[KongchangAI]
Unverified50% confidenceFactExact time

张量并行将单层权重切分到多卡,延迟低但通信开销大;流水线并行按层切分,吞吐高但首token延迟长

1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/480528
API
curl https://kongchang.com/api/v1/knowledge/claims/480528
MCP
get_claim(id=480528)