docs: Add cancellation docs for vLLM, TRT-LLM and SGLang backends (#3783)

Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>

docs/backends/sglang/README.md

@@ -69,6 +69,22 @@ Dynamo SGLang uses SGLang's native argument parser, so **most SGLang engine argu
 > [!NOTE]
 > When using `--use-sglang-tokenizer`, only `v1/chat/completions` is available through Dynamo's frontend.
 
+### Request Cancellation
+
+When a user cancels a request (e.g., by disconnecting from the frontend), the request is automatically cancelled across all workers, freeing compute resources for other requests.
+
+#### Cancellation Support Matrix
+
+| | Prefill | Decode |
+|-|---------|--------|
+| **Aggregated** | ✅ | ✅ |
+| **Disaggregated** | ⚠️ | ✅ |
+
+> [!WARNING]
+> ⚠️ SGLang backend currently does not support cancellation during remote prefill phase in disaggregated mode.
+
+For more details, see the [Request Cancellation Architecture](../../architecture/request_cancellation.md) documentation.
+
 ## Installation
 
 ### Install latest release

docs/backends/trtllm/README.md

@@ -228,6 +228,20 @@ python3 -m dynamo.trtllm ... --migration-limit=3
 
 This allows a request to be migrated up to 3 times before failing. See the [Request Migration Architecture](../../../docs/architecture/request_migration.md) documentation for details on how this works.
 
+## Request Cancellation
+
+When a user cancels a request (e.g., by disconnecting from the frontend), the request is automatically cancelled across all workers, freeing compute resources for other requests.
+
+### Cancellation Support Matrix
+
+| | Prefill | Decode |
+|-|---------|--------|
+| **Aggregated** | ✅ | ✅ |
+| **Disaggregated (Decode-First)** | ✅ | ✅ |
+| **Disaggregated (Prefill-First)** | ✅ | ✅ |
+
+For more details, see the [Request Cancellation Architecture](../../../docs/architecture/request_cancellation.md) documentation.
+
 ## Client
 
 See [client](../../../docs/backends/sglang/README.md#testing-the-deployment) section to learn how to send request to the deployment.

docs/backends/vllm/README.md

@@ -189,3 +189,16 @@ python3 -m dynamo.vllm ... --migration-limit=3
 ```
 
 This allows a request to be migrated up to 3 times before failing. See the [Request Migration Architecture](../../../docs/architecture/request_migration.md) documentation for details on how this works.
+
+## Request Cancellation
+
+When a user cancels a request (e.g., by disconnecting from the frontend), the request is automatically cancelled across all workers, freeing compute resources for other requests.
+
+### Cancellation Support Matrix
+
+| | Prefill | Decode |
+|-|---------|--------|
+| **Aggregated** | ✅ | ✅ |
+| **Disaggregated** | ✅ | ✅ |
+
+For more details, see the [Request Cancellation Architecture](../../../docs/architecture/request_cancellation.md) documentation.