5 papers
pHNSW: PCA-Based Filtering to Accelerate HNSW Approximate Nearest Neighbor Search
Zheng Li, Guangyi Zeng, Paul Delestrac +2
Hierarchical Navigable Small World (HNSW) has demonstrated impressive accuracy and low latency for high-dimensional nearest neighbor searches. However, its high computational deman…
TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
Haoyun Jiang, Junqi He, Feng Hong +8
Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and respo…
VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
Shengling Qin, Hao Yu, Chenxin Wu +10
This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when t…
PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
He Xiao, Runming Yang, Qingyao Yang +6
Post-training quantization (PTQ) of large language models (LLMs) to extremely low bit-widths remains challenging due to the fundamental trade-off between computational efficiency a…
FloE: On-the-Fly MoE Inference on Memory-constrained GPU
Yuxin Zhou, Zheng Li, Jun Zhang +5
With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters…