Unverified50% confidenceFactExact time
Long Decode allows output of up to 1M tokens, making it one of the implementations with the largest output window among current frontier models.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
Unverifieddecode阶段的生成速度近似等于内存带宽÷模型大小，例如在内存带宽273GB/s的M4 Pro上运行4GB的Q4量化7B模型理论最大生成速度约68 tokens/s74% similarUnverified自回归推理的decode阶段是纯粹的内存带宽受限操作，将模型从FP16压缩到1-bit理论上可将token生成速度提升16倍73% similarUnverifiedKV Cache stores the Key and Value matrices of all previous tokens during the Decode phase, grows with conversation turns and context window size, and can occupy anywhere from a few GB to tens of GB of memory in long-text scenarios71% similarUnverifiedLarge model context windows have expanded from 4K tokens to 128K or even longer, enabling models to understand the code structure of an entire project.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023317API
curl https://kongchang.com/api/v1/knowledge/claims/1023317MCP
get_claim(id=1023317)