LocalAI

0 Fork 0

mirror of https://github.com/mudler/LocalAI.git synced 2026-11-07 04:53:24 -05:00

Files

T

Caldalis 91ff3f06cc feat(gallery): add MiniCPM-OCR 1.0 models

Add OpenBMB's 1.3B Chinese/English document parser to the gallery as
three llama.cpp entries: the recommended Q8_0 build, a smaller Q4_K_M
build for constrained hosts, and an optional DSpark build that pairs the
Q8_0 target with the official speculative draft.

All entries install the required F16 4x vision projector, default to an
8,192-token single-slot context, and keep thinking disabled so
transcriptions land in the response content. Q8_0 is the declaring entry;
the other two are selectable variants.

Tested text, table, and mixed Chinese/English page OCR through LocalAI
on an RTX 4090; the DSpark build reached about 0.96 draft acceptance. The
model's projector type is new in llama.cpp, so the entries need a backend
built from the current master pin; the latest release backend predates it.

Assisted-by: claude code:opus5.5
Signed-off-by: Caldalis <zyk_computer@163.com>

2026-11-03 11:00:19 +08:00

application

feat(addons): declare typed host capabilities (#13034 )

2026-11-02 23:50:40 +00:00

backend

feat(realtime): LFM3-Audio speech-to-speech on llama.cpp, remove liquid-audio (#12958 )

2026-10-29 22:06:41 +01:00

cli

feat(addons): declare typed host capabilities (#13034 )

2026-11-02 23:50:40 +00:00

clients

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