Add /upstream endpoint (#30)

* 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

README.md

@@ -8,7 +8,7 @@ llama-swap is an OpenAI API compatible server that gives you complete control ov
 Features:
 
 - ✅ Easy to deploy: single binary with no dependencies
-- ✅ Single yaml configuration file
+- ✅ Easy to config: single yaml file
 - ✅ On-demand model switching
 - ✅ Full control over server settings per model
 - ✅ OpenAI API support (`v1/completions` and `v1/chat/completions`)
@@ -16,7 +16,8 @@ Features:
 - ✅ Run multiple models at once with `profiles`
 - ✅ Remote log monitoring at `/log`
 - ✅ Automatic unloading of models from GPUs after timeout
-- ✅ Use any local server that provides an OpenAI compatible API (llama.cpp, vllm, tabblyAPI, etc)
+- ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabblyAPI, etc)
+- ✅ Direct access to proxied upstream HTTP server via `/upstream/:model_id`
 
 ## Releases
 
@@ -73,6 +74,12 @@ models:
       --model path/to/Qwen2.5-1.5B-Instruct-Q4_K_M.gguf
     proxy: http://127.0.0.1:8999
 
+  # unlisted models do not show up in /v1/models or /upstream lists
+  # but they can still be requested as normal
+  "qwen-unlisted":
+    cmd: llama-server --port 9999 -m Llama-3.2-1B-Instruct-Q4_K_M.gguf -ngl 0
+    unlisted: true
+
 # profiles make it easy to managing multi model (and gpu) configurations.
 #
 # Tips: