mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-13 04:22:35 +00:00
move distribution folders
This commit is contained in:
Xi Yan
parent
fd90d2ae97
commit
b4aca0aeb6
13 changed files with 274 additions and 57 deletions
85
distributions/tgi/README.md
Normal file
85
distributions/tgi/README.md
Normal file
|
|
@ -0,0 +1,85 @@
|
|||
# TGI Distribution
|
||||
|
||||
The `llamastack/distribution-tgi` distribution consists of the following provider configurations.
|
||||
|
||||
|
||||
| **API** | **Inference** | **Agents** | **Memory** | **Safety** | **Telemetry** |
|
||||
|----------------- |--------------- |---------------- |-------------------------------------------------- |---------------- |---------------- |
|
||||
| **Provider(s)** | remote::tgi | meta-reference | meta-reference, remote::pgvector, remote::chroma | meta-reference | meta-reference |
|
||||
|
||||
|
||||
### Start the Distribution (Single Node GPU)
|
||||
|
||||
> [!NOTE]
|
||||
> This assumes you have access to GPU to start a TGI server with access to your GPU.
|
||||
|
||||
|
||||
```
|
||||
$ cd llama_stack/distribution/docker/tgi
|
||||
$ ls
|
||||
compose.yaml tgi-run.yaml
|
||||
$ docker compose up
|
||||
```
|
||||
|
||||
The script will first start up TGI server, then start up Llama Stack distribution server hooking up to the remote TGI provider for inference. You should be able to see the following outputs --
|
||||
```
|
||||
[text-generation-inference] | 2024-10-15T18:56:33.810397Z INFO text_generation_router::server: router/src/server.rs:1813: Using config Some(Llama)
|
||||
[text-generation-inference] | 2024-10-15T18:56:33.810448Z WARN text_generation_router::server: router/src/server.rs:1960: Invalid hostname, defaulting to 0.0.0.0
|
||||
[text-generation-inference] | 2024-10-15T18:56:33.864143Z INFO text_generation_router::server: router/src/server.rs:2353: Connected
|
||||
INFO: Started server process [1]
|
||||
INFO: Waiting for application startup.
|
||||
INFO: Application startup complete.
|
||||
INFO: Uvicorn running on http://[::]:5000 (Press CTRL+C to quit)
|
||||
```
|
||||
|
||||
To kill the server
|
||||
```
|
||||
docker compose down
|
||||
```
|
||||
|
||||
### Start the Distribution (Single Node CPU)
|
||||
|
||||
> [!NOTE]
|
||||
> This assumes you have an hosted endpoint
|
||||
|
||||
```
|
||||
$ cd llama-stack/distribution/tgi/cpu
|
||||
$ ls
|
||||
compose.yaml run.yaml
|
||||
$ docker compose up
|
||||
```
|
||||
|
||||
### (Alternative) TGI server + llama stack run (Single Node GPU)
|
||||
|
||||
If you wish to separately spin up a TGI server, and connect with Llama Stack, you may use the following commands.
|
||||
|
||||
#### (optional) Start TGI server locally
|
||||
- Please check the [TGI Getting Started Guide](https://github.com/huggingface/text-generation-inference?tab=readme-ov-file#get-started) to get a TGI endpoint.
|
||||
|
||||
```
|
||||
docker run --rm -it -v $HOME/.cache/huggingface:/data -p 5009:5009 --gpus all ghcr.io/huggingface/text-generation-inference:latest --dtype bfloat16 --usage-stats on --sharded false --model-id meta-llama/Llama-3.1-8B-Instruct --port 5009
|
||||
```
|
||||
|
||||
|
||||
#### Start Llama Stack server pointing to TGI server
|
||||
|
||||
```
|
||||
docker run --network host -it -p 5000:5000 -v ./run.yaml:/root/my-run.yaml --gpus=all llamastack-local-cpu --yaml_config /root/my-run.yaml
|
||||
```
|
||||
|
||||
Make sure in you `run.yaml` file, you inference provider is pointing to the correct TGI server endpoint. E.g.
|
||||
```
|
||||
inference:
|
||||
- provider_id: tgi0
|
||||
provider_type: remote::tgi
|
||||
config:
|
||||
url: http://127.0.0.1:5009
|
||||
```
|
||||
|
||||
**Via Conda**
|
||||
|
||||
```bash
|
||||
llama stack build --config ./build.yaml
|
||||
# -- start a TGI server endpoint
|
||||
llama stack run ./gpu/run.yaml
|
||||
```
|
||||
54
distributions/tgi/cpu/compose.yaml
Normal file
54
distributions/tgi/cpu/compose.yaml
Normal file
|
|
@ -0,0 +1,54 @@
|
|||
services:
|
||||
text-generation-inference:
|
||||
image: ghcr.io/huggingface/text-generation-inference:latest
|
||||
network_mode: "host"
|
||||
volumes:
|
||||
- $HOME/.cache/huggingface:/data
|
||||
ports:
|
||||
- "5009:5009"
|
||||
devices:
|
||||
- nvidia.com/gpu=all
|
||||
environment:
|
||||
- CUDA_VISIBLE_DEVICES=0
|
||||
- HF_HOME=/data
|
||||
- HF_DATASETS_CACHE=/data
|
||||
- HF_MODULES_CACHE=/data
|
||||
- HF_HUB_CACHE=/data
|
||||
command: ["--dtype", "bfloat16", "--usage-stats", "on", "--sharded", "false", "--model-id", "meta-llama/Llama-3.1-8B-Instruct", "--port", "5009", "--cuda-memory-fraction", "0.3"]
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
# that's the closest analogue to --gpus; provide
|
||||
# an integer amount of devices or 'all'
|
||||
count: 1
|
||||
# Devices are reserved using a list of capabilities, making
|
||||
# capabilities the only required field. A device MUST
|
||||
# satisfy all the requested capabilities for a successful
|
||||
# reservation.
|
||||
capabilities: [gpu]
|
||||
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-local-cpu
|
||||
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
|
||||
46
distributions/tgi/cpu/run.yaml
Normal file
46
distributions/tgi/cpu/run.yaml
Normal file
|
|
@ -0,0 +1,46 @@
|
|||
version: '2'
|
||||
built_at: '2024-10-08T17:40:45.325529'
|
||||
image_name: local
|
||||
docker_image: null
|
||||
conda_env: local
|
||||
apis:
|
||||
- shields
|
||||
- agents
|
||||
- models
|
||||
- memory
|
||||
- memory_banks
|
||||
- inference
|
||||
- safety
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: tgi0
|
||||
provider_type: remote::tgi
|
||||
config:
|
||||
url: <ENTER_YOUR_TGI_HOSTED_ENDPOINT>
|
||||
safety:
|
||||
- provider_id: meta0
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
llama_guard_shield:
|
||||
model: Llama-Guard-3-1B
|
||||
excluded_categories: []
|
||||
disable_input_check: false
|
||||
disable_output_check: false
|
||||
prompt_guard_shield:
|
||||
model: Prompt-Guard-86M
|
||||
memory:
|
||||
- provider_id: meta0
|
||||
provider_type: meta-reference
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta0
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ~/.llama/runtime/kvstore.db
|
||||
telemetry:
|
||||
- provider_id: meta0
|
||||
provider_type: meta-reference
|
||||
config: {}
|
||||
55
distributions/tgi/gpu/compose.yaml
Normal file
55
distributions/tgi/gpu/compose.yaml
Normal file
|
|
@ -0,0 +1,55 @@
|
|||
services:
|
||||
text-generation-inference:
|
||||
image: ghcr.io/huggingface/text-generation-inference:latest
|
||||
network_mode: "host"
|
||||
volumes:
|
||||
- $HOME/.cache/huggingface:/data
|
||||
ports:
|
||||
- "5009:5009"
|
||||
devices:
|
||||
- nvidia.com/gpu=all
|
||||
environment:
|
||||
- CUDA_VISIBLE_DEVICES=0
|
||||
- HF_HOME=/data
|
||||
- HF_DATASETS_CACHE=/data
|
||||
- HF_MODULES_CACHE=/data
|
||||
- HF_HUB_CACHE=/data
|
||||
command: ["--dtype", "bfloat16", "--usage-stats", "on", "--sharded", "false", "--model-id", "meta-llama/Llama-3.1-8B-Instruct", "--port", "5009", "--cuda-memory-fraction", "0.3"]
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
# that's the closest analogue to --gpus; provide
|
||||
# an integer amount of devices or 'all'
|
||||
count: 1
|
||||
# Devices are reserved using a list of capabilities, making
|
||||
# capabilities the only required field. A device MUST
|
||||
# satisfy all the requested capabilities for a successful
|
||||
# reservation.
|
||||
capabilities: [gpu]
|
||||
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-local-cpu
|
||||
network_mode: "host"
|
||||
volumes:
|
||||
- ~/.llama:/root/.llama
|
||||
# Link to TGI run.yaml file
|
||||
- ./run.yaml:/root/my-run.yaml
|
||||
ports:
|
||||
- "5000:5000"
|
||||
# Hack: wait for TGI server to start before starting docker
|
||||
entrypoint: bash -c "sleep 60; 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
|
||||
46
distributions/tgi/gpu/run.yaml
Normal file
46
distributions/tgi/gpu/run.yaml
Normal file
|
|
@ -0,0 +1,46 @@
|
|||
version: '2'
|
||||
built_at: '2024-10-08T17:40:45.325529'
|
||||
image_name: local
|
||||
docker_image: null
|
||||
conda_env: local
|
||||
apis:
|
||||
- shields
|
||||
- agents
|
||||
- models
|
||||
- memory
|
||||
- memory_banks
|
||||
- inference
|
||||
- safety
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: tgi0
|
||||
provider_type: remote::tgi
|
||||
config:
|
||||
url: http://127.0.0.1:5009
|
||||
safety:
|
||||
- provider_id: meta0
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
llama_guard_shield:
|
||||
model: Llama-Guard-3-1B
|
||||
excluded_categories: []
|
||||
disable_input_check: false
|
||||
disable_output_check: false
|
||||
prompt_guard_shield:
|
||||
model: Prompt-Guard-86M
|
||||
memory:
|
||||
- provider_id: meta0
|
||||
provider_type: meta-reference
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta0
|
||||
provider_type: meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ~/.llama/runtime/kvstore.db
|
||||
telemetry:
|
||||
- provider_id: meta0
|
||||
provider_type: meta-reference
|
||||
config: {}
|
||||
Loading…
Add table
Add a link
Reference in a new issue