Unverified50% confidenceEventExact time
In an AWS sample application, across 28 calls reviewing the same document, CloudWatch recorded 196,680 tokens written to cache and 0 reads, because the cache point was placed after each entry's own instructions; after moving the cache point to after the document, the second entry immediately became a read of 4,624 tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedA Strands user reported that a turn with 18 tool calls resulted in 0 cache reads and 134,082 tokens of cache writes.69% similarVerifiedTaking the LLaMA-2 70B model as an example, a sequence of 2048 tokens requires approximately 4 GB of VRAM for the KV cache alone.64% similarUnverifiedThe study validates on three datasets—TinyStories, WikiText-103, and CNN/DailyMail—scaling each corpus from 512 chunks to 2,048 chunks, with each chunk consisting of 64 tokens.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006081API
curl https://kongchang.com/api/v1/knowledge/claims/1006081MCP
get_claim(id=1006081)