phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama stack distributions / templates / docker refactor (#266)

Browse source 
* docker compose ollama

* comment

* update compose file

* readme for distributions

* readme

* move distribution folders

* move distribution/templates to distributions/

* rename

* kill distribution/templates

* readme

* readme

* build/developer cookbook/new api provider

* developer cookbook

* readme

* readme

* [bugfix] fix case for agent when memory bank registered without specifying provider_id (#264)

* fix case where memory bank is registered without provider_id

* memory test

* agents unit test

* Add an option to not use elastic agents for meta-reference inference (#269)

* Allow overridding checkpoint_dir via config

* Small rename

* Make all methods `async def` again; add completion() for meta-reference (#270)

PR #201 had made several changes while trying to fix issues with getting the stream=False branches of inference and agents API working. As part of this, it made a change which was slightly gratuitous. Namely, making chat_completion() and brethren "def" instead of "async def".

The rationale was that this allowed the user (within llama-stack) of this to use it as:

```
async for chunk in api.chat_completion(params)
```

However, it causes unnecessary confusion for several folks. Given that clients (e.g., llama-stack-apps) anyway use the SDK methods (which are completely isolated) this choice was not ideal. Let's revert back so the call now looks like:

```
async for chunk in await api.chat_completion(params)
```

Bonus: Added a completion() implementation for the meta-reference provider. Technically should have been another PR :)

* Improve an important error message

* update ollama for llama-guard3

* Add vLLM inference provider for OpenAI compatible vLLM server (#178)

This PR adds vLLM inference provider for OpenAI compatible vLLM server.

* Create .readthedocs.yaml

Trying out readthedocs

* Update event_logger.py (#275)

spelling error

* vllm

* build templates

* delete templates

* tmp add back build to avoid merge conflicts

* vllm

* vllm

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
Co-authored-by: Yuan Tang <terrytangyuan@gmail.com>
Co-authored-by: raghotham <rsm@meta.com>
Co-authored-by: nehal-a2z <nehal@coderabbit.ai>
This commit is contained in:
Xi Yan 2024-10-21 11:17:53 -07:00 • committed by GitHub
parent c995219731
commit 23210e8679
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
32 changed files with 850 additions and 335 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/cli/stack/build.py
View file

@ -13,7 +13,7 @@ from functools import lru_cache
from pathlib import Path
TEMPLATES_PATH = (
Path(os.path.relpath(__file__)).parent.parent.parent / "distribution" / "templates"
Path(os.path.relpath(__file__)).parent.parent.parent.parent / "distributions"
)

28
llama_stack/distribution/docker/README.md
View file

@ -1,28 +0,0 @@
# Docker Compose Scripts
This folder contains scripts to enable starting a distribution using `docker compose`.
#### Example: TGI Inference Adapter
```
$ 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
```

55
llama_stack/distribution/docker/tgi/compose.yaml
View file

@ -1,55 +0,0 @@
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-local-cpu:
depends_on:
text-generation-inference:
condition: service_healthy
image: llamastack-local-cpu
network_mode: "host"
volumes:
- ~/.llama:/root/.llama
# Link to TGI run.yaml file
- ./tgi-run.yaml:/root/llamastack-run-tgi.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/llamastack-run-tgi.yaml"
restart_policy:
condition: on-failure
delay: 3s
max_attempts: 5
window: 60s

46
llama_stack/distribution/docker/tgi/tgi-run.yaml
View file

@ -1,46 +0,0 @@
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: {}

10
llama_stack/distribution/templates/build_configs/local-bedrock-conda-example-build.yaml
View file

@ -1,10 +0,0 @@
name: local-bedrock-conda-example
distribution_spec:
description: Use Amazon Bedrock APIs.
providers:
inference: remote::bedrock
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

15
llama_stack/distribution/templates/build_configs/local-cpu-docker-build.yaml
View file

@ -1,15 +0,0 @@
name: local-cpu
distribution_spec:
description: remote inference + local safety/agents/memory
docker_image: null
providers:
inference:
- remote::ollama
- remote::tgi
- remote::together
- remote::fireworks
safety: meta-reference
agents: meta-reference
memory: meta-reference
telemetry: meta-reference
image_type: docker

10
llama_stack/distribution/templates/build_configs/local-databricks-build.yaml
View file

@ -1,10 +0,0 @@
name: local-databricks
distribution_spec:
description: Use Databricks for running LLM inference
providers:
inference: remote::databricks
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-fireworks-build.yaml
View file

@ -1,10 +0,0 @@
name: local-fireworks
distribution_spec:
description: Use Fireworks.ai for running LLM inference
providers:
inference: remote::fireworks
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-gpu-docker-build.yaml
View file

@ -1,10 +0,0 @@
name: local-gpu
distribution_spec:
description: Use code from `llama_stack` itself to serve all llama stack APIs
providers:
inference: meta-reference
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: docker

10
llama_stack/distribution/templates/build_configs/local-hf-endpoint-build.yaml
View file

@ -1,10 +0,0 @@
name: local-hf-endpoint
distribution_spec:
description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
providers:
inference: remote::hf::endpoint
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-hf-serverless-build.yaml
View file

@ -1,10 +0,0 @@
name: local-hf-serverless
distribution_spec:
description: "Like local, but use Hugging Face Inference API (serverless) for running LLM inference.\nSee https://hf.co/docs/api-inference."
providers:
inference: remote::hf::serverless
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-ollama-build.yaml
View file

@ -1,10 +0,0 @@
name: local-ollama
distribution_spec:
description: Like local, but use ollama for running LLM inference
providers:
inference: remote::ollama
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-tgi-build.yaml
View file

@ -1,10 +0,0 @@
name: local-tgi
distribution_spec:
description: Like local, but use a TGI server for running LLM inference.
providers:
inference: remote::tgi
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

11
llama_stack/distribution/templates/build_configs/local-tgi-chroma-docker-build.yaml
View file

@ -1,11 +0,0 @@
name: local-tgi-chroma
distribution_spec:
description: remote tgi inference + chromadb memory
docker_image: null
providers:
inference: remote::tgi
safety: meta-reference
agents: meta-reference
memory: remote::chromadb
telemetry: meta-reference
image_type: docker

10
llama_stack/distribution/templates/build_configs/local-together-build.yaml
View file

@ -1,10 +0,0 @@
name: local-together
distribution_spec:
description: Use Together.ai for running LLM inference
providers:
inference: remote::together
memory: meta-reference
safety: remote::together
agents: meta-reference
telemetry: meta-reference
image_type: conda

50
llama_stack/distribution/templates/run_configs/local-run.yaml
View file

@ -1,50 +0,0 @@
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: meta-reference
provider_type: meta-reference
config:
model: Llama3.1-8B-Instruct
quantization: null
torch_seed: null
max_seq_len: 4096
max_batch_size: 1
safety:
- provider_id: meta-reference
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: meta-reference
provider_type: meta-reference
config: {}
agents:
- provider_id: meta-reference
provider_type: meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta-reference
provider_type: meta-reference
config: {}

46
llama_stack/distribution/templates/run_configs/local-tgi-run.yaml
View file

@ -1,46 +0,0 @@
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: meta-reference
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: meta-reference
provider_type: meta-reference
config: {}
agents:
- provider_id: meta-reference
provider_type: meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta-reference
provider_type: meta-reference
config: {}

18
llama_stack/providers/registry/inference.py
View file

@ -60,15 +60,15 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.adapters.inference.ollama",
),
),
# remote_provider_spec(
# api=Api.inference,
# adapter=AdapterSpec(
# adapter_type="vllm",
# pip_packages=["openai"],
# module="llama_stack.providers.adapters.inference.vllm",
# config_class="llama_stack.providers.adapters.inference.vllm.VLLMImplConfig",
# ),
# ),
# remote_provider_spec(
# api=Api.inference,
# adapter=AdapterSpec(
# adapter_type="vllm",
# pip_packages=["openai"],
# module="llama_stack.providers.adapters.inference.vllm",
# config_class="llama_stack.providers.adapters.inference.vllm.VLLMImplConfig",
# ),
# ),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(