phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 07:33:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge-related changes.

Browse source
This commit is contained in:
ilya-kolchinsky 2025-04-02 19:56:44 +02:00
commit 60e9f46856
456 changed files with 38636 additions and 10892 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/templates/together/doc_template.md
View file

@ -49,9 +49,10 @@ You can do this via Conda (build code) or Docker which has a pre-built image.
This method allows you to get started quickly without having to build the distribution code.
```bash
LLAMA_STACK_PORT=5001
LLAMA_STACK_PORT=8321
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \

25
llama_stack/templates/together/run-with-safety.yaml
View file

@ -17,7 +17,7 @@ providers:
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY}
api_key: ${env.TOGETHER_API_KEY:}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -51,20 +51,32 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -98,7 +110,8 @@ providers:
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config: {}
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
preprocessing:
- provider_id: basic
provider_type: inline::basic

28
llama_stack/templates/together/run.yaml
View file

@ -17,7 +17,7 @@ providers:
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY}
api_key: ${env.TOGETHER_API_KEY:}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -32,7 +32,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -45,20 +46,32 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -92,7 +105,8 @@ providers:
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config: {}
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
preprocessing:
- provider_id: basic
provider_type: inline::basic

8
llama_stack/templates/together/together.py
View file

@ -20,7 +20,11 @@ from llama_stack.providers.inline.inference.sentence_transformers import (
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.together import TogetherImplConfig
from llama_stack.providers.remote.inference.together.models import MODEL_ENTRIES
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
from llama_stack.templates.template import (
DistributionTemplate,
RunConfigSettings,
get_model_registry,
)
def get_distribution_template() -> DistributionTemplate:
@ -168,7 +172,7 @@ def get_distribution_template() -> DistributionTemplate:
},
run_config_env_vars={
"LLAMA_STACK_PORT": (
"5001",
"8321",
"Port for the Llama Stack distribution server",
),
"TOGETHER_API_KEY": (