Spaces:

Duplicated from TamisAI/inference-lamp-api

TamisAI
/

inference-api-g1

Sleeping

App Files Files Community

inference-api-g1

Ctrl+K

Ctrl+K

1 contributor

History: 79 commits

alexfremont's picture

Update model lookup to use filename instead of ID in get_model function

9f9c6d5 3 days ago

api
Improve model unloading with explicit GPU memory cleanup and CUDA cache clearing 4 days ago
architecture
Refactor API architecture with modular design and database integration 8 days ago
config
Add model management endpoints and database fetch functionality 6 days ago
db
Disable prepared statement cache for pgbouncer compatibility 4 days ago
models
Update model lookup to use filename instead of ID in get_model function 3 days ago
schemas
Refactor API architecture with modular design and database integration 8 days ago
steps
Refactor API architecture with modular design and database integration 8 days ago
utils
Add timestamps to memory monitoring logs and display outputs 4 days ago
.gitattributes

1.52 kB

initial commit 7 months ago
.gitignore

347 Bytes

first commit for API 7 months ago
Dockerfile

832 Bytes

Merge Gradio UI into FastAPI app and standardize port to 7860 8 days ago
README.md

276 Bytes

Update README.md 16 days ago
docker-compose.yml

205 Bytes

Merge Gradio UI into FastAPI app and standardize port to 7860 8 days ago
main.py

8.75 kB

Remove periodic memory status updates and related helper function 4 days ago
requirements.txt

299 Bytes

Add system monitoring features and memory usage tracking for loaded models 4 days ago