This is a huge backend change that essentially started with rewriting
the concurrency handling for processes and blew up to a refactor of the
entire application. In short these are the improvements:
**Better state and life cycle management:**
Life cycle management of processes has always been the trickiest part of
the code. Juggling mutex locks between multiple locations to reduce race
conditions was complex. Too complex for my feeble brain to build a
simple mental model around as llama-swap gained more features. All of
that has been refactored. Most of the locks are gone, replaced with a
single run() that owns all state changes. There is one place to start
from now to understand and extend routing logic.
The improved life cycle management makes it easier to implement more
complex swap optimization strategies in the future like #727.
**Collation of requests:**
llama-swap previously handled requests and swapping in the order they
came in. For example requests for models in this order ABCABC would
result in 5 swaps. Now those requests are handled in this order AABBCC.
The result is less time waiting for swap under a high churn request
queue. This fixes#588#612.
A possible future enhancement is to support a starvation parameter so
swap can be forced when models have been waiting too long.
**Shared base implementation for groups and swap matrix:**
During the refactor it became clear that much of the swapping logic was
shared between these two implementations. That is not surprising
considering the swap matrix was added many moons after groups. Now they
share a common base and their specific swap strategies are implemented
into the swapPlanner interface.
Requests for bespoke or specific swapping scenarios is a common theme in
the issues. Now users can implement whatever bespoke and weird swapping
strategy they want in their own fork. Just ask your agent of choice to
implement swapPlanner. I'll still remaining more conservative on what
actually lands in core llama-swap and will continue to evaluate PRs if
the changes is good for everyone or just one specific use case.
**AI / Agentic Disclosure:**
I paid very close attention to the low level swap concurrency design and
implementation. It's important to keep that essential part reliable,
boring and no surprises. Backwards compatibility was also maintained,
even the one way non-exclusive group model loading behaviour that people
have rightly pointed out be a weird design decision.
With the underlying swap core done the web server, api and UI sitting on
top were largely ported over with Claude Code and Opus 4.7 in multiple
phases. If you're curious I kept the changes in docs/newrouter-todo.md.
I did several passes to make sure things weren't left behind.
However, even frontier LLMs at the time of this PR still make small
decisions that don't make a lot of sense. They get shit wrong all the
time, just in small subtle way.
That said, there's likely to be some new bugs introduced with this
massive refactor. I'm fairly confident that there's no major
architectural flaws that would cause goal seeking agents to make dumb,
ugly code decisions.
For a little while the legacy llama-swap will be available under
cmd/legacy/llama-swap. The plan is to eventually delete that entry point
as well as the proxy package.
On a bit of a personal note, this PR is exciting and a bit sad for me. I
hand wrote much of the original code and this PR ultimately replaces
much of it. While the old code served as a good reference for the agent
to implement the new stuff it still a bit sad to eventually delete it
all.
- inference handles to store an activity record for all inference endpoints
- add path, status code, and content type to Activities page
- toggle on/off columns no Activities page
- add configurable capture level for inference endpoints so large binary blobs are not stored in memory
- store captures in compressed binary format
Add proxy routes for stable-diffusion.cpp's /sdapi/v1/txt2img,
/sdapi/v1/img2img, and /sdapi/v1/loras endpoints. POST endpoints
use proxyInferenceHandler (model in JSON body), GET /loras uses
proxyGETModelHandler (model in query param).
Update the image playground with a dual-mode UI supporting both
OpenAI and SDAPI backends. In SDAPI mode, loras are fetched first
to prime the server-side cache, and all txt2img parameters are
exposed (negative prompt, steps, cfg_scale, seed, batch_size,
clip_skip, sampler, scheduler, lora selection with multipliers).
- Add 3 sdapi route registrations in proxymanager.go
- Add sdApi.ts client with generateSdImage and fetchSdLoras
- Add SDAPI types (SdApiTxt2ImgRequest, SdApiResponse, etc.)
- Add /sdapi to vite dev proxy config
- Add backend tests for sdapi routing
- Support batch image display in gallery grid
https://claude.ai/code/session_0186MGX6NXdHVBTv2KH45fqn
---------
Co-authored-by: Claude <noreply@anthropic.com>
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
Replace the legacy React UI with the new Svelte-based one. Introduce a Playground in the UI to quickly test out text, image, text to speech and speech to text models behind llama-swap.
Key Changes
New Svelte UI (ui-svelte/)
- Multi-tab Playground with Chat, Image Generation, Audio Transcription, and Speech interfaces
- Chat: message editing/regeneration, markdown rendering with LaTeX math support, image attachments, code syntax highlighting
- Image: size selector, download/fullscreen viewing
- Audio: transcription with peer support
- Speech: voice caching with manual refresh, download button
- Responsive mobile layout with collapsible navigation
- XSS fixes and accessibility improvements
Proxy Improvements
- Add gzip/brotli compression for UI static assets (proxy/ui_compress.go)
- Add GET /v1/audio/voices?model={model} endpoint for voice listing
- Add peer support for /v1/audio/transcriptions
Extend the /running endpoint to return more details about running
processes beyond just model and state.
- add cmd field to show the command being executed
- add proxy field to show the proxy URL
- add ttl (UnloadAfter) for automatic unloading configuration
- add name and description for model metadata
- update tests to verify new fields are returned correctly
fixes#471
This unifies the filtering capabilities for models and peers
- stripParams: removes params in the request
- setParams: sets params in the request
fixes#453
Fixes#444 where the UI with api keys did not work. The choice to use
http basic authorization is for simple, automatic browser support. No
changes to the UI were necessary. Just use an API key as the password,
no user name is required.
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
A {model_id} containing a forward slash trips up gin's path param
parsing. This updates /logs/stream to work like /upstream where the
model_id is built up in parts and searched for in the configuration.
Updates #421
- Add /api/version endpoint to ProxyManager that returns build date, commit hash, and version
- Implement SetVersion method to configure version info in ProxyManager
- Add version info fetching to APIProvider and display in ConnectionStatus component
- Include version info in UI context and update dependencies
- Add tests for version endpoint functionality
* proxy: refactor metrics recording
- remove metrics_middleware.go as this wrapper is no longer needed. This
also eliminiates double body parsing for the modelID
- move metrics parsing to be part of MetricsMonitor
- refactor how metrics are recording in ProxyManager
- add MetricsMonitor tests
- improve mem efficiency of processStreamingResponse
- add benchmarks for MetricsMonitor.addMetrics
- proxy: refactor MetricsMonitor to be more safe handling errors
* Refactor to use httputil.ReverseProxy
Refactor manual HTTP proxying logic in Process.ProxyRequest to use the standard
library's httputil.ReverseProxy.
* Refactor TestProcess_ForceStopWithKill test
Update to handle behavior with httputil.ReverseProxy.
* Fix gin interface conversion panic
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: create config package and migrate configuration
The configuration is become more complex as llama-swap adds more
advanced features. This commit moves config to its own package so it can
be developed independently of the proxy package.
Additionally, enforcing a public API for a configuration will allow
downstream usage to be more decoupled.
This adds a new API endpoint, /api/models/unload/*model, that unloads a single model. In the UI when a model is in a ReadyState it will have a new button to unload it.
Fixes#312
* Fix nginx proxy buffering for streaming endpoints
- Add X-Accel-Buffering: no header to SSE endpoints (/api/events, /logs/stream)
- Add X-Accel-Buffering: no header to proxied text/event-stream responses
- Add nginx reverse proxy configuration section to README
- Add tests for X-Accel-Buffering header on streaming endpoints
Fixes#236
* Fix goroutine cleanup in streaming endpoints test
Add context cancellation to TestProxyManager_StreamingEndpointsReturnNoBufferingHeader
to ensure the goroutine is properly cleaned up when the test completes.
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
Fix#198
- use llama-server's `timings` info if available in response body
- send "-1" for token/sec when not able to accurately calculate
performance
- optimize streaming body search for metrics information
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.
Sometimes upstreams can accept HTTP but never respond causing requests
to build up waiting for a response. This can block Process.Stop() as
that waits for inflight requests to finish. This change refactors the
code to not wait when attempting to shutdown the process.
Groups allows more control over swapping behaviour when a model is requested. The new groups feature provides three ways to control swapping: within the group, swapping out other groups or keep the models in the group loaded persistently (never swapped out).
Closes#96, #99 and #106.
Changes to CORS functionality:
- `Access-Control-Allow-Origin: *` is set for all requests
- for pre-flight OPTIONS requests
- specify methods: `Access-Control-Allow-Methods: GET, POST, PUT, PATCH, DELETE, OPTIONS`
- if the client sent `Access-Control-Request-Headers` then echo back the same value in `Access-Control-Allow-Headers`. If no `Access-Control-Request-Headers` were sent, then send back a default set
- set `Access-Control-Max-Age: 86400` to that may improve performance
- Add CORS tests to the proxy-manager
* Adds an endpoint '/running' that returns either an empty JSON object if no model has been loaded so far, or the last model loaded (model key) and it's current state (state key). Possible state values are: stopped, starting, ready and stopping.
* Improves the `/running` endpoint by allowing multiple entries under the `running` key within the JSON response.
Refactors the `/running` method name (listRunningProcessesHandler).
Removes the unlisted filter implementation.
* Adds tests for:
- no model loaded
- one model loaded
- multiple models loaded
* Adds simple comments.
* Simplified code structure as per 250313 comments on PR #65.
---------
Co-authored-by: FGDumitru|B <xelotx@gmail.com>
The profile slug in a model name, `profile:model`, is specific to
llama-swap. This strips `profile:` out of the model name request so
upstreams that expect just `model` work and do not require knowing about
the profile slug.
Introduce `Process.Shutdown()` and `ProxyManager.Shutdown()`. These two function required a lot of internal process state management refactoring. A key benefit is that `Process.start()` is now interruptable. When `Shutdown()` is called it will break the long health check loop.
State management within Process is also improved. Added `starting`, `stopping` and `shutdown` states. Additionally, introduced a simple finite state machine to manage transitions.
A panic occurs when a request for an invalid profile:model pair is made.
The edge case is that the profile exists and the model exists but they're
not configured as a pair.
This adds an additional check to make sure the profile:model pair is
valid before attempting to swap the model.
Benson Wong
Wim Vander Schelden
Benson Wong
Ryan Steed
David Wen Riccardi-Zhu
Artur Podsiadły
Yandrik
Ben Greene
g2mt
Sam
Florin-Gabriel Dumitru