core/go-ml
8
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: document InspectAttention pass-through on InferenceAdapter
All checks were successful
Security Scan / security (push) Successful in 12s
Details
Test / test (push) Successful in 2m31s
Details

Browse source 
Co-Authored-By: Virgil <virgil@lethean.io>
This commit is contained in:
Snider 2026-02-23 12:34:32 +00:00
parent 08c8cddbe4
commit 0cf35221e6
1 changed files with 1 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
docs/architecture.md
View file

@ -132,6 +132,7 @@ Key behaviours:
- `GenerateStream` and `ChatStream` forward each token's text to the provided `TokenCallback`. If the callback returns an error, iteration stops.
- `Available()` always returns `true` — the model is already loaded when the adapter is constructed.
- `Close()` delegates to `TextModel.Close()`, releasing GPU memory.
- `InspectAttention()` delegates to the underlying `TextModel` via type assertion to `inference.AttentionInspector`. Returns an error if the backend doesn't support attention inspection. This enables LEM's Q/K Bone Orientation analysis through the adapter without consumers needing to unwrap the underlying model.
### MLX Backend (`backend_mlx.go`, darwin/arm64 only)