Sept 10 — DeepSeek launched its V4.1 Flash model, the smallest in its new architecture series, with native multimodal visual understanding. The company said the model sharply reduces KV cache size: HBM requirements drop to one-quarter and SSD require

2026-09-10

Sept 10 — DeepSeek launched its V4.1 Flash model, the smallest in its new architecture series, with native multimodal visual understanding. The company said the model sharply reduces KV cache size: HBM requirements drop to one-quarter and SSD requirements to one-eighth versus the prior generation. DeepSeek added that KV cache compression materially lowers operating costs for agent-style workloads, where cache-hit costs are a significant share of expenses.

Other News
2026-09-10

Asian Stocks 1. The Shanghai Composite Index closed up 10.96 points, or 0.28%, at 3951.51 on Wednesday, September 9th. 2. The Shenzhen Component Index closed up 20.11 points, or 0.15%, at 13723.32 on Wednesday, September 9th. 3. The CSI 300 Index

2026-09-10

US President Trump: I am confident that the Air Force One donated by Qatar is safe.