phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 01:03:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

modify doc

Browse source
This commit is contained in:
Botao Chen 2024-12-17 14:09:32 -08:00
parent 486c0bc9c8
commit 85d0f5f528
7 changed files with 158 additions and 158 deletions
Download patch file Download diff file Expand all files Collapse all files

256
distributions/dependencies.json
View file

@ -1,9 +1,9 @@
{
"hf-serverless": [
"aiohttp",
"bedrock": [
"aiosqlite",
"autoevals",
"blobfile",
"boto3",
"chardet",
"chromadb-client",
"datasets",
@ -11,100 +11,6 @@
"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",
@ -157,7 +63,7 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"tgi": [
"hf-endpoint": [
"aiohttp",
"aiosqlite",
"autoevals",
@ -190,11 +96,11 @@
"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",
@ -202,6 +108,7 @@
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"matplotlib",
"nltk",
"numpy",
@ -300,34 +207,6 @@
"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",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"ollama": [
"aiohttp",
"aiosqlite",
@ -361,7 +240,7 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"hf-endpoint": [
"tgi": [
"aiohttp",
"aiosqlite",
"autoevals",
@ -393,5 +272,126 @@
"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"
]
}

16
docs/source/distributions/self_hosted_distro/meta-reference-gpu.md
View file

@ -31,9 +31,9 @@ Note that you need access to nvidia GPUs to run this distribution. This distribu
The following environment variables can be configured:
- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `meta-llama/Llama-3.2-3B-Instruct`)
- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `Llama3.2-3B-Instruct`)
- `INFERENCE_CHECKPOINT_DIR`: Directory containing the Meta Reference model checkpoint (default: `null`)
- `SAFETY_MODEL`: Name of the safety (Llama-Guard) model to use (default: `meta-llama/Llama-Guard-3-1B`)
- `SAFETY_MODEL`: Name of the safety (Llama-Guard) model to use (default: `Llama-Guard-3-1B`)
- `SAFETY_CHECKPOINT_DIR`: Directory containing the Llama-Guard model checkpoint (default: `null`)
@ -63,7 +63,7 @@ docker run \
-v ~/.llama:/root/.llama \
llamastack/distribution-meta-reference-gpu \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--env INFERENCE_MODEL=Llama3.2-3B-Instruct
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -75,8 +75,8 @@ docker run \
-v ~/.llama:/root/.llama \
llamastack/distribution-meta-reference-gpu \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--env INFERENCE_MODEL=Llama3.2-3B-Instruct \
--env SAFETY_MODEL=Llama-Guard-3-1B
```
### Via Conda
@ -87,7 +87,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
llama stack build --template meta-reference-gpu --image-type conda
llama stack run distributions/meta-reference-gpu/run.yaml \
--port 5001 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--env INFERENCE_MODEL=Llama3.2-3B-Instruct
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -95,6 +95,6 @@ If you are using Llama Stack Safety / Shield APIs, use:
```bash
llama stack run distributions/meta-reference-gpu/run-with-safety.yaml \
--port 5001 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--env INFERENCE_MODEL=Llama3.2-3B-Instruct \
--env SAFETY_MODEL=meta-Llama-Guard-3-1B
```

14
docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
View file

@ -33,7 +33,7 @@ Note that you need access to nvidia GPUs to run this distribution. This distribu
The following environment variables can be configured:
- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `meta-llama/Llama-3.2-3B-Instruct`)
- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `Llama3.2-3B-Instruct`)
- `INFERENCE_CHECKPOINT_DIR`: Directory containing the Meta Reference model checkpoint (default: `null`)
@ -63,7 +63,7 @@ docker run \
-v ~/.llama:/root/.llama \
llamastack/distribution-meta-reference-quantized-gpu \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--env INFERENCE_MODEL=Llama3.2-3B-Instruct
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -75,8 +75,8 @@ docker run \
-v ~/.llama:/root/.llama \
llamastack/distribution-meta-reference-quantized-gpu \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--env INFERENCE_MODEL=Llama3.2-3B-Instruct \
--env SAFETY_MODEL=meta-Llama-Guard-3-1B
```
### Via Conda
@ -87,7 +87,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
llama stack build --template meta-reference-quantized-gpu --image-type conda
llama stack run distributions/meta-reference-quantized-gpu/run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--env INFERENCE_MODEL=Llama3.2-3B-Instruct
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -95,6 +95,6 @@ If you are using Llama Stack Safety / Shield APIs, use:
```bash
llama stack run distributions/meta-reference-quantized-gpu/run-with-safety.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--env INFERENCE_MODEL=Llama3.2-3B-Instruct \
--env SAFETY_MODEL=Llama-Guard-3-1B
```

12
llama_stack/templates/meta-reference-gpu/doc_template.md
View file

@ -53,7 +53,7 @@ docker run \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--env INFERENCE_MODEL=Llama3.2-3B-Instruct
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -65,8 +65,8 @@ docker run \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--env INFERENCE_MODEL=Llama3.2-3B-Instruct \
--env SAFETY_MODEL=Llama-Guard-3-1B
```
### Via Conda
@ -77,7 +77,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
llama stack build --template {{ name }} --image-type conda
llama stack run distributions/{{ name }}/run.yaml \
--port 5001 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--env INFERENCE_MODEL=Llama3.2-3B-Instruct
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -85,6 +85,6 @@ If you are using Llama Stack Safety / Shield APIs, use:
```bash
llama stack run distributions/{{ name }}/run-with-safety.yaml \
--port 5001 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--env INFERENCE_MODEL=Llama3.2-3B-Instruct \
--env SAFETY_MODEL=Llama-Guard-3-1B
```

4
llama_stack/templates/meta-reference-gpu/meta_reference.py
View file

@ -112,7 +112,7 @@ def get_distribution_template() -> DistributionTemplate:
"Port for the Llama Stack distribution server",
),
"INFERENCE_MODEL": (
"meta-llama/Llama-3.2-3B-Instruct",
"Llama3.2-3B-Instruct",
"Inference model loaded into the Meta Reference server",
),
"INFERENCE_CHECKPOINT_DIR": (
@ -120,7 +120,7 @@ def get_distribution_template() -> DistributionTemplate:
"Directory containing the Meta Reference model checkpoint",
),
"SAFETY_MODEL": (
"meta-llama/Llama-Guard-3-1B",
"Llama-Guard-3-1B",
"Name of the safety (Llama-Guard) model to use",
),
"SAFETY_CHECKPOINT_DIR": (

12
llama_stack/templates/meta-reference-quantized-gpu/doc_template.md
View file

@ -55,7 +55,7 @@ docker run \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--env INFERENCE_MODEL=Llama3.2-3B-Instruct
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -67,8 +67,8 @@ docker run \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--env INFERENCE_MODEL=Llama3.2-3B-Instruct \
--env SAFETY_MODEL=Llama-Guard-3-1B
```
### Via Conda
@ -79,7 +79,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
llama stack build --template {{ name }} --image-type conda
llama stack run distributions/{{ name }}/run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--env INFERENCE_MODEL=Llama3.2-3B-Instruct
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -87,6 +87,6 @@ If you are using Llama Stack Safety / Shield APIs, use:
```bash
llama stack run distributions/{{ name }}/run-with-safety.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--env INFERENCE_MODEL=Llama3.2-3B-Instruct \
--env SAFETY_MODEL=Llama-Guard-3-1B
```

2
llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
View file

@ -84,7 +84,7 @@ def get_distribution_template() -> DistributionTemplate:
"Port for the Llama Stack distribution server",
),
"INFERENCE_MODEL": (
"meta-llama/Llama-3.2-3B-Instruct",
"Llama3.2-3B-Instruct",
"Inference model loaded into the Meta Reference server",
),
"INFERENCE_CHECKPOINT_DIR": (