FP4
AssessTechniques
A 4-bit floating-point numeric format used to reduce memory footprint and bandwidth.
Why it's here
Placed in Assess: 2 article(s) of evidence from 2 source(s), led by research-stage coverage, with 1 in the last 30 days. Confidence 42%.
Evidence (2)
- 8Hacker News·9/17/2026researchDeepSeek-V4.1 Flash Targets Extreme KV Cache Compression
A technical report on DeepSeek-V4.1 Flash describes a model redesign focused on reducing KV cache storage and prefill compute for long-context agent workloads. The paper combines architectural changes such as selective layer activation, multi-stage KV cache compression, sparse attention optimizations, and FP4 KV cache to improve throughput and lower deployment costs.
- 7Hacker News·8/3/2026researchCloudflare scales Kimi and GLM with KV cache quantization and weight compression
Cloudflare says it is serving Moonshot's Kimi K-series and Z.ai's GLM more efficiently on Workers AI by combining KV cache quantization, weight compression, and cache protection techniques. The company reports that FP8 KV cache and INT4 weights cut GPU memory use and lower costs while preserving model accuracy, using SGLang as the serving framework.