add support for automatically unloading a model (#10) (#14)

* Make starting upstream process on-demand (#10)
* Add automatic unload of model after TTL is reached
* add `ttl` configuration parameter to models in seconds, default is 0 (never unload)
This commit is contained in:
Benson Wong
2024-11-19 16:32:51 -08:00
committed by GitHub
parent ba39ed4c18
commit 533162ce6a
8 changed files with 149 additions and 54 deletions

View File

@@ -10,6 +10,9 @@ clean:
rm -rf $(BUILD_DIR)
test:
go test -short -v ./proxy
test-all:
go test -v ./proxy
# Build OSX binary