testing llama-swap settings for performance

gistfile1.txt

#
# need a handy gist url for this
#

# watch the logs for timing
$ curl -N localhost:8080/logs/stream | grep "eval time"

CURL: 
# make sure qwen-coder-32b-q* is in the llama-swap configuration: 

for model in "qwen-coder-32b-q4" "qwen-coder-32b-q8"; do 
    for lang in "python" "typescript" "swift"; do
        echo "Generating Snake Game in $lang using $model"
        curl -s --url http://localhost:8080/v1/chat/completions -d "{\"messages\": [{\"role\": \"system\", \"content\": \"you only write code.\"}, {\"role\": \"user\", \"content\": \"write snake game in $lang\"}], \"temperature\": 0.1, \"model\":\"$model\"}" > /dev/null
    done
done