Skip to content

Commit 34f13a1

Browse files
dagil-nvidiadagil-nvidia
authored
docs: use GitHub admonitions instead of Fern-native callouts (#7370)
Signed-off-by: Dan Gil <dagil@nvidia.com>
1 parent da783ce commit 34f13a1

File tree

2 files changed

+46
-47
lines changed

2 files changed

+46
-47
lines changed

‎docs/getting-started/quickstart.md‎

Lines changed: 35 additions & 43 deletions
Original file line numberDiff line numberDiff line change
@@ -6,11 +6,10 @@ title: Quickstart
66

77
This guide covers running Dynamo **using the CLI on your local machine or VM**.
88

9-
<Info>
10-
**Looking to deploy on Kubernetes instead?**
11-
See the [Kubernetes Installation Guide](../kubernetes/installation-guide.md)
12-
and [Kubernetes Quickstart](../kubernetes/README.md) for cluster deployments.
13-
</Info>
9+
> [!IMPORTANT]
10+
> **Looking to deploy on Kubernetes instead?**
11+
> See the [Kubernetes Installation Guide](../kubernetes/installation-guide.md)
12+
> and [Kubernetes Quickstart](../kubernetes/README.md) for cluster deployments.
1413
1514
## Install Dynamo
1615

@@ -29,12 +28,11 @@ docker run --gpus all --network host --rm -it nvcr.io/nvidia/ai-dynamo/tensorrtl
2928
docker run --gpus all --network host --rm -it nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0
3029
```
3130

32-
<Tip>
33-
To run frontend and worker in the same container, either:
34-
35-
- Run processes in background with `&` (see Run Dynamo section below), or
36-
- Open a second terminal and use `docker exec -it <container_id> bash`
37-
</Tip>
31+
> [!TIP]
32+
> To run frontend and worker in the same container, either:
33+
>
34+
> - Run processes in background with `&` (see Run Dynamo section below), or
35+
> - Open a second terminal and use `docker exec -it <container_id> bash`
3836
3937
See [Release Artifacts](../reference/release-artifacts.md#container-images) for available
4038
versions and backend guides for run instructions: [SGLang](../backends/sglang/README.md) |
@@ -61,10 +59,9 @@ sudo apt install python3-dev
6159
uv pip install --prerelease=allow "ai-dynamo[sglang]"
6260
```
6361

64-
<Note>
65-
For CUDA 13 (B300/GB300), the container is recommended. See
66-
[SGLang install docs](https://docs.sglang.io/get_started/install.html) for details.
67-
</Note>
62+
> [!NOTE]
63+
> For CUDA 13 (B300/GB300), the container is recommended. See
64+
> [SGLang install docs](https://docs.sglang.io/get_started/install.html) for details.
6865
6966
**TensorRT-LLM**
7067

@@ -74,12 +71,11 @@ pip install torch==2.9.0 torchvision --index-url https://download.pytorch.org/wh
7471
pip install --pre --extra-index-url https://pypi.nvidia.com "ai-dynamo[trtllm]"
7572
```
7673

77-
<Note>
78-
TensorRT-LLM requires `pip` due to a transitive Git URL dependency that
79-
`uv` doesn't resolve. We recommend using the TensorRT-LLM container for
80-
broader compatibility. See the [TRT-LLM backend guide](../backends/trtllm/README.md)
81-
for details.
82-
</Note>
74+
> [!NOTE]
75+
> TensorRT-LLM requires `pip` due to a transitive Git URL dependency that
76+
> `uv` doesn't resolve. We recommend using the TensorRT-LLM container for
77+
> broader compatibility. See the [TRT-LLM backend guide](../backends/trtllm/README.md)
78+
> for details.
8379
8480
**vLLM**
8581

@@ -90,17 +86,15 @@ uv pip install --prerelease=allow "ai-dynamo[vllm]"
9086

9187
## Run Dynamo
9288

93-
<Tip>
94-
**(Optional)** Before running Dynamo, verify your system configuration:
95-
`python3 deploy/sanity_check.py`
96-
</Tip>
89+
> [!TIP]
90+
> **(Optional)** Before running Dynamo, verify your system configuration:
91+
> `python3 deploy/sanity_check.py`
9792
9893
Start the frontend, then start a worker for your chosen backend.
9994

100-
<Tip>
101-
To run in a single terminal (useful in containers), append `> logfile.log 2>&1 &`
102-
to run processes in background. Example: `python3 -m dynamo.frontend --discovery-backend file > dynamo.frontend.log 2>&1 &`
103-
</Tip>
95+
> [!TIP]
96+
> To run in a single terminal (useful in containers), append `> logfile.log 2>&1 &`
97+
> to run processes in background. Example: `python3 -m dynamo.frontend --discovery-backend file > dynamo.frontend.log 2>&1 &`
10498
10599
```bash
106100
# Start the OpenAI compatible frontend (default port is 8000)
@@ -129,20 +123,18 @@ python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --discovery-backend file \
129123
--kv-events-config '{"enable_kv_cache_events": false}'
130124
```
131125

132-
<Note>
133-
For dependency-free local development, disable KV event publishing (avoids NATS):
134-
135-
- **vLLM:** Add `--kv-events-config '{"enable_kv_cache_events": false}'`
136-
- **SGLang:** No flag needed (KV events disabled by default)
137-
- **TensorRT-LLM:** No flag needed (KV events disabled by default)
138-
139-
**TensorRT-LLM only:** The warning `Cannot connect to ModelExpress server/transport error. Using direct download.`
140-
is expected and can be safely ignored.
141-
</Note>
142-
143-
<Note>
144-
**Deprecation notice:** vLLM automatically enables KV event publishing when prefix caching is active. In a future release, this will change — KV events will be disabled by default for all backends. Start using `--kv-events-config` explicitly to prepare.
145-
</Note>
126+
> [!NOTE]
127+
> For dependency-free local development, disable KV event publishing (avoids NATS):
128+
>
129+
> - **vLLM:** Add `--kv-events-config '{"enable_kv_cache_events": false}'`
130+
> - **SGLang:** No flag needed (KV events disabled by default)
131+
> - **TensorRT-LLM:** No flag needed (KV events disabled by default)
132+
>
133+
> **TensorRT-LLM only:** The warning `Cannot connect to ModelExpress server/transport error. Using direct download.`
134+
> is expected and can be safely ignored.
135+
136+
> [!NOTE]
137+
> **Deprecation notice:** vLLM automatically enables KV event publishing when prefix caching is active. In a future release, this will change — KV events will be disabled by default for all backends. Start using `--kv-events-config` explicitly to prepare.
146138
147139
## Test Your Deployment
148140

‎docs/reference/release-artifacts.md‎

Lines changed: 11 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,8 @@ We recommend using the TensorRT-LLM NGC container instead of the `ai-dynamo[trtl
5050
| `dynamo-platform-1.0.0` | Platform services (etcd, NATS) and Dynamo Operator for Dynamo cluster | [link](https://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/dynamo-platform-1.0.0.tgz) |
5151
| `snapshot-1.0.0` | Snapshot DaemonSet for fast GPU worker recovery | [link](https://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot-1.0.0.tgz) |
5252

53-
> **Note:** The `dynamo-crds` Helm chart is deprecated as of v1.0.0; CRDs are now managed by the Dynamo Operator. The `dynamo-graph` Helm chart is deprecated as of v0.9.0.
53+
> [!NOTE]
54+
> The `dynamo-crds` Helm chart is deprecated as of v1.0.0; CRDs are now managed by the Dynamo Operator. The `dynamo-graph` Helm chart is deprecated as of v0.9.0.
5455
5556
### Rust Crates
5657

@@ -70,7 +71,8 @@ We recommend using the TensorRT-LLM NGC container instead of the `ai-dynamo[trtl
7071

7172
### Container Images (NGC)
7273

73-
> For detailed run instructions, see the [Container README](https://github.com/ai-dynamo/dynamo/tree/main/container/README.md) or backend-specific guides: [vLLM](../backends/vllm/README.md) | [SGLang](../backends/sglang/README.md) | [TensorRT-LLM](../backends/trtllm/README.md)
74+
> [!TIP]
75+
> For detailed run instructions, see the backend-specific guides: [vLLM](../backends/vllm/README.md) | [SGLang](../backends/sglang/README.md) | [TensorRT-LLM](../backends/trtllm/README.md)
7476
7577
```bash
7678
# Runtime containers
@@ -94,6 +96,7 @@ docker pull nvcr.io/nvidia/ai-dynamo/snapshot-agent:1.0.0
9496

9597
### Python Wheels (PyPI)
9698

99+
> [!TIP]
97100
> For detailed installation instructions, see the [Local Quick Start](https://github.com/ai-dynamo/dynamo#local-quick-start) in the README.
98101
99102
```bash
@@ -112,6 +115,7 @@ uv pip install kvbm==1.0.0
112115

113116
### Helm Charts (NGC)
114117

118+
> [!TIP]
115119
> For Kubernetes deployment instructions, see the [Kubernetes Installation Guide](../kubernetes/installation-guide.md).
116120
117121
```bash
@@ -121,6 +125,7 @@ helm install snapshot oci://helm.ngc.nvidia.com/nvidia/ai-dynamo/charts/snapshot
121125

122126
### Rust Crates (crates.io)
123127

128+
> [!TIP]
124129
> For API documentation, see each crate on [docs.rs](https://docs.rs/). To build Dynamo from source, see [Building from Source](https://github.com/ai-dynamo/dynamo#building-from-source).
125130
126131
```bash
@@ -341,7 +346,8 @@ For a complete list of known issues, refer to the release notes for each version
341346
342347
#### dynamo-crds (Helm chart) -- Deprecated
343348

344-
> **Note:** The `dynamo-crds` Helm chart is deprecated as of v1.0.0. CRDs are now managed by the Dynamo Operator.
349+
> [!NOTE]
350+
> The `dynamo-crds` Helm chart is deprecated as of v1.0.0. CRDs are now managed by the Dynamo Operator.
345351
346352
| Chart | Notes |
347353
|-------|-------|
@@ -377,7 +383,8 @@ For a complete list of known issues, refer to the release notes for each version
377383

378384
#### dynamo-graph (Helm chart) -- Deprecated
379385

380-
> **Note:** The `dynamo-graph` Helm chart is deprecated as of v0.9.0.
386+
> [!NOTE]
387+
> The `dynamo-graph` Helm chart is deprecated as of v0.9.0.
381388
382389
| Chart | Notes |
383390
|-------|-------|

0 commit comments

Comments
 (0)