Zhongzhu (Charlie) Zhou
Home
Research
Publication
Experience
Recent News
Blog
CV
↗
Tag
#
Operating Systems
21 posts tagged with this label. Back to
all tags
or the
main feed
.
2026
09-03
EN
HIERA: Teaching LLM Agents Where to Optimize, Not Just How — Workload-Aware Planning Across GPU Implementation Spaces
09-03
中
HIERA 阅读笔记:让 LLM Agent 先学会「在哪一层优化」,再谈「怎么优化」——GPU 算子实现空间的分层规划
08-27
EN
SCOUT: Localizing Latent Training Failures via Strict-Majority Consensus Among Equivalent Replicas
08-27
中
SCOUT 阅读笔记:用「对等副本多数一致」定位大模型预训练中的隐性故障
08-23
EN
FreeToken: Turning Your Gaming PC Into a Frontier-Model Serving Box
08-23
中
FreeToken 阅读笔记:把家用主机变成能跑千亿参数模型的推理平台
08-22
EN
CacheRoute: Why Your LLM Load Balancer Is Fighting Your KV Cache
08-22
中
CacheRoute 阅读笔记:为什么你的负载均衡器一直在跟 KV Cache 打架
08-16
EN
vToken: Turning Token-Level KV Eviction into Actually Reusable GPU Memory
08-16
中
vToken 阅读笔记:如何把 Token 级 KV 淘汰真正变成可用显存
07-23
EN
PHOENIX: Recovering LLM Training in 40 Seconds Instead of Restarting the Whole Job
07-23
中
PHOENIX:让大模型训练在故障后 40 秒内复活,而不是整个作业重启
06-21
EN
Tutti: GPU-Centric SSD-Backed KV Cache That Finally Makes SSDs Practical for Long-Context LLM Serving
06-21
中
Tutti 阅读笔记:GPU 原生 SSD KV 缓存,让 NVMe 固态硬盘真正可用于长上下文大模型推理
06-14
EN
GF-DiT: Scheduling GPU Parallelism as a First-Class Resource for Diffusion Transformer Serving
06-14
中
GF-DiT:把 GPU 并行度当作可调度资源的扩散 Transformer 推理系统
2022
01-28
中
极路由S1-无官方破解路径下保姆级教程,辛酸刷机历程
2021
11-29
中
现代操作系统原理与实现-陈海波-Day 1
11-22
EN
Intel mac to M1 chip mac
09-29
EN
Operating System Memory Address
2020
11-25
EN
HHKB's BS and Delete 按钮引起的疑惑