🎯 Use Case Hermes Skill

optimizing-attention-flash

Speed up long-sequence transformer training and inference.

仓库: NousResearch/hermes-agent · v1.0.1 · by Orchestra Research · MIT

OptimizationFlash AttentionAttention OptimizationMemory EfficiencySpeed OptimizationLong ContextPyTorchSDPAH100FP8Transformers

文件路径

optional-skills/mlops/flash-attention/SKILL.md