31 lines
708 B
YAML
31 lines
708 B
YAML
version: '3.3'
|
|
|
|
services:
|
|
server:
|
|
build: .
|
|
working_dir: /app
|
|
command: /opt/conda/bin/python server/app.py
|
|
environment:
|
|
- TOKENIZER_NAME=/tokenizer
|
|
- TRITON_HOST=triton
|
|
ports:
|
|
- "5000:5000"
|
|
volumes:
|
|
- ./testdata/gptneox/tokenizer:/tokenizer
|
|
links:
|
|
- triton
|
|
|
|
triton:
|
|
image: tabbyml/fastertransformer_backend
|
|
command: mpirun -n 1 --allow-run-as-root /opt/tritonserver/bin/tritonserver --model-repository=/model
|
|
shm_size: 1gb
|
|
volumes:
|
|
- ./testdata/gptneox/models:/model
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|