[KongchangAI]
Unverified50% confidenceFactExact time

FlashInfer 是一个专为 LLM 推理设计的高性能注意力计算库,提供针对 GPU 优化的 kernel,能加速大模型的解码与预填充阶段

1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/929265
API
curl https://kongchang.com/api/v1/knowledge/claims/929265
MCP
get_claim(id=929265)