inference/research
verifiedhigh · 0.88updated 2026-10-03

Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference (Tang et al., MIT Han Lab)

paper

Fields

id
sources/qlab-quest-paper
URL
https://arxiv.org/abs/2406.10774
Publisher
arXiv
Kind
paper
Published
2024-06-16
Accessed
2026-10-03
notes
v2. Page-level min/max Key metadata; sparsity, NOT quantization.

Notes

v2. Page-level min/max Key metadata; sparsity, NOT quantization.

Cross-references

This record references no other records.