Author

BirdNest Tech Talk

Author of the rpcx microservice framework, original book author, and chair of Baidu's Go CMC committee.

131

Articles

Likes

Views

Comments

Latest from BirdNest Tech Talk

100 recent articles max

BirdNest Tech Talk

Oct 20, 2025 · Artificial Intelligence

How Embedding Models Power Semantic Search: A Hands‑On LangChain Guide

This article explains what embeddings are, how LangChain’s Embeddings interface abstracts various providers, compares common models, and walks through a complete Python example that uses a Chinese‑optimized HuggingFace model to generate document and query vectors, compute cosine similarity, and identify the most relevant text.

EmbeddingsLangChainNLP

0 likes · 9 min read

How Embedding Models Power Semantic Search: A Hands‑On LangChain Guide

BirdNest Tech Talk

Oct 17, 2025 · Artificial Intelligence

How to Extend Claude with Custom Agent Skills Using SKILL.md

Claude’s new Agent Skills let developers package domain expertise into organized SKILL.md files and resource folders, enabling progressive disclosure, code execution, and scalable context loading, with detailed guidance on structure, bundling, evaluation, and security considerations for building robust, reusable AI agents.

AI AgentsAgent SkillsClaude

0 likes · 11 min read

How to Extend Claude with Custom Agent Skills Using SKILL.md

BirdNest Tech Talk

Oct 16, 2025 · Artificial Intelligence

Mastering Text Splitting in LangChain: From Theory to Code

This guide explains why large documents must be broken into semantic chunks for LLMs, introduces core parameters like chunk_size and chunk_overlap, compares LangChain's various splitters, and walks through a complete Python example that loads a long text, configures a RecursiveCharacterTextSplitter, and inspects the resulting chunks.

EmbeddingLangChainRAG

0 likes · 9 min read

Mastering Text Splitting in LangChain: From Theory to Code

BirdNest Tech Talk

Oct 15, 2025 · Artificial Intelligence

How DeepSeek‑V3.2‑Exp Achieves Fast Distributed LLM Inference with FP8 and MoE

This article walks through the DeepSeek‑V3.2‑Exp inference codebase, detailing its MoE architecture, Multi‑Head Latent Attention, FP8 quantization, custom CUDA kernels, and 8‑GPU NCCL‑based distributed execution from initialization through prefill and decode stages.

CUDAFP8 quantizationLLM

0 likes · 9 min read

How DeepSeek‑V3.2‑Exp Achieves Fast Distributed LLM Inference with FP8 and MoE

BirdNest Tech Talk

Oct 14, 2025 · Fundamentals

Can You Write IPv4 Addresses in One Number? Exploring the Hidden Shorthand Rules

This article explains the undocumented IPv4 address shorthand supported by Unix-like tools, detailing how different part counts are expanded, the underlying fill‑in logic, practical command‑line examples, security implications, and cross‑platform compatibility.

IPv4Unixaddress shorthand

0 likes · 9 min read

Can You Write IPv4 Addresses in One Number? Exploring the Hidden Shorthand Rules

BirdNest Tech Talk

Oct 14, 2025 · Artificial Intelligence

How DeepSeek’s Lightning Indexer Enables Efficient Sparse Attention for Long Texts

The article explains how DeepSeek’s Lightning Indexer acts as a memory‑filtering expert that computes index scores, selects the top‑k relevant tokens, and maps a compact formula to FP8 kernel code, reducing attention complexity from 128K to 2048 tokens for massive sequences.

DeepSeekFP8Lightning Indexer

0 likes · 7 min read

How DeepSeek’s Lightning Indexer Enables Efficient Sparse Attention for Long Texts

BirdNest Tech Talk

Oct 12, 2025 · Artificial Intelligence

What Happens When a Token Travels Through GPU Villages via RDMA and NVLink?

The article uses a whimsical journey to illustrate how token data is dispatched across GPU clusters—detailing functions like get_dispatch_layout, notify_dispatch, and combine_token, showing RDMA and NVLink pathways, performance experiments, and the final verification of token integrity.

AIDistributed SystemsGPU

0 likes · 5 min read

What Happens When a Token Travels Through GPU Villages via RDMA and NVLink?

BirdNest Tech Talk

Oct 11, 2025 · Artificial Intelligence

How to Load Documents into LangChain: From Files to APIs

Learn how to use LangChain's Document Loaders to import data from files, web pages, databases, and APIs, understand the Document object structure, compare load() versus lazy_load(), and follow a step‑by‑step Python example that demonstrates loading, inspecting, and optionally processing documents with an LLM.

Document LoaderLLMLangChain

0 likes · 12 min read

How to Load Documents into LangChain: From Files to APIs

BirdNest Tech Talk

Oct 10, 2025 · Artificial Intelligence

How to Build a Custom Output Parser in LangChain for Non‑Standard LLM Formats

This guide explains why custom output parsers are needed for LangChain when dealing with non‑JSON or XML responses, walks through inheriting BaseOutputParser, implementing parse() and optional format instructions, and provides a complete Python example that converts a simple "Key: Value" string into a dictionary.

CustomParserLLMLangChain

0 likes · 6 min read

How to Build a Custom Output Parser in LangChain for Non‑Standard LLM Formats

BirdNest Tech Talk

Oct 9, 2025 · Fundamentals

What’s New in Go’s sync Package? A Deep Dive into APIs, Performance, and Safety

Over the past two years, Go’s sync and sync/atomic packages have introduced new APIs like WaitGroup.Go, enhanced Map methods, modernized atomic types, restructured internal implementations, and added developer‑friendly safeguards such as noCopy, all aimed at improving usability, safety, and performance for concurrent Go programs.

APIGoPerformance

0 likes · 12 min read

What’s New in Go’s sync Package? A Deep Dive into APIs, Performance, and Safety