Fixed readme, removed error for --help

README.md

@@ -85,7 +85,7 @@ API responses contains a subset of the fields provided by the OpenAI API.
 For more details see the <a href="https://docs.vllm.ai/en/stable/getting_started/quickstart.html#openai-completions-api-with-vllm">vLLM documentation</a>
 
 ## Command line parameters
-- `config`: the path to a yaml configuration file 
+- `config`: the path to a yaml configuration file that can contain the simulator's command line parameters. If a parameter is defined in both the config file and the command line, the command line value overwrites the configuration file value. An example configuration file can be found at `manifests/config.yaml`
 - `port`: the port the simulator listents on, default is 8000
 - `model`: the currently 'loaded' model, mandatory
 - `served-model-name`: model names exposed by the API (a list of space-separated strings)
@@ -134,7 +134,7 @@ The following environment variables can be used to change the image tag: `REGIST
 ### Running
 To run the vLLM Simulator image under Docker, run:
 ```bash
-docker run --rm --publish 8000:8000 ghcr.io/llm-d/llm-d-inference-sim:dev  --port 8000 --model "Qwen/Qwen2.5-1.5B-Instruct" --lora "tweet-summary-0,tweet-summary-1"
+docker run --rm --publish 8000:8000 ghcr.io/llm-d/llm-d-inference-sim:dev  --port 8000 --model "Qwen/Qwen2.5-1.5B-Instruct"  --lora-modules '{"name":"tweet-summary-0"}' '{"name":"tweet-summary-1"}'
 ```
 **Note:** To run the vLLM Simulator with the latest release version, in the above docker command replace `dev` with the current release which can be found on [GitHub](https://github.com/llm-d/llm-d-inference-sim/pkgs/container/llm-d-inference-sim).
 

pkg/llm-d-inference-sim/simulator.go

@@ -158,7 +158,7 @@ func (s *VllmSimulator) parseCommandParamsAndLoadConfig() error {
 
 	// These values were manually parsed above in getParamValueFromArgs, we leave this in order to get these flags in --help
 	var dummyString string
-	f.StringVar(&dummyString, "config", "", "The configuration file")
+	f.StringVar(&dummyString, "config", "", "The path to a yaml configuration file. The command line values overwrite the configuration file values")
 	var dummyMultiString multiString
 	f.Var(&dummyMultiString, "served-model-name", "Model names exposed by the API (a list of space-separated strings)")
 	f.Var(&dummyMultiString, "lora-modules", "List of LoRA adapters (a list of space-separated JSON strings)")
@@ -171,6 +171,10 @@ func (s *VllmSimulator) parseCommandParamsAndLoadConfig() error {
 	f.AddGoFlagSet(flagSet)
 
 	if err := f.Parse(os.Args[1:]); err != nil {
+		if err == pflag.ErrHelp {
+			// --help - exit without printing an error message
+			os.Exit(0)
+		}
 		return err
 	}