Add configurable HTTP timeout settings to both models and peers to support installations that requires longer timeouts than the current hardcoded defaults.
Closes#618
Add a new configuration parameter globalTTL that all models will
inherit. The default value is 0 which matches the currently
functionality to never automatically unload a model.
The model.ttl's default has changed to -1, which means use the global
TTL value. Any model.ttl >=0 is now value with 0 meaning never unload.
This allows a model to override a globalTTL > 0 and be configured to
never unload.
Fixes#459Closes#512
Add setParamsByID filter that applies different request parameters based
on the requested model ID, enabling per-alias behaviour for a single
loaded model.
- add SetParamsByID field to Filters struct and SanitizedSetParamsByID
method
- substitute ${MODEL_ID} and other macros in setParamsByID keys and
values
- validate no unknown macros remain in keys or values after substitution
- apply setParamsByID in proxyInferenceHandler after setParams (can
override it)
- update config-schema.json with setParamsByID definition
- update UI to show aliases and make them selectable in the Playground
closes#534
Add saving request and response headers and bodies that go through
llama-swap in memory.
- captureBuffer added to configuration. Captures are enabled by default.
- 5MB of memory is allocated for req/response captures in a ring buffer.
Setting captureBuffer to 0 will disable captures.
- UI elements to view captured data added to Activity page. Includes
some
QOL features like json formatting and recombining SSE chat streams
- capture saving is done at the byte level and has minimal impact on
llama-swap performance
Fixes#464
Ref #503
* config: support environment variable macros in peer apiKeys
Add ${env.VAR_NAME} substitution for peer apiKey fields, consistent
with existing env macro support for model fields and global apiKeys.
- Add env macro substitution for peers.{name}.apiKey in LoadConfigFromReader
- Add tests for peer apiKey env substitution
- Update config.example.yaml to show env macro usage
* config: support macros in peer apiKey and filters
Extend macro substitution to peer configuration fields:
- peers.{name}.apiKey supports both global macros and env macros
- peers.{name}.filters.stripParams supports both macro types
- peers.{name}.filters.setParams supports both macro types
Also renamed validateMetadataForUnknownMacros to validateNestedForUnknownMacros
for reuse across model metadata and peer filters validation.
* config: add environment variable macros
Add support for ${env.VAR_NAME} syntax to pull values from system
environment variables during config loading.
- env macros processed before regular macros (allows macros to reference env vars)
- works in cmd, cmdStop, proxy, checkEndpoint, filters.stripParams, metadata
- returns error if env var is not set
- add comprehensive tests
fixes#462
* docs: add env macro example to config.example.yaml
This unifies the filtering capabilities for models and peers
- stripParams: removes params in the request
- setParams: sets params in the request
fixes#453
This PR allows a single llama-swap to be the central proxy for models served by other inference servers. The peer servers can be another llama-swap or any API that supports the /v1/* inference endpoint.
Updates: #433, #299Closes: #296
Add configuration support for api keys that are enforced by llama-swap. Keys are stripped before sending them to upstream servers.
Updates: #433, #50 and #251
The new logToStdout option controls what is logged to stdout. The
default has been changed to just the proxy logs, which contain swap and
http request logs.
There are four supported settings: none, proxy, upstream, both. The
"both" setting is the legacy setting where everything was spewed to
stdout.
introduces a new configuration option logTimeFormat that allows customizing the timestamp in log messages using golang's built in time format constants. The default remains no timestamp.
Swapping models can take a long time and leave a lot of silence while the model is loading. Rather than silently load the model in the background, this PR allows llama-swap to send status updates in the reasoning_content of a streaming chat response.
Fixes: #366
Add full macro-in-macro support so any user defined macro can contain another one as long as it was previously declared in the configuration file.
Fixes#336
Supercedes #335
Changes:
- add Metadata key to ModelConfig
- include metadata in /v1/models under meta.llamaswap key
- add recursive macro substitution into Metadata
- change macros at global and model level to be any scalar type
Note:
This is the first mostly AI generated change to llama-swap. See #333 for notes about the workflow and approach to AI going forward.
* 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.
Benson Wong