DeepSeek V4.1-Flash squeezes KV cache to 890 bytes per token, cuts persistent cache 8x
jbhuang0604 · x · 2026-10-01
- DeepSeek V4.1-Flash compresses global KV cache to just 890 bytes per token and shrinks the persistent cache 8x, while staying competitive on agentic benchmarks.
- Three key techniques enable this: Causal Encoder-Decoder, Compressed Sparse Attention, and SWA Bounded Replay.
- Significant implications for inference cost on long-context and agent workloads; the linked video walks through the details.
More from Infra
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16
- vLLM serves DeepSeek V4.1-Flash at 954K tokens/s per GPU, $38.96/GPU-hour on GB300 NVL72 — bookwormengr · 2026-11-16
- Colossus 2's 1.2M B200s could generate ~$400B/year in tokens at DeepSeek Flash rates — bookwormengr · 2026-11-16
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- Qdrant 1.20.1: 50% fewer cold-storage reads, ~2x faster quantization, agent-ready setup — qdrant_engine · 2026-11-16
- One 16GB GPU runs songs, voice, images, 720p video and local RAG — all offline and open source — llama-of-death · 2026-11-16