docs/examples/llm_deployment.md (1)

95-118: Remove duplicated explanatory block

The paragraph from lines 97-107 is repeated verbatim at 108-118, making the Note twice as long and tripping readers.

  Building a vLLM docker image for ARM machines currently involves building vLLM from source, which is known to have performance issues to require extensive system RAM; see [vLLM Issue 8878](https://github.com/vllm-project/vllm/issues/8878).
@@
-When vLLM has pre-built ARM wheels published, this process can be improved.
-
-You can tune the number of parallel build jobs for building VLLM from source
-on ARM based on your available cores and system RAM with `VLLM_MAX_JOBS`.
-
-For example, on an ARM machine with low system resources:
-`./container/build.sh --framework vllm --platform linux/arm64 --build-arg VLLM_MAX_JOBS=2`
-
-For example, on a GB200 which has very high CPU cores and memory resource:
-`./container/build.sh --framework vllm --platform linux/arm64 --build-arg VLLM_MAX_JOBS=64`
-
-When vLLM has pre-built ARM wheels published, this process can be improved.
+When vLLM ships pre-built ARM wheels, this process will simplify.

docs/guides/dynamo_deploy/quickstart.md (3)

4-4: Prefer “can install” over “could install” for clarity

“Could” reads like a hypothetical. “Can install” (or “You can install”) is the common idiom for instructions.

-You could install from [Published Artifacts](#1-installing-from-published-artifacts) or [Source](#2-installing-from-source)
+You can install from [Published Artifacts](#1-installing-from-published-artifacts) or [Source](#2-installing-from-source)

---

139-151: Streamline the destination-selection snippet

1. Capitalise “Kubernetes” for consistency.
2. Consider using a list instead of free-form prose to make the two alternatives visually parallel and easier to scan.
3. The current layout omits language identifiers on the second code block – stick with ```bash for both.

-Pick your deployment destination.
-
-If local
-
-```bash
-export DYNAMO_CLOUD=http://localhost:8080
-```
-
-If kubernetes
-```bash
-export DYNAMO_CLOUD=https://dynamo-cloud.nvidia.com
-```
+Pick your deployment destination:
+
+- **Local**
+  ```bash
+  export DYNAMO_CLOUD=http://localhost:8080
+  ```
+
+- **Kubernetes**
+  ```bash
+  export DYNAMO_CLOUD=https://dynamo-cloud.nvidia.com
+  ```

---

161-168: Fix grammar & tighten cross-references

• “Example are stored” → “Examples are stored”.
• Links already imply folder and guide; no need for extra words.

-Example are stored in the [Examples Folder](../../examples/README.md)
-
-Follow the most basic ones in the dedicated guides below:
-
-[Hello World](../../examples/hello_world.md)
-
-[LLM](../../examples/llm_deployment.md)
+Examples live in the [examples directory](../../examples/README.md).
+
+Quick-start guides:
+- [Hello World](../../examples/hello_world.md)
+- [LLM](../../examples/llm_deployment.md)

docs/examples/llm_deployment.md (1)

150-152: Minor casing correction

“Planner” sentence is great; just lower-case the flag to match CLI conventions (--planner.no-operation=false) unless the binary really expects uppercase P.

docs/guides/dynamo_deploy/README.md (2)

18-24: Tighten wording and fix “Prior to”

Replace “Prior to” with “Before” (Wordiness). Also, sentence 20-24 is long; splitting improves readability.

-We expect users to deploy their inference graphs using CRDs or helm charts.
-
-Prior to deploying an inference graph the user should deploy the Dynamo Cloud Platform.
-Dynamo Cloud acts as an orchestration layer between the end user and Kubernetes, handling the complexity of deploying your graphs for you. This is a one-time action, only necessary the first time you deploy a DynamoGraph.
+We expect users to deploy inference graphs via CRDs or Helm charts.
+
+Before deploying a graph, install the Dynamo Cloud Platform.  
+Dynamo Cloud is an orchestration layer that hides Kubernetes complexity and only needs to be installed once for a given cluster.

---

26-30: Avoid heading numbers inside Markdown heading text

Markdown headings with “# 1.” & “# 2.” render oddly and hurt anchor stability. Prefer plain headings or an ordered list.

-# 1. Please follow [Installing Dynamo Cloud](./dynamo_cloud.md) for steps to install.
-For details about the Dynamo Cloud Platform, see the [Dynamo Operator Guide](dynamo_operator.md)
-
-# 2. Follow [Examples](../../examples/README.md) to see how you can deploy your Inference Graphs.
+## 1  Install Dynamo Cloud  
+See [Installing Dynamo Cloud](./dynamo_cloud.md). For operator details, consult the [Dynamo Operator Guide](dynamo_operator.md).
+
+## 2  Deploy an inference graph  
+Browse the [examples](../../examples/README.md) to get started.

docs/guides/dynamo_deploy/dynamo_cloud.md (1)

56-66: Unclear one-time image instructions

The block mixes “pre-built image” vs “build & push your own” but uses the same variable (DYNAMO_IMAGE) later. Consider explicitly stating which path readers should choose and when to set DYNAMO_IMAGE.

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

Learnt from: PeaBrane
PR: ai-dynamo/dynamo#1409
File: examples/router_standalone/worker.py:171-186
Timestamp: 2025-06-08T08:30:45.126Z
Learning: Example code in the `examples/` directory may intentionally use hard-coded values or simplified implementations that wouldn't be appropriate for production code, but are acceptable for demonstration and testing purposes.

Learnt from: biswapanda
PR: ai-dynamo/dynamo#1412
File: lib/bindings/python/src/dynamo/runtime/logging.py:100-100
Timestamp: 2025-06-06T21:48:35.214Z
Learning: In the Dynamo codebase, BentoML has been completely removed from all executable code, with only documentation and attribution references remaining. The error_loggers configuration in lib/bindings/python/src/dynamo/runtime/logging.py should not include "bentoml" since those modules no longer exist.

Learnt from: julienmancuso
PR: ai-dynamo/dynamo#1365
File: deploy/cloud/operator/api/v1alpha1/dynamocomponentdeployment_types.go:171-178
Timestamp: 2025-06-04T13:09:53.416Z
Learning: The `DYN_DEPLOYMENT_CONFIG` environment variable (commonconsts.DynamoDeploymentConfigEnvVar) in the Dynamo operator will never be set via ValueFrom (secrets/config maps), only via direct Value assignment. The GetDynamoDeploymentConfig method correctly only checks env.Value for this specific environment variable.

Learnt from: julienmancuso
PR: ai-dynamo/dynamo#1474
File: deploy/cloud/operator/internal/controller/dynamocomponent_controller.go:1302-1306
Timestamp: 2025-06-11T21:18:00.425Z
Learning: In the Dynamo operator, the project’s preferred security posture is to set a Pod-level `PodSecurityContext` with `runAsUser`, `runAsGroup`, and `fsGroup` all set to `1000`, and then selectively override the user at the individual container level (e.g., `RunAsUser: 0` for Kaniko) when root is required.