zartbot.github.io DeepSeek-V4.1 Flash: Pushing the Limits of KV Cache Compression · zartbot A deep dive into the DeepSeek-V4.1 Flash technical report: CED, CSA2, HSI, Single-Pass mHC, Engram and FP4 KV Cache — how the KV cache was compressed to just 890 bytes per token.

• ❤ 13
• 🤔 1
• 🤮 1
• 🌭 1
• 🖕 1