Yisheng's Blog

I want to share a common failure pattern of quantization aware training: quantization can leave scars in tensor.

AI agents live and die by their context windows.

In this post, we implement GPT-OSS-20B inference from scratch in PyTorch.

In this post, we implement Qwen3 MoE inference from scratch in PyTorch.

Better late than never — I’ve started a repo called llm-from-scratch, where I reimplement popular open-source LLMs piece by piece, with a focus on making every component’s structure clear and easy to follow.

Today I revisit the classic LRU cache problem in my playground repo.

最近读到laike9m <工作三年我学到了什么>，听完那期捕蛇者说博客，觉得自己的视角下有许多不同，想也来写一写自己的感想。

Background 过去一年各大云服务厂商在Redis换license之后，力推使用Valkey代替Redis作为kv内存数据库的使用方案。

Background Our team planned to upgrade one of our MySQL instance from 8.0.28 to 8.0.36 through AWS RDS blue/green deployment.

Background When I tried to run a big range query on mysql using aiomysql‘s SSDictCursor, everything looks fine at first but after a period of time (15min to 20min), the query stopped with error.

Background One of the pipelines I maintained failed last week.

背景 摘抄自plantegg的blog 从2018年开始，我们有个业务陆续接到反馈 Nginx 线上集群经常出现不响应或者偶发性的“超慢”请求。

Background As what is explained in my pervious post, B+ tree depth decides the worst case of MySQL’s query performance, only considering those use index.

Rumor There’s rumor around the internet that we should avoid having > 20M rows in a single MySQL table.

背景 这个问题一开始是在进行RDS实验的时候发现的。

send/receive buffer Goal Get a better understanding of how send/receive buffer size may affect the network rtt and throughput.

packet delay, loss, duplicate, corrupt, out-of-order and bandwidth limit Goal The goal of packet capture experiment here is to get a better understanding of TCP protocol.

Observation Spark Job runtime is not stable As what can see from the screenshot, the pipeline (spark job) runtime is not quite stable.

Observation Spark cluster master node OOM Master node shutdown due to OOM.

Observation Queue client performance went down Everything worked well in the morning until we got monitoring alarm at 12:45 PM EST: <topic_name> Queue lag is too big.

Observation CronJob is taking more than 1h to complete My colleagues told me that one of the cron job stuck in the middle after a random day.

Observation Signal file is widely used in Hadoop ecosystem.

My name is Yisheng Gong.