Daniel Hiltgen ea8d65004a server: extract GGUF metadata and unify capabilities (#17858) ...

Loading GGUF metadata is an expensive operation. Two caches had evolved to
mitigate this, and the two capability implementations produced inconsistent
results for some models.

This PR now extracts the metadata once per blob into a file at
<OLLAMA_MODELS>/metadata/sha256-<hex>.json. Only arrays over 4096 elements and
non-finite floats are left out.

Direct Capabilities() discovery now costs us instead of ms.  /api/tags can
build directly from manifests and the extracted metadata.

2026-09-10 11:16:37 -07:00

..

layer.go

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

manifest_test.go

Clean up the manifest and modelpath (#13807)

2026-01-21 11:46:17 -08:00

manifest.go

server: extract GGUF metadata and unify capabilities (#17858)

2026-09-10 11:16:37 -07:00

paths.go

server: extract GGUF metadata and unify capabilities (#17858)

2026-09-10 11:16:37 -07:00