Unverified50% confidenceFactExact time
流水线并行按模型的不同层将计算分配到不同设备,通信量仅为相邻层的激活张量,但存在流水线气泡问题
1
Sources
50%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
TensorRT多设备推理:突破单GPU显存瓶颈的工程实践
rss6/25/2026
Related Claims
Cite This Claim
Stable URI
https://kongchang.com/claim/461708API
curl https://kongchang.com/api/v1/knowledge/claims/461708MCP
get_claim(id=461708)