deepseek harness is quite promising considering MIT license, plugin-based architecutre and harness optimization. Today I tried to work on how to write plugins for cordis and deepseek-harness. In the past I built it from source and run it. however I got below issues this time when I tried to develop somethings following develop guide. # following the steps mentioned in readme.md pnpm install pnpm run build ERROR Error: [@deepseek-ai/dsh-root] Cannot find entry: ["lib/types/{index,invariant,startup}.

Several days ago, I came across a claim from Magnitude stating that it’s up to 2x faster than llama.cpp, and—more interestingly for me—that it supports AMD GPUs as well. Naturally, I was skeptical. A 2x speedup over llama.cpp is a bold claim, especially on AMD hardware where the ROCm ecosystem can be hit-or-miss. So today, I decided to give it a try and run my own benchmarks. Setup I used the following build for Magnitude:

When talking about AI at scale, I have always thought about it from the model-serving infrastructure perspective: How many GPUs do we need? How do we scale inference? How do we reduce latency and cost? How do we serve millions of concurrent requests? How do we efficiently distribute models across GPU clusters? But there is another way to think about AI at scale. Instead of scaling the AI model itself, what if we scale software development across ordinary users?

From COBOL to Modern Programming Languages About 26 years ago, I learnt COBOL using the book 《COBOL 语言》（上、下册） by 谭浩强 (Tan Haoqiang). Here is a portion of my transcript. At the time, I developed a simple MIS (Management Information System) using COBOL. It was one of the programming languages I worked with early in my career. Since then, I never really had the opportunity to work with COBOL professionally.

Overview This document outlines the procedure for deploying the BMC Control-M Workbench (version 9.20.200) within a Docker environment. The Workbench provides a local development sandbox for the Control-M Automation API, allowing users to test workload automation jobs and orchestration flows without connecting to a production Control-M Server. The official BMC distribution currently provides access to the Workbench image without requiring a commercial license for evaluation purposes.

In March, I attempted to run DevStack on my newly bought mini PC, but something was wrong and I couldn’t get it started. Since then, I poured all my attention into AI‑related studies. During lunch today, OpenStack came up in conversation, and the idea popped into my head: “Why not use a coding agent to make it work, since I’ve already used one for several issues in my WSL environment?” This post is the result.

Over the past few days, I’ve been using reranker models through cloud APIs as part of my RAG experiments. After successfully running several LLMs locally with llama.cpp, I started wondering: Can I also run a reranker model locally? The answer is yes. It turns out that llama-server can host embedding models, reranker models, and chat models behind the same OpenAI-compatible API. This makes it easy to build a completely local RAG pipeline without relying on external services.

Automatic Speech Recognition (ASR) has become an essential capability for many AI-powered applications. Whether it is transcribing meetings, generating subtitles, or enabling voice-based interactions, ASR is increasingly becoming a core feature of modern AI systems. As part of my ongoing learning journey with AI technologies, I decided to start exploring the ASR capabilities available today. My first stop is Qwen3-ASR, one of the latest speech recognition models from the Qwen family.

Serving LLMs with Dev Containers: A New Rabbit Hole One of the interesting things about working with AI is that you often discover new ideas when you’re exploring something completely different. I never imagined I would write about serving Large Language Models (LLMs) using Dev Containers. Although I’ve been using the vLLM container for quite some time, I always thought of it simply as another containerized application running in Kubernetes or Docker.