first commit

docker-compose.yaml

@@ -127,7 +127,7 @@ services:
     profiles: [chat_completions_vllm]
     image: vllm/vllm-openai:v0.6.5
     ports:
-      - "${CHAT_COMPLETIONS_SERVER_PORT}:8000"
+      - "127.0.0.1:${CHAT_COMPLETIONS_SERVER_PORT}:8000"
     ipc: host
     command: ${VLLM_ENGINE_ARGS}
 
@@ -139,7 +139,7 @@ services:
       context: https://github.com/atoma-network/vllm.git#main
       dockerfile: Dockerfile.cpu
     ports:
-      - "${CHAT_COMPLETIONS_SERVER_PORT}:8000"
+      - "127.0.0.1:${CHAT_COMPLETIONS_SERVER_PORT}:8000"
     command: --model ${CHAT_COMPLETIONS_MODEL} --max-model-len ${CHAT_COMPLETIONS_MAX_MODEL_LEN}
 
   vllm-rocm:
@@ -150,7 +150,7 @@ services:
       context: https://github.com/atoma-network/vllm.git#main
       dockerfile: Dockerfile.rocm
     ports:
-      - "${CHAT_COMPLETIONS_SERVER_PORT}:8000"
+      - "127.0.0.1:${CHAT_COMPLETIONS_SERVER_PORT}:8000"
     command: --model ${CHAT_COMPLETIONS_MODEL} --max-model-len ${CHAT_COMPLETIONS_MAX_MODEL_LEN} --tensor-parallel-size ${VLLM_TENSOR_PARALLEL_SIZE}
 
   mistralrs-cpu:
@@ -161,7 +161,7 @@ services:
       context: https://github.com/EricLBuehler/mistral.rs.git
       dockerfile: Dockerfile
     ports:
-      - "${CHAT_COMPLETIONS_SERVER_PORT}:80"
+      - "127.0.0.1:${CHAT_COMPLETIONS_SERVER_PORT}:80"
     command: plain -m ${CHAT_COMPLETIONS_MODEL}
 
   tei:
@@ -170,7 +170,7 @@ services:
     profiles: [embeddings_tei]
     image: ${TEI_IMAGE}
     ports:
-      - "${EMBEDDINGS_SERVER_PORT}:80"
+      - "127.0.0.1:${EMBEDDINGS_SERVER_PORT}:80"
     command: --model-id ${EMBEDDINGS_MODEL} --huggingface-hub-cache /root/.cache/huggingface/hub
 
   mistralrs:
@@ -179,7 +179,7 @@ services:
     profiles: [image_generations_mistralrs]
     image: ${MISTRALRS_IMAGE}
     ports:
-      - "${IMAGE_GENERATIONS_SERVER_PORT}:80"
+      - "127.0.0.1:${IMAGE_GENERATIONS_SERVER_PORT}:80"
     command: diffusion-plain -m ${IMAGE_GENERATIONS_MODEL} --arch ${IMAGE_GENERATIONS_ARCHITECTURE}
 
 networks: