conftrace_

language model inference

18 papers

Explore in graph

Co-occurring keywords

large language model (13587) speculative decoding (111) inference acceleration (244) inference optimization (219) token generation (47) key-value cache (55) language model (4599) gpu optimization (27) memory efficiency (261) batch processing (19)

Papers

Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs EACL 2026
iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference AAAI 2026
Steering Pretrained Drafters During Speculative Decoding AAAI 2026
Dynamic-Width Speculative Beam Decoding for LLM Inference AAAI 2025
CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation AAAI 2025
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025
Improving Consistency in LLM Inference using Probabilistic Tokenization NAACL 2025
Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention EMNLP 2025
Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree AAAI 2025
BASS: Batched Attention-optimized Speculative Sampling ACL 2024
Optimized Speculative Sampling for GPU Hardware Accelerators EMNLP 2024
An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference EMNLP 2024
Loki: Low-rank Keys for Efficient Sparse Attention NIPS 2024
The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics NAACL 2024
Efficient LLM Scheduling by Learning to Rank NIPS 2024
Speculative Contrastive Decoding ACL 2024
An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language Models NAACL 2021
SyntaxGym: An Online Platform for Targeted Evaluation of Language Models ACL 2020