anhvth
10 verified skills70 total stars
caching-utilities
Guide for using caching utilities in speedy_utils, including memory, disk, and hybrid caching strategies for sync and async functions.
documentation7
io-utilities
Guide for using IO utilities in speedy_utils, including fast JSONL reading, multi-format loading, and file serialization.
development7
dataset-processing-multiprocessing
Advanced pattern for processing large HuggingFace datasets in parallel using speedy_utils.multi_process, with sharding, worker initialization, temporary file management, and safe cleanup.
data-ai7
llm-integration
Guide for using LLM utilities in speedy_utils, including memoized OpenAI clients and chat format transformations.
tools7
.github/skills/ray-distributed-computing
Comprehensive guide to using Ray for scalable distributed computing, including Ray Core, Data, Train, Tune, Serve, and RLlib with practical examples
documentation7
vision-utilities
Guide for using vision utilities in speedy_utils, including fast GPU image loading, memory-mapped datasets, and notebook visualization.
documentation7
edit-llm-inference-style
Guide for adjusting speedy_utils LLM inference style, including chat templating, <think> prefixes, stop sequences, and boxed-answer handling.
documentation7
make-vscode-happy
Reduce VS Code Python red squiggles to zero in this repository. Use when Pylance or pyright reports errors, when tools/check_syntax.py fails, or when a change should leave VS Code diagnostics clean.
tools7
skill-creation
Guide for creating new Agent Skills with proper structure, frontmatter, bundled assets, and validation. Includes templates, best practices, and examples for building reusable skill resources.
development7
multi-threading-processing
Comprehensive guide for using multi-threading and multi-processing in Python, including when to choose each approach, best practices, and practical examples using the speedy_utils library.
development7