Add CLI and HTTP API guide

Author: Andrey Cheptsov

mkdocs.yml

@@ -361,25 +361,25 @@ nav:
               - dstack export: docs/reference/cli/dstack/export.md
               - dstack import: docs/reference/cli/dstack/import.md
           - HTTP API:
-            - Users: docs/reference/http/users.md
-            - Projects: docs/reference/http/projects.md
-            - Backends: docs/reference/http/backends.md
-            - Fleets: docs/reference/http/fleets.md
-            - Runs: docs/reference/http/runs.md
-            - Gateways: docs/reference/http/gateways.md
-            - Volumes: docs/reference/http/volumes.md
-            - Logs: docs/reference/http/logs.md
-            - Events: docs/reference/http/events.md
-            - Repos: docs/reference/http/repos.md
-            - Files: docs/reference/http/files.md
-            - Secrets: docs/reference/http/secrets.md
-            - Exports: docs/reference/http/exports.md
-            - Metrics: docs/reference/http/metrics.md
-            - GPUs: docs/reference/http/gpus.md
-            - Templates: docs/reference/http/templates.md
-            - Proxy: docs/reference/http/proxy.md
-            - Authentication: docs/reference/http/authentication.md
-            - Server: docs/reference/http/server.md
+            - users: docs/reference/http/users.md
+            - projects: docs/reference/http/projects.md
+            - backends: docs/reference/http/backends.md
+            - fleets: docs/reference/http/fleets.md
+            - runs: docs/reference/http/runs.md
+            - gateways: docs/reference/http/gateways.md
+            - volumes: docs/reference/http/volumes.md
+            - logs: docs/reference/http/logs.md
+            - events: docs/reference/http/events.md
+            - repos: docs/reference/http/repos.md
+            - files: docs/reference/http/files.md
+            - secrets: docs/reference/http/secrets.md
+            - exports: docs/reference/http/exports.md
+            - metrics: docs/reference/http/metrics.md
+            - gpus: docs/reference/http/gpus.md
+            - templates: docs/reference/http/templates.md
+            - proxy: docs/reference/http/proxy.md
+            - authentication: docs/reference/http/authentication.md
+            - server: docs/reference/http/server.md
           - Environment variables: docs/reference/env.md
           - More:
             - .dstack/profiles.yml: docs/reference/profiles.yml.md

mkdocs/docs/concepts/services.md

@@ -125,7 +125,7 @@ If you do not have a [gateway](gateways.md) created, the service endpoint will b
 ```shell
 $ curl http://localhost:3000/proxy/services/main/qwen36/v1/chat/completions \
     -H 'Content-Type: application/json' \
-    -H 'Authorization: Bearer <dstack token>' \
+    -H 'Authorization: Bearer <user token>' \
     -d '{
         "model": "Qwen/Qwen3.6-27B",
         "messages": [
@@ -143,7 +143,7 @@ The request and response format depends on the serving framework used by the
 service. Even for OpenAI-compatible endpoints, the format may vary slightly
 across frameworks.
 
-If [authorization](#authorization) is not disabled, the service endpoint requires the `Authorization` header with `Bearer <dstack token>`.
+If [authorization](#authorization) is not disabled, the service endpoint requires the `Authorization` header with `Bearer <user token>`.
 
 ## Configuration options
 
@@ -173,7 +173,7 @@ If you have a [gateway](gateways.md) created, the service endpoint will be acces
 ```shell
 $ curl https://llama31.example.com/v1/chat/completions \
     -H 'Content-Type: application/json' \
-    -H 'Authorization: Bearer &lt;dstack token&gt;' \
+    -H 'Authorization: Bearer &lt;user token&gt;' \
     -d '{
         "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
         "messages": [

mkdocs/docs/examples/accelerators/amd.md

@@ -93,8 +93,15 @@ Here are examples of a [service](../../concepts/services.md) that deploy
     </div>
 
 !!! info "Docker image"
-    AMD deployments require specifying an image that already includes ROCm
-    drivers. The SGLang and vLLM examples above use pinned ROCm images.
+    AMD workloads require specifying an image with ROCm-compatible userspace and
+    framework packages. The SGLang and vLLM examples above use pinned ROCm
+    images.
+
+    If you already have a ROCm-compatible image, use it. Otherwise, choose an
+    image for the framework you use from
+    [ROCm Docker images](https://hub.docker.com/u/rocm), e.g. `rocm/sgl-dev`
+    for SGLang, `rocm/vllm` for vLLM, or `rocm/pytorch` for PyTorch. For
+    generic AMD dev environments or tasks, use `rocm/dev-ubuntu-24.04`.
 
 To request multiple GPUs, specify the quantity after the GPU name, separated by a colon, e.g., `MI300X:4`.
 

mkdocs/docs/examples/accelerators/tenstorrent.md

@@ -98,7 +98,7 @@ at `<dstack server URL>/proxy/services/<project name>/<run name>/`.
 ```shell
 $ curl http://127.0.0.1:3000/proxy/services/main/tt-inference-server/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer &lt;dstack token&gt;' \
+    -H 'Authorization: Bearer &lt;user token&gt;' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "meta-llama/Llama-3.2-1B-Instruct",

mkdocs/docs/examples/inference/nim.md

@@ -71,7 +71,7 @@ If no gateway is created, the service endpoint will be available at `<dstack ser
 ```shell
 $ curl http://127.0.0.1:3000/proxy/services/main/nemotron120/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer &lt;dstack token&gt;' \
+    -H 'Authorization: Bearer &lt;user token&gt;' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "nvidia/nemotron-3-super-120b-a12b",

mkdocs/docs/examples/inference/sglang.md

@@ -112,7 +112,7 @@ If no gateway is created, the service endpoint will be available at `<dstack ser
 ```shell
 curl http://127.0.0.1:3000/proxy/services/main/qwen36/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer &lt;dstack token&gt;' \
+    -H 'Authorization: Bearer &lt;user token&gt;' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "Qwen/Qwen3.6-27B",

mkdocs/docs/examples/inference/trtllm.md

@@ -72,7 +72,7 @@ If no gateway is created, the service endpoint will be available at `<dstack ser
 ```shell
 $ curl http://127.0.0.1:3000/proxy/services/main/qwen235/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer &lt;dstack token&gt;' \
+    -H 'Authorization: Bearer &lt;user token&gt;' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "nvidia/Qwen3-235B-A22B-FP8",

mkdocs/docs/examples/inference/vllm.md

@@ -106,7 +106,7 @@ If no gateway is created, the service endpoint will be available at `<dstack ser
 ```shell
 curl http://127.0.0.1:3000/proxy/services/main/qwen36/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer &lt;dstack token&gt;' \
+    -H 'Authorization: Bearer &lt;user token&gt;' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "Qwen/Qwen3.6-27B",

mkdocs/docs/examples/models/deepseek-v4.md

@@ -83,7 +83,7 @@ If no gateway is created, the service endpoint will be available at
 ```shell
 curl http://127.0.0.1:3000/proxy/services/main/deepseek-v4/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer <dstack token>' \
+    -H 'Authorization: Bearer <user token>' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "deepseek-ai/DeepSeek-V4-Pro",
@@ -114,7 +114,7 @@ top-level JSON fields.
 ```shell
 curl http://127.0.0.1:3000/proxy/services/main/deepseek-v4/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer <dstack token>' \
+    -H 'Authorization: Bearer <user token>' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "deepseek-ai/DeepSeek-V4-Pro",

mkdocs/docs/examples/models/qwen36.md

@@ -110,7 +110,7 @@ If no gateway is created, the service endpoint will be available at
 ```shell
 curl http://127.0.0.1:3000/proxy/services/main/qwen36/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer <dstack token>' \
+    -H 'Authorization: Bearer <user token>' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "Qwen/Qwen3.6-27B",
@@ -138,7 +138,7 @@ To disable thinking, pass `chat_template_kwargs` in the request body.
 ```shell
 curl http://127.0.0.1:3000/proxy/services/main/qwen36/v1/chat/completions \
     -X POST \
-    -H 'Authorization: Bearer <dstack token>' \
+    -H 'Authorization: Bearer <user token>' \
     -H 'Content-Type: application/json' \
     -d '{
       "model": "Qwen/Qwen3.6-27B",