phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 04:49:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Cerebras Integration

Browse source
This commit is contained in:
Henry Tu 2024-11-20 10:20:28 -08:00
parent 34be07e0df
commit 3838bd1704
16 changed files with 515 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

1
distributions/cerebras/build.yaml Symbolic link
View file

@ -0,0 +1 @@
../../llama_stack/templates/cerebras/build.yaml

16
distributions/cerebras/compose.yaml Normal file
View file

@ -0,0 +1,16 @@
services:
llamastack:
image: llamastack/distribution-cerebras
network_mode: "host"
volumes:
- ~/.llama:/root/.llama
- ./run.yaml:/root/llamastack-run-cerebras.yaml
ports:
- "5000:5000"
entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-cerebras.yaml"
deploy:
restart_policy:
condition: on-failure
delay: 3s
max_attempts: 5
window: 60s

1
distributions/cerebras/run.yaml Symbolic link
View file

@ -0,0 +1 @@
../../llama_stack/templates/cerebras/run.yaml

68
distributions/dependencies.json
View file

@ -36,6 +36,7 @@
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"matplotlib",
"nltk",
"numpy",
@ -47,7 +48,6 @@
"scikit-learn",
"scipy",
"sentencepiece",
"together",
"tqdm",
"transformers",
"uvicorn",
@ -163,33 +163,6 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"bedrock": [
"aiosqlite",
"blobfile",
"boto3",
"chardet",
"chromadb-client",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"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"
],
"meta-reference-gpu": [
"accelerate",
"aiosqlite",
@ -222,19 +195,15 @@
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"meta-reference-quantized-gpu": [
"accelerate",
"together": [
"aiosqlite",
"blobfile",
"chardet",
"chromadb-client",
"fairscale",
"faiss-cpu",
"fastapi",
"fbgemm-gpu",
"fire",
"httpx",
"lm-format-enforcer",
"matplotlib",
"nltk",
"numpy",
@ -246,13 +215,10 @@
"scikit-learn",
"scipy",
"sentencepiece",
"torch",
"torchao==0.5.0",
"torchvision",
"together",
"tqdm",
"transformers",
"uvicorn",
"zmq",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
@ -283,33 +249,5 @@
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
],
"hf-endpoint": [
"aiohttp",
"aiosqlite",
"blobfile",
"chardet",
"chromadb-client",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"matplotlib",
"nltk",
"numpy",
"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"
]
}