Real-models implementation: multimodal ingestion, Context Cartridge memory, sparse + Qwen embedding retrieval, Cache Fabric, Qwen runtime adapters, verifier contracts, Visual HashHop proofs, BF16 LoRA fine-tuning, and a local dashboard. Verified by a 15-check PRD proof suite on the live model.
19 lines
423 B
YAML
19 lines
423 B
YAML
services:
|
|
ely-eye:
|
|
build: .
|
|
ports:
|
|
- "8765:8765"
|
|
volumes:
|
|
- ./.ely_eye:/data/ely-eye
|
|
environment:
|
|
ELY_EYE_HOME: /data/ely-eye
|
|
ELY_EYE_RUNTIME_BACKEND: sglang
|
|
ELY_EYE_SGLANG_BASE_URL: http://host.docker.internal:8000/v1
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|