ZeroHour

Search: “Canvas”

2 stories in the last 30d

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

DeepSeek-V4.1 Flash is a 552B-parameter multimodal MoE model with 1M-token context achieving 4x KV cache compression for long-horizon agent workloads.

A detailed analysis of the DeepSeek-V4.1 Flash technical report describes a 552B-parameter multimodal mixture-of-experts model supporting contexts up to 1 million tokens. Its Causal Encoder-Decoder (CED) architecture activates 8B parameters during prefill and 16B during decode, and reportedly delivers about 420 tokens/s. Joint optimization of architecture (CSA2 cross-layer compression), FP4 KV cache precision, and deployment strategy cuts runtime KV cache to roughly 1/4 and persistent KV cache to about 1/8 of DeepSeek-V4-Flash at the same sequence length, targeting storage and bandwidth bottlenecks in long-horizon agent serving. The author notes all DeepSeek-V4 Pro models were taken offline following the release.

ChatGPT Images 2.5: Faster, more precise, but not the same for everyone

OpenAI released GPT-Image-2.5 (Flare and Sunburst variants), cutting image generation latency up to 50% and improving multi-round edit consistency.

OpenAI launched GPT-Image-2.5 in two API variants: Flare, the faster default with higher quality than GPT-Image-2 at up to 50% lower latency, and Sunburst, built for precise multi-round edits. Both cost $8 per million input and $30 per million output tokens, with new xhigh and max quality tiers; a max-tier 1024x1024 image runs roughly $0.21. Testing found edit consistency strong in ChatGPT Work but inconsistent in Chat, and OpenAI has not documented how ChatGPT routes users between the models.

The Decoder · 8d agoModel release