docs: Add documentation for verbosity flag in `dynamo-run` (#1353)

docs/guides/dynamo_run.md

@@ -41,13 +41,20 @@ It supports these engines: mistralrs, llamacpp, sglang, vllm, and tensorrt-llm.
 
 Usage:
 ```
-dynamo-run in=[http|text|dyn://<path>|batch:<folder>] out=echo_core|echo_full|mistralrs|llamacpp|sglang|vllm|dyn [--http-port 8080] [--model-path <path>] [--model-name <served-model-name>] [--model-config <hf-repo>] [--tensor-parallel-size=1] [--context-length=N] [--num-nodes=1] [--node-rank=0] [--leader-addr=127.0.0.1:9876] [--base-gpu-id=0] [--extra-engine-args=args.json] [--router-mode random|round-robin|kv] [--kv-overlap-score-weight=2.0] [--kv-gpu-cache-usage-weight=1.0] [--kv-waiting-requests-weight=1.0]
+dynamo-run in=[http|text|dyn://<path>|batch:<folder>] out=echo_core|echo_full|mistralrs|llamacpp|sglang|vllm|dyn [--http-port 8080] [--model-path <path>] [--model-name <served-model-name>] [--model-config <hf-repo>] [--tensor-parallel-size=1] [--context-length=N] [--num-nodes=1] [--node-rank=0] [--leader-addr=127.0.0.1:9876] [--base-gpu-id=0] [--extra-engine-args=args.json] [--router-mode random|round-robin|kv] [--kv-overlap-score-weight=2.0] [--kv-gpu-cache-usage-weight=1.0] [--kv-waiting-requests-weight=1.0] [--verbosity (-v|-vv)]
 ```
 
 Example: `dynamo run Qwen/Qwen3-0.6B`
 
 Set the environment variable `DYN_LOG` to adjust the logging level; for example, `export DYN_LOG=debug`. It has the same syntax as `RUST_LOG`.
 
+To adjust verbosity, use `-v` to enable debug logging or `-vv` to enable full trace logging. For example:
+
+```bash
+dynamo-run in=http out=mistralrs -v  # enables debug logging
+dynamo-run in=text out=llamacpp -vv  # enables full trace logging
+```
+
 ## Quickstart with pip and vllm
 
 If you used `pip` to install `dynamo`, you have the `dynamo-run` binary pre-installed with the `vllm` engine. You must be in a virtual environment with vllm installed to use this engine. To compile from source, see [Full usage details](#full-usage-details) below.

launch/dynamo-run/src/main.rs

@@ -23,6 +23,11 @@ use dynamo_runtime::logging;
 const HELP: &str = r#"
 dynamo-run is a single binary that wires together the various inputs (http, text, network) and workers (network, engine), that runs the services. It is the simplest way to use dynamo locally.
 
+Verbosity:
+- -v enables debug logs
+- -vv enables full trace logs
+- Default is info level logging
+
 Example:
 - cargo build --features cuda -p dynamo-run
 - cd target/debug
@@ -30,7 +35,7 @@ Example:
 - OR: ./dynamo-run /data/models/Llama-3.2-1B-Instruct-Q4_K_M.gguf
 "#;
 
-const USAGE: &str = "USAGE: dynamo-run in=[http|text|dyn://<path>|batch:<folder>] out=ENGINE_LIST|dyn [--http-port 8080] [--model-path <path>] [--model-name <served-model-name>] [--model-config <hf-repo>] [--tensor-parallel-size=1] [--context-length=N] [--kv-cache-block-size=16] [--num-nodes=1] [--node-rank=0] [--leader-addr=127.0.0.1:9876] [--base-gpu-id=0] [--extra-engine-args=args.json] [--router-mode random|round-robin|kv] [--kv-overlap-score-weight=2.0] [--kv-gpu-cache-usage-weight=1.0] [--kv-waiting-requests-weight=1.0]";
+const USAGE: &str = "USAGE: dynamo-run in=[http|text|dyn://<path>|batch:<folder>] out=ENGINE_LIST|dyn [--http-port 8080] [--model-path <path>] [--model-name <served-model-name>] [--model-config <hf-repo>] [--tensor-parallel-size=1] [--context-length=N] [--kv-cache-block-size=16] [--num-nodes=1] [--node-rank=0] [--leader-addr=127.0.0.1:9876] [--base-gpu-id=0] [--extra-engine-args=args.json] [--router-mode random|round-robin|kv] [--kv-overlap-score-weight=2.0] [--kv-gpu-cache-usage-weight=1.0] [--kv-waiting-requests-weight=1.0] [--verbosity (-v|-vv)]";
 
 fn main() -> anyhow::Result<()> {
     // Set log level based on verbosity flag