Add Replica Groups Docs

Author: Bihan Rana

docs/docs/concepts/services.md

@@ -164,6 +164,59 @@ Setting the minimum number of replicas to `0` allows the service to scale down t
 
 > The `scaling` property requires creating a [gateway](gateways.md).
 
+### Replica Groups
+
+Replica groups let you define multiple groups of replicas within a single service. Each group can define its own replica count, autoscaling rules, resource requirements, and commands.
+
+<div editor-title="service.dstack.yml"> 
+
+```yaml
+type: service
+name: replica-groups
+image: lmsysorg/sglang:latest
+
+env:
+  - MODEL_ID=deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+
+replicas:
+  - count: 1..2
+    scaling:
+      metric: rps
+      target: 10
+    commands:
+      - |
+          python -m sglang.launch_server \
+            --model-path $MODEL_ID \
+            --port 8000 \
+            --trust-remote-code
+
+    resources:
+      gpu: 48GB
+
+  - count: 1..4
+    scaling:
+      metric: rps
+      target: 5
+    commands:
+      - |
+          python -m sglang.launch_server \
+            --model-path $MODEL_ID \
+            --port 8000 \
+            --trust-remote-code
+    resources:
+      gpu: 24GB
+
+port: 8000
+model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+```
+
+</div>
+
+> Support for configuring `port`, `image`, `env`, `docker`, and other properties is coming soon.
+
+!!! info
+    Replica groups enable `prefill–decode` disaggregation by running prefill and decode workers as separate replica groups within a single service. This capability is planned for an upcoming release. See the [issue](https://github.com/dstackai/dstack/issues/3363) for more details.
+
 ### Model
 
 If the service is running a chat model with an OpenAI-compatible interface,