Add ${MODEL_ID} macro (#226)
The automatic ${MODEL_ID} macro includes the name of the model and can be used in Cmd and CmdStop.
This commit is contained in:
@@ -49,6 +49,7 @@ macros:
|
||||
# - required
|
||||
# - each key is the model's ID, used in API requests
|
||||
# - model settings have default values that are used if they are not defined here
|
||||
# - the model's ID is available in the ${MODEL_ID} macro, also available in macros defined above
|
||||
# - below are examples of the various settings a model can have:
|
||||
# - available model settings: env, cmd, cmdStop, proxy, aliases, checkEndpoint, ttl, unlisted
|
||||
models:
|
||||
@@ -148,12 +149,12 @@ models:
|
||||
cmd: llama-server --port ${PORT} -m Llama-3.2-1B-Instruct-Q4_K_M.gguf -ngl 0
|
||||
|
||||
# Docker example:
|
||||
# container run times like Docker and Podman can be used reliably with a
|
||||
# a combination of cmd and cmdStop.
|
||||
# container runtimes like Docker and Podman can be used reliably with
|
||||
# a combination of cmd, cmdStop, and ${MODEL_ID}
|
||||
"docker-llama":
|
||||
proxy: "http://127.0.0.1:${PORT}"
|
||||
cmd: |
|
||||
docker run --name dockertest
|
||||
docker run --name ${MODEL_ID}
|
||||
--init --rm -p ${PORT}:8080 -v /mnt/nvme/models:/models
|
||||
ghcr.io/ggml-org/llama.cpp:server
|
||||
--model '/models/Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf'
|
||||
@@ -167,7 +168,7 @@ models:
|
||||
# - on POSIX systems: a SIGTERM signal is sent
|
||||
# - on Windows, calls taskkill to stop the process
|
||||
# - processes have 5 seconds to shutdown until forceful termination is attempted
|
||||
cmdStop: docker stop dockertest
|
||||
cmdStop: docker stop ${MODEL_ID}
|
||||
|
||||
# groups: a dictionary of group settings
|
||||
# - optional, default: empty dictionary
|
||||
|
||||
@@ -237,7 +237,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
|
||||
|
||||
- name must fit the regex ^[a-zA-Z0-9_-]+$
|
||||
- names must be less than 64 characters (no reason, just cause)
|
||||
- name can not be any reserved macros: PORT
|
||||
- name can not be any reserved macros: PORT, MODEL_ID
|
||||
- macro values must be less than 1024 characters
|
||||
*/
|
||||
macroNameRegex := regexp.MustCompile(`^[a-zA-Z0-9_-]+$`)
|
||||
@@ -253,6 +253,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
|
||||
}
|
||||
switch macroName {
|
||||
case "PORT":
|
||||
case "MODEL_ID":
|
||||
return Config{}, fmt.Errorf("macro name '%s' is reserved and cannot be used", macroName)
|
||||
}
|
||||
}
|
||||
@@ -296,6 +297,11 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
|
||||
nextPort++
|
||||
}
|
||||
|
||||
if strings.Contains(modelConfig.Cmd, "${MODEL_ID}") || strings.Contains(modelConfig.CmdStop, "${MODEL_ID}") {
|
||||
modelConfig.Cmd = strings.ReplaceAll(modelConfig.Cmd, "${MODEL_ID}", modelId)
|
||||
modelConfig.CmdStop = strings.ReplaceAll(modelConfig.CmdStop, "${MODEL_ID}", modelId)
|
||||
}
|
||||
|
||||
// make sure there are no unknown macros that have not been replaced
|
||||
macroPattern := regexp.MustCompile(`\$\{([a-zA-Z0-9_-]+)\}`)
|
||||
fieldMap := map[string]string{
|
||||
|
||||
@@ -440,3 +440,44 @@ models:
|
||||
expectedCmd := "/user/llama.cpp/build/bin/llama-server --port 9990 --model /path/to/model.gguf -ngl 99"
|
||||
assert.Equal(t, expectedCmd, cmdStr, "Final command does not match expected structure")
|
||||
}
|
||||
|
||||
func TestConfig_MacroModelId(t *testing.T) {
|
||||
content := `
|
||||
startPort: 9000
|
||||
macros:
|
||||
"docker-llama": docker run --name ${MODEL_ID} -p ${PORT}:8080 docker_img
|
||||
"docker-stop": docker stop ${MODEL_ID}
|
||||
|
||||
models:
|
||||
model1:
|
||||
cmd: /path/to/server -p ${PORT} -hf ${MODEL_ID}
|
||||
|
||||
model2:
|
||||
cmd: ${docker-llama}
|
||||
cmdStop: ${docker-stop}
|
||||
|
||||
author/model:F16:
|
||||
cmd: /path/to/server -p ${PORT} -hf ${MODEL_ID}
|
||||
cmdStop: stop
|
||||
`
|
||||
|
||||
config, err := LoadConfigFromReader(strings.NewReader(content))
|
||||
assert.NoError(t, err)
|
||||
sanitizedCmd, err := SanitizeCommand(config.Models["model1"].Cmd)
|
||||
assert.NoError(t, err)
|
||||
assert.Equal(t, "/path/to/server -p 9001 -hf model1", strings.Join(sanitizedCmd, " "))
|
||||
|
||||
assert.Equal(t, "docker stop ${MODEL_ID}", config.Macros["docker-stop"])
|
||||
|
||||
sanitizedCmd2, err := SanitizeCommand(config.Models["model2"].Cmd)
|
||||
assert.NoError(t, err)
|
||||
assert.Equal(t, "docker run --name model2 -p 9002:8080 docker_img", strings.Join(sanitizedCmd2, " "))
|
||||
|
||||
sanitizedCmdStop, err := SanitizeCommand(config.Models["model2"].CmdStop)
|
||||
assert.NoError(t, err)
|
||||
assert.Equal(t, "docker stop model2", strings.Join(sanitizedCmdStop, " "))
|
||||
|
||||
sanitizedCmd3, err := SanitizeCommand(config.Models["author/model:F16"].Cmd)
|
||||
assert.NoError(t, err)
|
||||
assert.Equal(t, "/path/to/server -p 9000 -hf author/model:F16", strings.Join(sanitizedCmd3, " "))
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user