phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

add 3.3 to together inference provider (#729)

Browse source 
# What does this PR do?

- add llama3.3 model for together
- fix fireworks distro_codegen

```
python llama_stack/scripts/distro_codegen.py
```

## Test Plan

<img width="1132" alt="image"
src="https://github.com/user-attachments/assets/bf94b933-9200-4e73-878e-d1a95d450a88"
/>

**Tests**
```
pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.3-70B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
```
<img width="1139" alt="image"
src="https://github.com/user-attachments/assets/407dc98b-8de3-4841-8cb1-75e4b5128544"
/>


## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] 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.
This commit is contained in:
Xi Yan 2025-01-06 15:39:41 -08:00 • committed by GitHub
parent 7a90fc5854
commit 7a4383e4c1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 140 additions and 129 deletions
Download patch file Download diff file Expand all files Collapse all files

256
distributions/dependencies.json
View file

@ -1,9 +1,9 @@
{
"bedrock": [
"hf-serverless": [
"aiohttp",
"aiosqlite",
"autoevals",
"blobfile",
"boto3",
"chardet",
"chromadb-client",
"datasets",
@ -11,6 +11,100 @@
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"together": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"scikit-learn",
"scipy",
"sentencepiece",
"together",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"vllm-gpu": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"vllm",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"remote-vllm": [
"aiosqlite",
"blobfile",
"chardet",
"chromadb-client",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
@ -63,7 +157,7 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"hf-endpoint": [
"tgi": [
"aiohttp",
"aiosqlite",
"autoevals",
@ -96,11 +190,11 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"hf-serverless": [
"aiohttp",
"bedrock": [
"aiosqlite",
"autoevals",
"blobfile",
"boto3",
"chardet",
"chromadb-client",
"datasets",
@ -108,7 +202,6 @@
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"matplotlib",
"nltk",
"numpy",
@ -207,6 +300,34 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"cerebras": [
"aiosqlite",
"blobfile",
"cerebras_cloud_sdk",
"chardet",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"ollama": [
"aiohttp",
"aiosqlite",
@ -240,7 +361,7 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"tgi": [
"hf-endpoint": [
"aiohttp",
"aiosqlite",
"autoevals",
@ -272,126 +393,5 @@
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"together": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"scikit-learn",
"scipy",
"sentencepiece",
"together",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"remote-vllm": [
"aiosqlite",
"blobfile",
"chardet",
"chromadb-client",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"vllm-gpu": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"vllm",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"cerebras": [
"aiosqlite",
"blobfile",
"cerebras_cloud_sdk",
"chardet",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
]
}

1
docs/source/distributions/self_hosted_distro/fireworks.md
View file

@ -42,6 +42,7 @@ The following models are available by default:
- `meta-llama/Llama-3.2-3B-Instruct (fireworks/llama-v3p2-3b-instruct)`
- `meta-llama/Llama-3.2-11B-Vision-Instruct (fireworks/llama-v3p2-11b-vision-instruct)`
- `meta-llama/Llama-3.2-90B-Vision-Instruct (fireworks/llama-v3p2-90b-vision-instruct)`
- `meta-llama/Llama-3.3-70B-Instruct (fireworks/llama-v3p3-70b-instruct)`
- `meta-llama/Llama-Guard-3-8B (fireworks/llama-guard-3-8b)`
- `meta-llama/Llama-Guard-3-11B-Vision (fireworks/llama-guard-3-11b-vision)`

1
docs/source/distributions/self_hosted_distro/together.md
View file

@ -41,6 +41,7 @@ The following models are available by default:
- `meta-llama/Llama-3.2-3B-Instruct`
- `meta-llama/Llama-3.2-11B-Vision-Instruct`
- `meta-llama/Llama-3.2-90B-Vision-Instruct`
- `meta-llama/Llama-3.3-70B-Instruct`
- `meta-llama/Llama-Guard-3-8B`
- `meta-llama/Llama-Guard-3-11B-Vision`

2
llama_stack/providers/remote/inference/fireworks/config.py
View file

@ -22,7 +22,7 @@ class FireworksImplConfig(BaseModel):
)
@classmethod
def sample_run_config(cls, __distro_dir__: str) -> Dict[str, Any]:
def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
return {
"url": "https://api.fireworks.ai/inference/v1",
"api_key": "${env.FIREWORKS_API_KEY}",

4
llama_stack/providers/remote/inference/together/together.py
View file

@ -79,6 +79,10 @@ MODEL_ALIASES = [
"meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
CoreModelId.llama3_2_90b_vision_instruct.value,
),
build_model_alias(
"meta-llama/Llama-3.3-70B-Instruct-Turbo",
CoreModelId.llama3_3_70b_instruct.value,
),
build_model_alias(
"meta-llama/Meta-Llama-Guard-3-8B",
CoreModelId.llama_guard_3_8b.value,

5
llama_stack/templates/together/run.yaml
View file

@ -105,6 +105,11 @@ models:
provider_id: together
provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: together
provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-8B
provider_id: together