corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0d93b-fffe-72d4-a430-05eb9d27ba2c

DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse

marktechpost.com · published 10 September 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at marktechpost.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
10
Words captured
885

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://huggingface.co/deepseek-ai
huggingface.co
https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
huggingface.co
https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/tree/main/LICENSE
huggingface.co
https://arxiv.org/abs/2405.05254
arxiv.org
Introducing NVFP4 for Efficient and Accurate Low-Precision Inference Read at the source ↗
developer.nvidia.com
https://arxiv.org/abs/2512.24880
arxiv.org
https://arxiv.org/abs/2601.07372
arxiv.org
https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/DeepSeek_V41_Tech_Report.pdf
huggingface.co
https://magic.beehiiv.com/v1/f5e63dd4-5653-4f09-83e2-321a8b1ba526?email={{email}}
magic.beehiiv.com
https://forms.gle/wbash1wF6efRj8G58
forms.gle