34 lines
702 B
YAML
34 lines
702 B
YAML
version: '3.3'
|
|
|
|
services:
|
|
server:
|
|
image: tabbyml/tabby
|
|
environment:
|
|
- MODEL_BACKEND=triton
|
|
- TRITON_TOKENIZER_NAME=/tokenizer
|
|
volumes:
|
|
- ../testdata/tiny-70M/tokenizer:/tokenizer
|
|
links:
|
|
- triton
|
|
|
|
admin:
|
|
links:
|
|
- triton
|
|
|
|
|
|
|
|
triton:
|
|
image: tabbyml/fastertransformer_backend
|
|
container_name: tabby-triton
|
|
command: mpirun -n 1 --allow-run-as-root /opt/tritonserver/bin/tritonserver --model-repository=/model
|
|
shm_size: 1gb
|
|
volumes:
|
|
- ../testdata/tiny-70M/models:/model
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|