Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: remove port specification for inference containers #307

Merged
merged 2 commits into from
Dec 26, 2024
Merged

feat: remove port specification for inference containers #307

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0addafd
first commit
jorgeantonio21 Dec 26, 2024
b7e23a0
refactor config.example.toml
jorgeantonio21 Dec 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion config.example.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
[atoma_service]
chat_completions_service_url = "http://chat-completions:80" # Internal Docker network URL
chat_completions_service_url = "http://chat-completions:8000" # Internal Docker network URL
embeddings_service_url = "http://embeddings:80"
image_generations_service_url = "http://image-generations:80"
# List of models to be used by the service, the current value here is just a placeholder, please change it to the models you want to deploy
Expand Down
12 changes: 0 additions & 12 deletions docker-compose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,8 +126,6 @@ services:
container_name: chat-completions
profiles: [chat_completions_vllm]
image: vllm/vllm-openai:v0.6.5
ports:
- "127.0.0.1:${CHAT_COMPLETIONS_SERVER_PORT}:8000"
ipc: host
command: ${VLLM_ENGINE_ARGS}

Expand All @@ -138,8 +136,6 @@ services:
build:
context: https://github.com/atoma-network/vllm.git#main
dockerfile: Dockerfile.cpu
ports:
- "127.0.0.1:${CHAT_COMPLETIONS_SERVER_PORT}:8000"
command: --model ${CHAT_COMPLETIONS_MODEL} --max-model-len ${CHAT_COMPLETIONS_MAX_MODEL_LEN}

vllm-rocm:
Expand All @@ -149,8 +145,6 @@ services:
build:
context: https://github.com/atoma-network/vllm.git#main
dockerfile: Dockerfile.rocm
ports:
- "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:
Expand All @@ -160,26 +154,20 @@ services:
build:
context: https://github.com/EricLBuehler/mistral.rs.git
dockerfile: Dockerfile
ports:
- "127.0.0.1:${CHAT_COMPLETIONS_SERVER_PORT}:80"
command: plain -m ${CHAT_COMPLETIONS_MODEL}

tei:
<<: *inference-service-cuda
container_name: embeddings
profiles: [embeddings_tei]
image: ${TEI_IMAGE}
ports:
- "127.0.0.1:${EMBEDDINGS_SERVER_PORT}:80"
command: --model-id ${EMBEDDINGS_MODEL} --huggingface-hub-cache /root/.cache/huggingface/hub

mistralrs:
<<: *inference-service-cuda
container_name: image-generations
profiles: [image_generations_mistralrs]
image: ${MISTRALRS_IMAGE}
ports:
- "127.0.0.1:${IMAGE_GENERATIONS_SERVER_PORT}:80"
command: diffusion-plain -m ${IMAGE_GENERATIONS_MODEL} --arch ${IMAGE_GENERATIONS_ARCHITECTURE}

networks:
Expand Down