Cara mengurangi kemacetan cache kv dengan nvidia dynamo

# start up etcd for KVBM leader/worker registration and discovery
docker compose -f deploy/docker-compose.yml up -d

# build a container containing vllm and kvbm
./container/build.sh --framework vllm --enable-kvbm

# launch the container
./container/run.sh --framework vllm -it --mount-workspace --use-nixl-gds

# enable kv offloading to CPU memory
# 4 means 4GB of CPU memory would be used
export DYN_KVBM_CPU_CACHE_GB=4

# enable kv offloading to disk
# 8 means 8GB of disk would be used
export DYN_KVBM_DISK_CACHE_GB=8

# serve an example LLM model
vllm serve --kv-transfer-config 
'{"kv_connector":"DynamoConnector","kv_role":"kv_both", 
"kv_connector_module_path": "dynamo.llm.vllm_integration.connector"}' 
deepseek-ai/DeepSeek-R1-Distill-Llama-8B

# make a call to LLM
curl localhost:8000/v1/chat/completions   -H "Content-Type: application/json"   -d '{
    "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
    "messages": [
    {
        "role": "user",
        "content": "In the heart of Eldoria, an ancient land of boundless magic and mysterious creatures, 
lies the long-forgotten city of Aeloria. Once a beacon of knowledge and power, Aeloria was buried 
beneath the shifting sands of time, lost to the world for centuries. You are an intrepid explorer, known 
for your unparalleled curiosity and courage, who has stumbled upon an ancient map hinting that Aeloria 
holds a secret so profound that it has the potential to reshape the very fabric of reality. Your journey 
will take you through treacherous deserts, enchanted forests, and across perilous mountain ranges. 
Your Task: Character Background: Develop a detailed background for your character. Describe their 
motivations for seeking out Aeloria, their skills and weaknesses, and any personal connections to the 
ancient city or its legends. Are they driven by a quest for knowledge, or a search for lost family? A clue is hidden."
    }
    ],
    "stream":false,
    "max_tokens": 30
  }'