Eagle
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
Learn how to configure FlashAttention for Eagle inference across diverse GPUs. Install the right FlashAttention 2 wheel and enable optimized kernels for faster performance.
Eagle Tokenizer Configuration for Multimodal Inputs: A Complete GuideDiscover the Eagle tokenizer configuration for multimodal inputs. Learn how Eagle uses Hugging Face AutoTokenizer with special image tokens and padding for vision-language encoding.
How LocateAnything Performs Zero-Shot Object Detection in the Wild: A Technical Deep DiveUnlock zero-shot object detection with LocateAnything. Discover how this unified vision-language model achieves precise detection in the wild without fine-tuning. Learn the technical details.
How to Add a Custom Evaluation Task to Eagle's LMMS-Eval FrameworkEasily add custom evaluation tasks to Eagle's LMMS-Eval framework. Create YAML and Python files in a new folder for automatic discovery without core code changes.
Memory Optimization Techniques in Eagle for Training Large Multimodal ModelsDiscover Eagle's memory optimization techniques like FlashAttention and gradient checkpointing for efficient large model training. Train 8B models on a single GPU.
How Eagle's Vision-Language Projector Handles Feature Fusion from Multiple EncodersDiscover how Eagle fuses features from multiple vision encoders. Learn about its configurable linear layer or MLP projection into the LLM's hidden space.
How to Debug Vision Tower Loading Issues in Eagle Training: A Complete GuideDebug Eagle training vision tower loading issues. Verify paths inspect keys check config and run a dummy pass. Master NVlabs/Eagle troubleshooting for efficient AI development.
Understanding Spatial and Flat Patch Merge Types in EagleDiscover the difference between spatial and flat patch merge types in Eagle models. Learn how mm_patch_merge_type configures 1D vs 2D patch processing for enhanced visual understanding.
How Eagle Handles Multi-Image Input in a Single Forward Pass: Architecture and ImplementationDiscover how Eagle handles multi-image input in a single forward pass. Learn its architecture and implementation for efficient image processing and feature integration.
How to Integrate Eagle with TensorRT for Optimized InferenceIntegrate Eagle with TensorRT for optimized inference by exporting to ONNX, building a TensorRT engine, and replacing PyTorch execution.
Data Post-Training Strategies in Eagle 2 for Frontier Vision-Language ModelsDiscover Eagle 2.5's data post-training strategies, including Progressive Mixed Post-Training and Information-First Sampling, that expand context windows to 128K tokens while maintaining visual fidelity.
Eagle 2.5 Long-Context Training Strategy: Processing 28K Tokens EfficientlyDiscover Eagle 2.5's efficient long-context training strategy. Learn how its custom attention kernel and token packing process 28K tokens for stable, high-performance results.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →