Results for “memory efficiency”

Optimize Python code for reduced memory usage and improved memory efficiency. Use when asked to reduce memory footprint, fix memory leaks, optimize data structures for memory, handle large datasets efficiently, or diagnose memory issues. Covers object sizing, generator patterns, efficient data structures, and memory profiling strategies.

The English summary is being prepared. Showing the original description.

Design persistent agent memory that retains knowledge across sessions and retrieves relevant facts when needed. Compare storage approaches, track people and changing information, and plan memory consolidation and evaluation based on the kinds of questions the agent must answer.

• Retain user preferences across conversations
• Track people and entities consistently across sessions
• Retrieve facts valid at a specific point in time

Integrate Flash Attention into transformer models to reduce processing time and GPU memory use for long sequences. Covers PyTorch integration, advanced attention options, and benchmarks that compare speed, memory use, and output accuracy.

• Speeding up transformer training on long sequences
• Reducing GPU memory use during attention
• Adding Flash Attention to a PyTorch model

Optimize transformer attention, the calculation that relates tokens to one another, using Flash Attention. The skill guides PyTorch integration, GPU memory reduction, performance measurement, and output comparisons for training or inference with long sequences.

• Reducing GPU memory use with long sequences
• Integrating Flash Attention into PyTorch models
• Comparing runtime and outputs before and after changes

Analyzes and optimizes code for better performance, memory usage, and efficiency. Use when code is slow, memory-intensive, or inefficient. Supports Python and Java optimization including execution speed improvements, memory reduction, database query optimization, and I/O efficiency. Provides before/after examples with detailed explanations of why optimizations work, complexity analysis, and measurable performance improvements.

The English summary is being prepared. Showing the original description.

Configure large language model training with NVIDIA Megatron-Core across multiple GPUs. This skill helps choose how to split computation, set training parameters, monitor GPU efficiency, and address memory limits or unstable training.

• Planning multi-GPU training for a LLaMA-style model
• Distributing MoE model experts across GPUs
• Tuning training throughput and GPU utilization

Optimizes Simulink models for Embedded Coder generated code. Use when asked to optimize or improve generated code, or reduce code metrics for a Simulink model. Targets: execution time, memory footprint (RAM, ROM, stack, data copies), code size, MISRA compliance, or any semantically similar generated-code metric. Works iteratively — measures baseline, suggests changes, applies, and re-measures to confirm improvement. Triggers can be prompts similar to: optimize generated code runtime, reduce runtime, shrink code size, improve code efficiency, reduce memory usage, speed up generated code, follow MISRA compliance and so on. CAUTION: Do NOT attempt to optimize Simulink models for generated code efficiency without following this skill — the iterative measurement, gating, and rollback workflow is essential for safe optimization.

The English summary is being prepared. Showing the original description.

Optimizes 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.

The English summary is being prepared. Showing the original description.

Configure large language model training across multiple NVIDIA GPUs with Megatron-Core. The skill helps choose how to split models and workloads, set training parameters, monitor performance, and address memory shortages or low GPU utilization.

• Planning distributed training for a LLaMA-style model
• Distributing MoE expert networks across GPUs
• Tuning GPU utilization and training throughput

Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.

• Compressing LLMs without calibration datasets
• Serving quantized models with vLLM or HuggingFace Transformers
• Comparing bit widths and inference backends

Apply HQQ quantization, which stores language model weights using fewer bits without calibration examples. Covers precision settings, inference backends, saving compressed models, deployment with HuggingFace Transformers or vLLM, and further training with LoRA.

• Compressing a model without calibration data
• Comparing 4-bit and 2-bit quantization settings
• Running quantized models with HuggingFace Transformers or vLLM

Golang performance optimization patterns and methodology - if X bottleneck, then apply Y. Covers allocation reduction, CPU efficiency, memory layout, GC tuning, pooling, caching, and hot-path optimization. Use when profiling or benchmarks have identified a bottleneck and you need the right optimization pattern to fix it. Also use when performing performance code review to suggest improvements or benchmarks that could help identify quick performance gains. Not for measurement methodology (→ See `samber/cc-skills-golang@golang-benchmark` skill) or debugging workflow (→ See `samber/cc-skills-golang@golang-troubleshooting` skill).

The English summary is being prepared. Showing the original description.

Plan, diagnose, and verify performance budgets, latency targets, load tests, capacity estimates, bottleneck analysis, caching strategy, query efficiency, queue throughput, and regression gates. Use when a feature may be slow, a system must scale, a performance regression is suspected, or release readiness depends on throughput, cost, memory, CPU, or response time.

The English summary is being prepared. Showing the original description.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

The English summary is being prepared. Showing the original description.

Power management and performance optimization for Zephyr RTOS. Covers system power states (Idle, Suspend, Off), device-level power management, residency hooks, and code/data relocation for speed efficiency. Trigger when optimizing battery life, reducing latency, or managing memory constraints.

The English summary is being prepared. Showing the original description.

Expert in batch cooking, meal planning, food storage, and efficient kitchen workflows

The English summary is being prepared. Showing the original description.

Profile and audit mobile app performance -- cold/warm/hot startup time, memory leaks, battery drain, network efficiency, frame rate jank, and binary size. Triggers: diagnosing slow launches, investigating ANRs, reducing app size, or benchmarking rendering performance.

The English summary is being prepared. Showing the original description.

Otimiza atenção em transformers com Flash Attention para ganho de 2-4x em velocidade e redução de 10-20x em memória. Use ao treinar/executar transformers com sequências longas (>512 tokens), ao encontrar problemas de memória GPU com atenção, ou quando precisa de inferência mais rápida. Suporta SDPA nativo do PyTorch, biblioteca flash-attn, H100 FP8 e sliding window attention.

The English summary is being prepared. Showing the original description.

Quantização Half-Quadratic para LLMs sem dados de calibração. Use ao quantizar modelos com precisão 4/3/2-bit sem necessidade de conjuntos de calibração, para workflows de quantização rápida, ou ao fazer deploy com vLLM ou HuggingFace Transformers.

The English summary is being prepared. Showing the original description.

For example: 32-bit float: 4 bytes per parameter 8-bit integer: 1 byte per parameter (75% memory red GAP: public SDK / programmatic API: competitor si

The English summary is being prepared. Showing the original description.

Hive CE (Community Edition v2.19.x) NoSQL object database for Flutter providing blazing-fast key-value and object storage with TypeAdapters. Use this skill when implementing offline-first architecture, high-performance local data caching, NoSQL document-style object stores, custom TypeAdapter serialization for complex objects, lazy loading boxes for memory efficiency, encrypted boxes (HiveAES encryption), database compaction for size optimization, storing large datasets without SQL schema overhead, implementing local-first sync patterns, or migrating from SQLite to NoSQL. Supports primitive types, custom objects, lists, and maps. Ideal for apps requiring ultra-fast read/write operations (microsecond latency), object persistence without ORM complexity, or local-first data architecture.

The English summary is being prepared. Showing the original description.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

The English summary is being prepared. Showing the original description.