DeepSeek-V4.1-Flash incorporates Compressed Sparse Attention 2 and an FP4 global key-value cache that reduces memory footprint to 890 bytes per token
Agree
Disagree
Overview
Debates
Related claims
Topics
Sources
From the article
DeepSeek Just Released V4.1-Flash-1017, Scores 77.0 on DeepSWE, Opens Search API
4
41e85161
Article
DeepSeek Just Released V4.1-Flash-1017, Scores 77.0 on DeepSWE, Opens Search API
0