refactor: remove sglang config and util files from components (#3467)

Signed-off-by: Anant Sharma <[email protected]>

Author: nv-anants

components/backends/sglang/benchmarks/bench.sh

@@ -56,13 +56,7 @@ docker run \
     dynamo-wideep-gb200:latest
 ```
 
-3. On the head prefill node, run the helper script provided to generate commands to start the `nats-server`, `etcd`. This script will also tell you which environment variables to export on each node to make deployment easier.
-
-```bash
-./utils/gen_env_vars.sh
-```
-
-4. Run the ingress and prefill worker
+3. Run the ingress and prefill worker
 
 ```bash
 # run ingress
@@ -115,7 +109,7 @@ python3 -m dynamo.sglang \
   --log-level debug
 ```
 
-5. Run the decode worker on the head decode node
+4. Run the decode worker on the head decode node
 
 ```bash
 SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=768 \

components/backends/sglang/benchmarks/generate_bench_data.py

@@ -41,13 +41,7 @@ docker run \
 
 In each container, you should be in the `/sgl-workspace/dynamo/components/backends/sglang` directory.
 
-3. On the head prefill node, run the helper script provided to generate commands to start the `nats-server`, `etcd`. This script will also tell you which environment variables to export on each node to make deployment easier.
-
-```bash
-./utils/gen_env_vars.sh
-```
-
-4. Run the ingress and prefill worker
+3. Run the ingress and prefill worker
 
 ```bash
 # run ingress
@@ -87,7 +81,7 @@ python3 -m dynamo.sglang \
 
 On the other prefill node (since this example has 4 total prefill nodes), run the same command but change `--node-rank` to 1,2, and 3
 
-5. Run the decode worker on the head decode node
+4. Run the decode worker on the head decode node
 
 ```bash
 python3 -m dynamo.sglang \

components/backends/sglang/docs/dsr1-wideep-gb200.md

@@ -18,12 +18,7 @@ docker build -f container/Dockerfile.sglang-wideep . -t dynamo-wideep --no-cache
 
 You can use a specific tag from the [lmsys dockerhub](https://hub.docker.com/r/lmsysorg/sglang/tags) by adding `--build-arg SGLANG_IMAGE_TAG=<tag>` to the build command.
 
-**Step 1**: Use the provided helper script to generate commands to start NATS/ETCD on your head prefill node. This script will also give you environment variables to export on each other node. You will need the IP addresses of your head prefill and head decode node to run this script.
-```bash
-./utils/gen_env_vars.sh
-```
-
-**Step 2**: Ensure that your configuration file has the required arguments. Here's an example configuration that runs prefill and the model in TP16:
+**Step 1**: Ensure that your configuration file has the required arguments. Here's an example configuration that runs prefill and the model in TP16:
 
 Node 1: Run HTTP ingress, processor, and 8 shards of the prefill worker
 ```bash
@@ -104,7 +99,7 @@ python3 -m dynamo.sglang \
   --mem-fraction-static 0.82
 ```
 
-**Step 3**: Run inference
+**Step 2**: Run inference
 SGLang typically requires a warmup period to ensure the DeepGEMM kernels are loaded. We recommend running a few warmup requests and ensuring that the DeepGEMM kernels load in.
 
 ```bash