Results for “flash attention”

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

Integrate Flash Attention into Transformer models to speed up attention, the calculation that relates input elements, while reducing GPU memory use. Covers PyTorch integration, performance measurement, output comparison, and a separate H100 optimization path.

• Optimize training with long input sequences
• Reduce memory use during long-context inference
• Measure speed and compare model outputs

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.

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.

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.

Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.

• Compare performance before and after v3 optimization
• Evaluate vector search speed and memory use
• Track performance regressions over time

Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.

• Compare performance before and after v3 optimization
• Evaluate vector search speed and memory use
• Track performance regressions over time

Helps extend how much text a language model can process at once. Covers choosing RoPE, YaRN, ALiBi, or position interpolation, implementing position information, fine-tuning on longer documents, and managing memory during inference.

• Extend an existing model to handle longer documents
• Compare context extension methods
• Implement position information in attention layers

Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.

• Consolidate duplicate agent and task management code
• Design an adapter that preserves existing APIs
• Integrate learning, shared memory, and MCP tools

Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.

• Consolidate duplicate agent and task management code
• Design an adapter that preserves existing APIs
• Integrate learning, shared memory, and MCP tools

Operate Flash Linear Attention package workflows: setup, kernels, layers/models, KDA/context parallel, and benchmarking.

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

Extend the amount of text a language model can process at once. Compares RoPE, YaRN, ALiBi, and position interpolation, with implementation examples, additional training guidance, and memory optimization approaches for long document processing.

• Extend an existing model to handle longer inputs
• Compare methods for representing token positions
• Plan additional training with long documents

Train language models on pairs of preferred and rejected answers without a separate reference model. The skill guides training setup, model-specific configurations, parameter tuning, and troubleshooting for unstable training or memory limits.

• Train a base model using preferred and rejected answer pairs
• Further tune an instruction-following model
• Adjust training settings for math and coding tasks

Train language models with SimPO using pairs of preferred and rejected answers. Configure preference training without a separate reference model, adapt settings for base or instruction models, and address unstable training, memory limits, or lost capabilities.

• Training a base model with preferred and rejected answers
• Further tuning an instruction model with preference data
• Adjusting training settings for math and code tasks

Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.

• Training a language model on example responses
• Training with preferred and rejected response pairs
• Debugging GRPO reward functions and batch settings

Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.

• Running large language models with limited GPU memory
• Quantizing a model with domain-specific text
• Serving an AWQ model with vLLM

Guide language model training with SimPO using pairs of preferred and rejected answers. Covers configuration, learning rate tuning, and memory troubleshooting for preference alignment, which adjusts model responses toward human preferences without a separate reference model.

• Training on preferred and rejected answer pairs
• Exploring an alternative to DPO without a reference model
• Tuning preference training for math and code tasks

Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.

• Training a language model on example responses
• Training with preferred and rejected response pairs
• Debugging GRPO reward functions and batch settings

Build iOS and Android apps with React Native and Expo. Get guidance and typed component code for navigation, lists, animations, storage, and platform differences, with attention to scrolling performance and testing on both platforms.

• Building mobile screens with React Native and Expo
• Adding screen navigation with Expo Router
• Improving list scrolling and animation performance

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.

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

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.

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

Provides guidance for writing, optimizing, and benchmarking Triton kernels for Intel XPU GPUs (Battlemage/Arc Pro B50) using the Xe-Forge optimization framework. Includes an LLM-driven trial-loop workflow (analyze, validate, benchmark, profile, finalize), XPU-specific patterns (tensor descriptors, GRF mode, tile swizzling), KernelBench fused kernels, and Flash Attention.

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

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.

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