inference/research
verifiedhigh · 0.95updated 2026-10-03

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

paper

Fields

id
sources/pap-attn-minference
URL
https://arxiv.org/abs/2407.02490
Publisher
arXiv
Kind
paper
Published
2024-07-02
Accessed
2026-10-03
notes
arXiv comment states 'Accepted at NeurIPS 2024 (Spotlight)'.

Notes

arXiv comment states 'Accepted at NeurIPS 2024 (Spotlight)'.

Cross-references

This record references no other records.