* proxy/config: add model level macros
Add macros to model configuration. Model macros override macros that are
defined at the global configuration level. They follow the same naming
and value rules as the global macros.
* proxy/config: fix bug with macro reserved name checking
The PORT reserved name was not properly checked
* proxy/config: add tests around model.filters.stripParams
- add check that model.filters.stripParams has no invalid macros
- renamed strip_params to stripParams for camel case consistency
- add legacy code compatibility so model.filters.strip_params continues to work
* proxy/config: add duplicate removal to model.filters.stripParams
* clean up some doc nits
Add barebones but working implementation of model preload
* add config test for Preload hook
* improve TestProxyManager_StartupHooks
* docs for new hook configuration
* add a .dev to .gitignore
llama-swap can strip specific keys in JSON requests. This is useful for removing the ability for clients to set sampling parameters like temperature, top_k, top_p, etc.
This change revamps the internal logging architecture to be more flexible and descriptive. Previously all logs from both llama-swap and upstream services were mixed together. This makes it harder to troubleshoot and identify problems. This PR adds these new endpoints:
- `/logs/stream/proxy` - just llama-swap's logs
- `/logs/stream/upstream` - stdout output from the upstream server
* remove catch-all route to upstream proxy (it was broken anyways)
* add /upstream/:model_id to swap and route to upstream path
* add /upstream HTML endpoint and unlisted option
* add /upstream endpoint to show a list of available models
* add `unlisted` configuration option to omit a model from /v1/models and /upstream lists
* add favicon.ico
Refactor code to support starting of multiple back end llama.cpp servers. This functionality is exposed as `profiles` to create a simple configuration format.
Changes:
* refactor proxy tests to get ready for multi-process support
* update proxy/ProxyManager to support multiple processes (#7)
* Add support for Groups in configuration
* improve handling of Model alias configs
* implement multi-model swapping
* improve code clarity for swapModel
* improve docs, rename groups to profiles in config
* 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)
llama-swap only waited a maximum of 5 seconds for an upstream
HTTP server to be available. If it took longer than that it will error
out the request. Now it will wait up to the configured healthCheckTimeout
or the upstream process unexpectedly exits.
Replace previously hardcoded value for `/health` to check when the
server became ready to serve traffic. With this the server can support
any server that provides an an OpenAI compatible inference endpoint.
