Other
3,534 results
- Microservices Patternsdavila7Master microservices architecture patterns including service boundaries, inter-service communication, data management, and resilience patterns for building distributed systems.
- Miles Rl Trainingdavila7Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
- Model PruningOrchestra ResearchReduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
- Moe Trainingdavila7Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase.
- N8n Node Configurationdavila7Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node_essentials and get_node_info, or learning common configuration patterns by node type.
- Nextjs Supabase Authdavila7Expert integration of Supabase Auth with Next.js App Router Use when: supabase auth next, authentication next.js, login supabase, auth middleware, protected route.
- Offer Comparison Analyzerdavila7Compare multiple job offers side-by-side with total compensation analysis. Use when the user has multiple offers and wants to compare salary, equity, benefits, or total comp.
- Openrlhf TrainingOrchestra ResearchHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
- Optimizing Attention Flashdavila7Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
- Perplexitydavila7Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.
- PocketBase Migrationsdavila7Schema migrations and versioning for PocketBase. Use when creating migrations, managing schema versions, syncing collections between environments, using automigrate, or creating collections programmatically. Covers migrate commands, migration file format, snapshot imports, and the _migrations tracking table.
- Powershell Windowsdavila7PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.
- Progressive Web Appdavila7Build Progressive Web Apps (PWAs) with offline support, installability, and caching strategies. Trigger whenever the user mentions PWA, service workers, web app manifests, Workbox, 'add to home screen', or wants their web app to work offline, feel native, or be installable.
- Prometheus Configurationdavila7Complete guide to Prometheus setup, metric collection, scrape configuration, and recording rules.
- Pytorch Fsdpdavila7Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
- Quantizing Models BitsandbytesOrchestra ResearchQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
- Rag Implementationdavila7Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.
- Ray TrainOrchestra ResearchDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
- Reference List Builderdavila7Format professional references properly and prepare reference materials. Use when the user mentions references, reference list, references page, or preparing referees for a job application.
- Resume Ats Optimizerdavila7Optimize resumes for Applicant Tracking Systems, check ATS compatibility, and analyze keyword match. Use when the user mentions ATS, applicant tracking, keyword optimization, parsing, or getting past resume screening software.
- Resume Quantifierdavila7Find opportunities to add metrics and estimate numbers when exact data is unavailable. Use when the user wants to quantify achievements, add numbers, percentages, or impact metrics to a resume.
- Resume Tailordavila7Customize resume for specific job postings while maintaining truthfulness. Use when the user wants to tailor, customize, or target their resume for a specific job, company, or role.
- Resume Version Managerdavila7Track different resume versions, maintain a master resume, and manage tailored variants. Use when the user mentions managing multiple resume versions, master resume, or organizing tailored copies.
- Salary Negotiation Prepdavila7Research market rates, build negotiation strategy, and create counter-offer scripts. Use when the user mentions salary negotiation, counter offer, compensation discussion, or pay raise conversation.