June 2026

Recent Posts
LLM 推理优化学习主干道
03 · C++ 编译模型与 CMake
04 · CUDA 执行模型
01 · Transformer 结构与 Attention 计算
02 · C++ 必要基础
Categories
Tags
QUIC Index scheduling task_struct memory-hierarchy 进程管理 pointer consumer-group ISR gemm IO多路复用 throughput retention gpu Linux engineering continuous-batching DNS distributed-systems memory zookeeper cmake grid replication kafka append-only log ai-infra attention metadata llm-inference template offset inference consumer roofline autoregressive cpp compression qkv
Archives
Website Info
Article Count :
24
Total Word Count :
44.1k
Unique Visitors :
Page Views :
Last Update :