后训练 RL：从 Trainer 框架到 Runtime 系统

笔记 分类

2026

06-14

后训练 RL：从 Trainer 框架到 Runtime 系统

06-10

NeMo-RL 中 NVLink Domain 与 Rank Placement

06-05

MAI-Thinking-1 技术报告阅读

06-04

MiniMax M2 Series 技术报告阅读

05-23

Ray Direct Transport (RDT)

03-24

Ray Job Init Containers in KubeRay: Lifecycle Nuances

2025

10-12

rl infra

2022

08-14

Docker container -i -t

2021

07-18

k8s init and sidecar container

07-18

pod spec of volcano job and sysctl