Unverified50% confidenceFactExact time
In an environment where cgroup limits the CPU quota (about 30 cores) but exposes 256 threads, Strata's default worker pool configuration caused performance to drop to about 30 tokens/s instead of the expected 170 tokens/s
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedStrata's multi-user concurrency uses a parallel slot mechanism, and the slots do not use speculative decoding, causing single-user speed to drop from 144 to 38 tokens/s76% similarUnverifiedWhen the context exceeds 64,000 tokens, Strata keeps most of the KV cache in memory and retains only the hottest 32,000 tokens in VRAM, improving speed from approximately 51 to 63 tokens/second at a 262,000-token context.72% similarUnverifiedLocally running open-source LLM models typically have a context capacity of only 4K to 32K tokens, limited by hardware memory.69% similarUnverifiedA user runs the 397B model on 4× ASUS GB10 units achieving 30 tokens/s at only 400W of power consumption, compared to 50–60 tokens/s at 6kW previously.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053019API
curl https://kongchang.com/api/v1/knowledge/claims/1053019MCP
get_claim(id=1053019)