Worker refactor

Co-authored-by: rltakashige <rl.takashige@gmail.com>
Co-authored-by: Alex Cheema <alexcheema123@gmail.com>

tmp/run_llm.sh

@@ -13,7 +13,7 @@ QUERY="$*"
 curl -sN -X POST "http://$HOST:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   -d "{
-        \"model\": \"mlx-community/DeepSeek-V3.1-8bit\",
+        \"model\": \"mlx-community/Llama-3.3-70B-Instruct-8bit\",
         \"stream\": true,
         \"messages\": [{ \"role\": \"user\",   \"content\": \"$QUERY\" }]
       }" |
@@ -21,4 +21,4 @@ curl -sN -X POST "http://$HOST:8000/v1/chat/completions" \
   grep --line-buffered -v 'data: \[DONE\]' |
   cut -d' ' -f2- |
   jq -r --unbuffered '.choices[].delta.content // empty' |
-  awk '{ORS=""; print; fflush()} END {print "\n"}'
+  awk '{ORS=""; print; fflush()} END {print "\n"}'