Tag

#hybrid-attention-architecture

1 post

AI & Machine LearningMay 2, 202621 min
DeepSeek V4: Open-Weight Frontier at 1/7 the Cost
DeepSeek V4 ships 1.6T MoE open weights with 1M-token context: 80.6% on SWE-bench Verified at $1.74/$3.48 per million — roughly 1/7 the output cost of Claude Opus 4.7.

Every post in #hybrid-attention-architecture (1)

DeepSeek V4: Open-Weight Frontier at 1/7 the Cost