DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression

·Hacker News··

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.

Read full article →

Related Articles

OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 4mo ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 4mo ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 4mo ago
Using “underdrawings” for accurate text and numbers
samcollins · Hacker News · 4mo ago
ProgramBench: Can language models rebuild programs from scratch?
jonbaer · Hacker News · 4mo ago