tags

computer_composition database sql distributed_sys cloud_native history kubernetes Consensus Chubby etcd ZooKeeper structure algorithm p_np computability agentsys search mcts reinforcement_learning pl java jvm gc transformer llm math probability stochastic_process queueing reliability mlsys gpu cuda operating_system os unix power-management acpi context_engineering memory_management agentic_search prompt_engineering planning reasoning llm_inference rca log_analysis cloud_incidents moe decoding llm_agent tool_use reflection self_improvement safety hallucination steering rollback kernel ml_training vllm kvcache memory virtual_machine container schedule chaos_system system_failure network cyber_security docker icmp vpn security go linear_attention edge_inference nccl

Yuchen You (Wesley)

Announcement

This is my Blog

Recent Post

prims_simple.h2026-09-21

Kimi Linear: An Expressive, Efficient Attention Architecture2026-09-02

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution2026-09-02

4. Inference-Time Intervention (Steering 与 Rollback)2026-09-01

8.deepseekv22026-07-29

Categories

notes88
papers45

Tags

agentic_search unix jvm acpi os transformer llm_agent llm_inference context_engineering llm vllm java rca edge_inference agentsys distributed_sys log_analysis mlsys probability memory_management virtual_machine queueing container cyber_security computer_composition algorithm Chubby hallucination decoding p_np docker safety gc linear_attention icmp reasoning go self_improvement kvcache pl

Archives

September 20264
July 202611
June 20266
May 202612
April 20263
March 20262
January 20261
December 20254

Info

Article :

134

UV :

PV :

Last Update :

©2020 - 2026 By Yuchen You (Wesley)

Framework Hexo|Theme Butterfly

welcome to my blog!

Search

Loading the Database