Run multiple LLM models on your machine and hot-swap between them as needed. llama-swap works with any OpenAI API-compatible server, giving you the flexibility to switch models without restarting your applications.
Built in Go for performance and simplicity, llama-swap has zero dependencies and is incredibly easy to set up. Get started in minutes - just one binary and one configuration file.
- ✅ Easy to deploy and configure: one binary, one configuration file. no external dependencies
- ✅ On-demand model switching
- ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabbyAPI, etc)
- future proof, upgrade your inference servers at any time.
- ✅ OpenAI API supported endpoints:
- ✅ llama-server (llama.cpp) supported endpoints
v1/rerank,v1/reranking,/rerank/infill- for code infilling/completion- for completion endpoint
- ✅ llama-swap API
- ✅ Customizable
llama-swap includes a real time web interface for monitoring logs and controlling models:
The Activity Page shows recent requests:
llama-swap can be installed in multiple ways
- Docker
- Homebrew (OSX and Linux)
- WinGet
- From release binaries
- From source
Docker Install (download images)
Nightly container images with llama-swap and llama-server are built for multiple platforms (cuda, vulkan, intel, etc).
$ docker pull ghcr.io/mostlygeek/llama-swap:cuda
# run with a custom configuration and models directory
$ docker run -it --rm --runtime nvidia -p 9292:8080 \
-v /path/to/models:/models \
-v /path/to/custom/config.yaml:/app/config.yaml \
ghcr.io/mostlygeek/llama-swap:cudamore examples
# pull latest images per platform
docker pull ghcr.io/mostlygeek/llama-swap:cpu
docker pull ghcr.io/mostlygeek/llama-swap:cuda
docker pull ghcr.io/mostlygeek/llama-swap:vulkan
docker pull ghcr.io/mostlygeek/llama-swap:intel
docker pull ghcr.io/mostlygeek/llama-swap:musa
# tagged llama-swap, platform and llama-server version images
docker pull ghcr.io/mostlygeek/llama-swap:v166-cuda-b6795
brew tap mostlygeek/llama-swap
brew install llama-swap
llama-swap --config path/to/config.yaml --listen localhost:8080Note
WinGet is maintained by community contributor Dvd-Znf (#327). It is not an official part of llama-swap.
# install
C:\> winget install llama-swap
# upgrade
C:\> winget upgrade llama-swapBinaries are available on the release page for Linux, Mac, Windows and FreeBSD.
- Building requires Go and Node.js (for UI).
git clone https://github.com/mostlygeek/llama-swap.gitmake clean all- look in the
build/subdirectory for the llama-swap binary
# minimum viable config.yaml
models:
model1:
cmd: llama-server --port ${PORT} --model /path/to/model.ggufThat's all you need to get started:
models- holds all model configurationsmodel1- the ID used in API callscmd- the command to run to start the server.${PORT}- an automatically assigned port number
Almost all configuration settings are optional and can be added one step at a time:
- Advanced features
groupsto run multiple models at oncehooksto run things on startupmacrosreusable snippets
- Model customization
ttlto automatically unload modelsaliasesto use familiar model names (e.g., "gpt-4o-mini")envto pass custom environment variables to inference serverscmdStopgracefully stop Docker/Podman containersuseModelNameto override model names sent to upstream servers${PORT}automatic port variables for dynamic port assignmentfiltersrewrite parts of requests before sending to the upstream server
See the configuration documentation for all options.
When a request is made to an OpenAI compatible endpoint, llama-swap will extract the model value and load the appropriate server configuration to serve it. If the wrong upstream server is running, it will be replaced with the correct one. This is where the "swap" part comes in. The upstream server is automatically swapped to handle the request correctly.
In the most basic configuration llama-swap handles one model at a time. For more advanced use cases, the groups feature allows multiple models to be loaded at the same time. You have complete control over how your system resources are used.
If you deploy llama-swap behind nginx, disable response buffering for streaming endpoints. By default, nginx buffers responses which breaks Server‑Sent Events (SSE) and streaming chat completion. (#236)
Recommended nginx configuration snippets:
# SSE for UI events/logs
location /api/events {
proxy_pass http://your-llama-swap-backend;
proxy_buffering off;
proxy_cache off;
}
# Streaming chat completions (stream=true)
location /v1/chat/completions {
proxy_pass http://your-llama-swap-backend;
proxy_buffering off;
proxy_cache off;
}As a safeguard, llama-swap also sets X-Accel-Buffering: no on SSE responses. However, explicitly disabling proxy_buffering at your reverse proxy is still recommended for reliable streaming behavior.
# sends up to the last 10KB of logs
curl http://host/logs'
# streams combined logs
curl -Ns 'http://host/logs/stream'
# just llama-swap's logs
curl -Ns 'http://host/logs/stream/proxy'
# just upstream's logs
curl -Ns 'http://host/logs/stream/upstream'
# stream and filter logs with linux pipes
curl -Ns http://host/logs/stream | grep 'eval time'
# skips history and just streams new log entries
curl -Ns 'http://host/logs/stream?no-history'Any OpenAI compatible server would work. llama-swap was originally designed for llama-server and it is the best supported.
For Python based inference servers like vllm or tabbyAPI it is recommended to run them via podman or docker. This provides clean environment isolation as well as responding correctly to SIGTERM signals for proper shutdown.
Note
⭐️ Star this project to help others discover it!
