LocalAI

0 Fork 0

mirror of https://github.com/mudler/LocalAI.git synced 2026-09-25 15:44:56 -04:00

Files

T

leilei3167 a95ef3e7f3 fix(backend): re-probe MediaMarker after cold vision model load (#12254 )

llama.cpp picks a new random media marker per backend process. LocalAI
cached the first probe on the model config and skipped later probes when
MediaMarker was non-empty, so after SINGLE_ACTIVE eviction/reload the
prompt still used the stale marker and mtmd_tokenize failed (0 markers
vs 1 bitmap).

Re-probe whenever the model was not already resident before Load, while
still skipping the RPC on warm cache hits.

Fixes #12246

Assisted-by: Cursor:composer-2.5

Signed-off-by: leilei3167 <imleilei123@gmail.com>

2026-09-25 09:16:33 +02:00

application

fix(gallery): verification follow-ups for oci:// galleries (#12243 )

2026-09-24 21:20:21 +02:00

backend

fix(backend): re-probe MediaMarker after cold vision model load (#12254 )

2026-09-25 09:16:33 +02:00

cli

feat(gallery): galleries published as OCI artifacts (#12167 )

2026-09-21 09:23:05 +02:00

clients

security(http): refuse redirects on outbound clients via hardened pkg/httpclient (#10087 )