forked from phoenix-oss/llama-stack-mirror
c810a4184d
* move docs -> source * Add files via upload * mv image * Add files via upload * colocate iOS setup doc * delete image * Add files via upload * fix * delete image * Add files via upload * Update developer_cookbook.md * toctree * wip subfolder * docs update * subfolder * updates * name * updates * index * updates * refactor structure * depth * docs * content * docs * getting started * distributions * fireworks * fireworks * update * theme * theme * theme * pdj theme * pytorch theme * css * theme * agents example * format * index * headers * copy button * test tabs * test tabs * fix * tabs * tab * tabs * sphinx_design * quick start commands * size * width * css * css * download models * asthetic fix * tab format * update * css * width * css * docs * tab based * tab * tabs * docs * style * image * css * color * typo * update docs * missing links * list templates * links * links update * troubleshooting * fix * distributions * docs * fix table * kill llamastack-local-gpu/cpu * Update index.md * Update index.md * mv ios_setup.md * Update ios_setup.md * Add remote_or_local.gif * Update ios_setup.md * release notes * typos * Add ios_setup to index * nav bar * hide torctree * ios image * links update * rename * rename * docs * rename * links * distributions * distributions * distributions * distributions * remove release * remote --------- Co-authored-by: dltn <6599399+dltn@users.noreply.github.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
33 lines
1.1 KiB
YAML
33 lines
1.1 KiB
YAML
services:
|
|
text-generation-inference:
|
|
image: ghcr.io/huggingface/text-generation-inference:latest
|
|
network_mode: "host"
|
|
volumes:
|
|
- $HOME/.cache/huggingface:/data
|
|
ports:
|
|
- "5009:5009"
|
|
command: ["--dtype", "bfloat16", "--usage-stats", "on", "--sharded", "false", "--model-id", "meta-llama/Llama-3.1-8B-Instruct", "--port", "5009", "--cuda-memory-fraction", "0.3"]
|
|
runtime: nvidia
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://text-generation-inference:5009/health"]
|
|
interval: 5s
|
|
timeout: 5s
|
|
retries: 30
|
|
llamastack:
|
|
depends_on:
|
|
text-generation-inference:
|
|
condition: service_healthy
|
|
image: llamastack/llamastack-tgi
|
|
network_mode: "host"
|
|
volumes:
|
|
- ~/.llama:/root/.llama
|
|
# Link to run.yaml file
|
|
- ./run.yaml:/root/my-run.yaml
|
|
ports:
|
|
- "5000:5000"
|
|
entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
|
|
restart_policy:
|
|
condition: on-failure
|
|
delay: 3s
|
|
max_attempts: 5
|
|
window: 60s
|