Ettore Di Giacinto b40843cf62 feat(dllm): image input through the backend (multimodal C-ABI) ...

Routes PredictOptions.Images (raw base64, the core convention) through
dllm.cpp's probed multimodal entry points as data: URIs; the gemma4
renderer appends one engine-side <image> marker per image after the
last user message (llama.cpp attachment convention; the template's
content-parts branch is unreachable through the flattened pb shape).
The engine expands markers to boi + soft*n + eoi and splices the
vision-tower embeddings. Older libdllm.so without the mm symbols fails
with an actionable error (Dlsym probe). DLLM_VERSION pin bumped to the
engine's vision-capable commit.

Assisted-by: Claude Code (Fable 5)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-06-12 00:41:04 +00:00

..

e2e

…

e2e-aio

…

e2e-backends

feat(dllm): image input through the backend (multimodal C-ABI)

2026-06-12 00:41:04 +00:00

e2e-ui

…

fixtures

…

integration

…