Update formatting

Author: rahulgurnani

site-src/implementations/model-servers.md

@@ -23,7 +23,7 @@ Use `--set inferencePool.modelServerType=triton-tensorrt-llm` to install the `in
 
  Add the following to the `flags` in the helm chart as [flags to EPP](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/29ea29028496a638b162ff287c62c0087211bbe5/config/charts/inferencepool/values.yaml#L36)
 
- ```
+```
 - --total-queued-requests-metric
 - "nv_trt_llm_request_metrics{request_type=waiting}"
 - --kv-cache-usage-percentage-metric
@@ -36,6 +36,7 @@ Use `--set inferencePool.modelServerType=triton-tensorrt-llm` to install the `in
 
  Add the following `flags` while deploying using helm charts in the [EPP deployment](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/29ea29028496a638b162ff287c62c0087211bbe5/config/charts/inferencepool/values.yaml#L36)
 
+
 ```
 - --totalQueuedRequestsMetric
 - "sglang:num_queue_reqs"