mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-20 21:28:16 -04:00
localai-org-maint-botandEttore Di Giacinto
3d63736c56
Add a video_lora_dir model option that passes lora_dir as a model-load extra to the vllm.cpp engine. The engine uses it to resolve <lora:name:strength> prompt tags at request time, loading the safetensors LoRA factors and applying per-request deltas without touching base weights (row ROAD-V1-LORA-RUNTIME). This is distinct from the existing load-time lora_path/lora_strength fusion (ROAD-V1-DIT-LORA), which bakes deltas into the DiT weights at load. Both mechanisms coexist: load-time adapters are always active, while prompt-tag adapters are selected per request. The prompt passes through verbatim — the engine strips the tags internally. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: AGENT:regolo/glm5.2 [maki] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>