feat: re-enable multimodal vision ViT projector offloaded to 12GB RTX 2060 (CUDA2)
This commit is contained in:
@@ -13,6 +13,9 @@ export NCCL_PROTO=SIMPLE
|
||||
|
||||
exec /opt/llama.cpp-xrip/build-nccl/bin/llama-server \
|
||||
-m /opt/models/gguf/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
|
||||
--mmproj /opt/models/gguf/mmproj-Qwen3.8-27B-Uncensored-f16.gguf \
|
||||
--mmproj-device CUDA2 \
|
||||
--image-min-tokens 1024 \
|
||||
--spec-type draft-mtp \
|
||||
--spec-draft-n-max 2 \
|
||||
--numa split \
|
||||
|
||||
Reference in New Issue
Block a user