phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix issue when generating distros (#755)

Browse source 
Addressed comment
https://github.com/meta-llama/llama-stack/pull/723#issuecomment-2581902075.

cc @yanxi0830 

I am not 100% sure if the diff is correct though but this is the result
of running `python llama_stack/scripts/distro_codegen.py`.

---------

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-01-15 08:34:08 -05:00 • committed by GitHub
parent 52a21ce78f
commit 300e6e2702
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 133 additions and 143 deletions
Download patch file Download diff file Expand all files Collapse all files

264
distributions/dependencies.json
View file

@ -1,9 +1,9 @@
{
"hf-serverless": [
"aiohttp",
"bedrock": [
"aiosqlite",
"autoevals",
"blobfile",
"boto3",
"chardet",
"chromadb-client",
"datasets",
@ -11,103 +11,6 @@
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"requests",
"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",
"requests",
"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",
"requests",
"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",
@ -162,7 +65,7 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"tgi": [
"hf-endpoint": [
"aiohttp",
"aiosqlite",
"autoevals",
@ -196,11 +99,11 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"bedrock": [
"hf-serverless": [
"aiohttp",
"aiosqlite",
"autoevals",
"blobfile",
"boto3",
"chardet",
"chromadb-client",
"datasets",
@ -208,6 +111,7 @@
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"matplotlib",
"nltk",
"numpy",
@ -309,35 +213,6 @@
"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",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"ollama": [
"aiohttp",
"aiosqlite",
@ -372,7 +247,7 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"hf-endpoint": [
"tgi": [
"aiohttp",
"aiosqlite",
"autoevals",
@ -405,5 +280,130 @@
"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",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"together",
"tqdm",
"transformers",
"uvicorn",
"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",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"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",
"requests",
"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",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"vllm",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
]
}

10
docs/source/distributions/self_hosted_distro/cerebras.md
View file

@ -1,15 +1,5 @@
---
orphan: true
---
# Cerebras Distribution
```{toctree}
:maxdepth: 2
:hidden:
self
```
The `llamastack/distribution-cerebras` distribution consists of the following provider configurations.
| API | Provider(s) |

2
llama_stack/templates/remote-vllm/vllm.py
View file

@ -134,7 +134,7 @@ def get_distribution_template() -> DistributionTemplate:
"Inference model loaded into the vLLM server",
),
"VLLM_URL": (
"http://host.docker.internal:5100}/v1",
"http://host.docker.internal:5100/v1",
"URL of the vLLM server with the main inference model",
),
"MAX_TOKENS": (