based Sparse Retrieval EMNLP 2024
Context Consistency between Training and Inference in Simultaneous Machine Translation ACL 2024
How Speculative Can Speculative Decoding Be? COLING 2024
RepTor: Re-parameterizable Temporal Convolution for Keyword Spotting via Differentiable Kernel Search INTERSPEECH 2024
StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection ACL 2024
Vulcan: Automatic Query Planning for Live ML Analytics NSDI 2024
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction NIPS 2024
Bolt: Sub-RTT Congestion Control for Ultra-Low Latency NSDI 2023
Enabling High Quality Real-Time Communications with Adaptive Frame-Rate NSDI 2023
ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices ICCV 2023
BAT: Boundary aware transducer for memory-efficient and low-latency ASR INTERSPEECH 2023
Protego: Overload Control for Applications with Unpredictable Lock Contention NSDI 2023
Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases ICML 2023
A New ANN-SNN Conversion Method with High Accuracy, Low Latency and Good Robustness IJCAI 2023
Delay-penalized CTC Implemented Based on Finite State Transducer INTERSPEECH 2023
Towards Real-Time Segmentation on the Edge AAAI 2023
Simultaneous Machine Translation with Tailored Reference EMNLP 2023
Unleashing the Potential of Spiking Neural Networks with Dynamic Confidence ICCV 2023