ggml-org/llama.cpp b11388

on GitHub

imatrix: calculate activation-based statistics for new format (GGUF) imatrices (#14891)

• Use activations to calculate the stats
• Determine calculation mode
• Compute entropy for activations
• Compute cosine similarity based on activations
• Compute l2 norm
• Add compute_layer_statistics() function
• Update aggregated statistic report layout
• Fix printing l2 norm when calc_mode = 1
• Refactor variable name
• Compute aggregated (per layer) l2 norm
• Update aggregated sum of squared activations per layer
• Make ZD Score two-tailed
• Update report layout
• Reverse conditional logic to match convention
• Rename report heading
• Add --activation-statistics parameter
• Add Euclidean–Cosine Score (ECS)
• Add --activation-statistics logic to avoid doubling the imatrix size by default
• Update stats output sort based on imatrix type
• Process external NextN draft files (-md / --model-draft)
• Refactor to use new llama_batch_ext

Co-authored-by: compilade git@compilade.net
Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co