conftrace_

inference acceleration

244 papers

Explore in graph

Co-occurring keywords

model compression (3302) large language model (13587) speculative decoding (111) diffusion model (3751) model acceleration (80) efficient computing (781) language model (4599) inference optimization (219) knowledge distillation (3725) neural network optimization (1293)

Papers

Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning AAAI 2025
CopySpec: Accelerating LLMs with Speculative Copy-and-Paste EMNLP 2025
LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation EMNLP 2025
FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference IJCNLP 2025
Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference CVPR 2025
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models CVPR 2025
Conical Visual Concentration for Efficient Large Vision-Language Models CVPR 2025
Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information IJCAI 2025
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion NAACL 2025
Quantization without Tears CVPR 2025
Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping ICCV 2025
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling ACL 2025
ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition AAAI 2025
Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference AAAI 2025
GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference AACL 2025
QSpec: Speculative Decoding with Complementary Quantization Schemes EMNLP 2025
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding NAACL 2025
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text EMNLP 2025
Towards Codec-LM Co-design for Neural Codec Language Models NAACL 2025
The Impact of Inference Acceleration on Bias of LLMs NAACL 2025
Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention EMNLP 2025
Speculative Sampling via Exponential Races ACL 2025
Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling ACL 2025
Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference EMNLP 2025
SAM Decoding: Speculative Decoding via Suffix Automaton ACL 2025