mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-22 12:37:53 +00:00
17fdb47e5e
# What does this PR do?
- Makes Llama 70B 3.3 available for fireworks
## Test Plan
```shell
pip install -e . \
&& llama stack build --config distributions/fireworks/build.yaml --image-type conda \
&& llama stack run distributions/fireworks/run.yaml \
--port 5000
```
```python
response = client.inference.chat_completion(
model_id="Llama3.3-70B-Instruct",
messages=[
{"role": "user", "content": "hello world"},
],
)
```
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Ran pre-commit to handle lint / formatting issues.
- [x] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
142 lines
3.9 KiB
YAML
142 lines
3.9 KiB
YAML
version: '2'
|
|
image_name: fireworks
|
|
docker_image: null
|
|
conda_env: fireworks
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- inference
|
|
- memory
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
providers:
|
|
inference:
|
|
- provider_id: fireworks
|
|
provider_type: remote::fireworks
|
|
config:
|
|
url: https://api.fireworks.ai/inference/v1
|
|
api_key: ${env.FIREWORKS_API_KEY}
|
|
- provider_id: sentence-transformers
|
|
provider_type: inline::sentence-transformers
|
|
config: {}
|
|
memory:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/faiss_store.db
|
|
safety:
|
|
- provider_id: llama-guard
|
|
provider_type: inline::llama-guard
|
|
config: {}
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/agents_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
|
|
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/fireworks/trace_store.db}
|
|
eval:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config: {}
|
|
datasetio:
|
|
- provider_id: huggingface
|
|
provider_type: remote::huggingface
|
|
config: {}
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config: {}
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
config: {}
|
|
- provider_id: llm-as-judge
|
|
provider_type: inline::llm-as-judge
|
|
config: {}
|
|
- provider_id: braintrust
|
|
provider_type: inline::braintrust
|
|
config:
|
|
openai_api_key: ${env.OPENAI_API_KEY:}
|
|
metadata_store:
|
|
namespace: null
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-8B-Instruct
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-v3p1-8b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-70B-Instruct
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-v3p1-70b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-v3p1-405b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-1B-Instruct
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-v3p2-1b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-3B-Instruct
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-v3p2-3b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-v3p2-11b-vision-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-v3p2-90b-vision-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.3-70B-Instruct
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-v3p3-70b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-Guard-3-8B
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-guard-3-8b
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-Guard-3-11B-Vision
|
|
provider_id: fireworks
|
|
provider_model_id: fireworks/llama-guard-3-11b-vision
|
|
model_type: llm
|
|
- metadata:
|
|
embedding_dimension: 384
|
|
model_id: all-MiniLM-L6-v2
|
|
provider_id: sentence-transformers
|
|
provider_model_id: null
|
|
model_type: embedding
|
|
shields:
|
|
- params: null
|
|
shield_id: meta-llama/Llama-Guard-3-8B
|
|
provider_id: null
|
|
provider_shield_id: null
|
|
memory_banks: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
eval_tasks: []
|