phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-09 19:58:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

adding fiddlecube as a safety provider to a few distros

Browse source
This commit is contained in:
Kaushik 2025-02-11 15:22:57 -08:00
parent e1ebeea950
commit c9265524aa
16 changed files with 20 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/source/distributions/remote_hosted_distro/nvidia.md
View file

@ -9,7 +9,7 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov
| datasetio | `remote::huggingface`, `inline::localfs` | | datasetio | `remote::huggingface`, `inline::localfs` |
| eval | `inline::meta-reference` | | eval | `inline::meta-reference` |
| inference | `remote::nvidia` | | inference | `remote::nvidia` |
| safety | `inline::llama-guard` | | safety | `remote::fiddlecube` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` | | telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` | | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

2
docs/source/distributions/self_hosted_distro/cerebras.md
View file

@ -9,7 +9,7 @@ The `llamastack/distribution-cerebras` distribution consists of the following pr
| datasetio | `remote::huggingface`, `inline::localfs` | | datasetio | `remote::huggingface`, `inline::localfs` |
| eval | `inline::meta-reference` | | eval | `inline::meta-reference` |
| inference | `remote::cerebras` | | inference | `remote::cerebras` |
| safety | `inline::llama-guard` | | safety | `remote::fiddlecube` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` | | telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` | | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |

2
docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
View file

@ -19,7 +19,7 @@ The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists
| datasetio | `remote::huggingface`, `inline::localfs` | | datasetio | `remote::huggingface`, `inline::localfs` |
| eval | `inline::meta-reference` | | eval | `inline::meta-reference` |
| inference | `inline::meta-reference-quantized` | | inference | `inline::meta-reference-quantized` |
| safety | `inline::llama-guard` | | safety | `remote::fiddlecube` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` | | telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` | | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |

2
docs/source/distributions/self_hosted_distro/sambanova.md
View file

@ -17,7 +17,7 @@ The `llamastack/distribution-sambanova` distribution consists of the following p
|-----|-------------| |-----|-------------|
| agents | `inline::meta-reference` | | agents | `inline::meta-reference` |
| inference | `remote::sambanova` | | inference | `remote::sambanova` |
| safety | `inline::llama-guard` | | safety | `remote::fiddlecube` |
| telemetry | `inline::meta-reference` | | telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` | | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |

2
llama_stack/templates/cerebras/build.yaml
View file

@ -5,7 +5,7 @@ distribution_spec:
inference: inference:
- remote::cerebras - remote::cerebras
safety: safety:
- inline::llama-guard - remote::fiddlecube
vector_io: vector_io:
- inline::faiss - inline::faiss
- remote::chromadb - remote::chromadb

2
llama_stack/templates/cerebras/cerebras.py
View file

@ -22,7 +22,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
def get_distribution_template() -> DistributionTemplate: def get_distribution_template() -> DistributionTemplate:
providers = { providers = {
"inference": ["remote::cerebras"], "inference": ["remote::cerebras"],
"safety": ["inline::llama-guard"], "safety": ["remote::fiddlecube"],
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"], "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"agents": ["inline::meta-reference"], "agents": ["inline::meta-reference"],
"eval": ["inline::meta-reference"], "eval": ["inline::meta-reference"],

4
llama_stack/templates/cerebras/run.yaml
View file

@ -21,8 +21,8 @@ providers:
provider_type: inline::sentence-transformers provider_type: inline::sentence-transformers
config: {} config: {}
safety: safety:
- provider_id: llama-guard - provider_id: fiddlecube
provider_type: inline::llama-guard provider_type: remote::fiddlecube
config: {} config: {}
vector_io: vector_io:
- provider_id: faiss - provider_id: faiss

2
llama_stack/templates/meta-reference-quantized-gpu/build.yaml
View file

@ -9,7 +9,7 @@ distribution_spec:
- remote::chromadb - remote::chromadb
- remote::pgvector - remote::pgvector
safety: safety:
- inline::llama-guard - remote::fiddlecube
agents: agents:
- inline::meta-reference - inline::meta-reference
telemetry: telemetry:

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

@ -22,7 +22,7 @@ def get_distribution_template() -> DistributionTemplate:
providers = { providers = {
"inference": ["inline::meta-reference-quantized"], "inference": ["inline::meta-reference-quantized"],
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"], "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"safety": ["inline::llama-guard"], "safety": ["remote::fiddlecube"],
"agents": ["inline::meta-reference"], "agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"], "telemetry": ["inline::meta-reference"],
"eval": ["inline::meta-reference"], "eval": ["inline::meta-reference"],

4
llama_stack/templates/meta-reference-quantized-gpu/run.yaml
View file

@ -32,8 +32,8 @@ providers:
namespace: null namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/faiss_store.db db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/faiss_store.db
safety: safety:
- provider_id: llama-guard - provider_id: fiddlecube
provider_type: inline::llama-guard provider_type: remote::fiddlecube
config: {} config: {}
agents: agents:
- provider_id: meta-reference - provider_id: meta-reference

2
llama_stack/templates/nvidia/build.yaml
View file

@ -7,7 +7,7 @@ distribution_spec:
vector_io: vector_io:
- inline::faiss - inline::faiss
safety: safety:
- inline::llama-guard - remote::fiddlecube
agents: agents:
- inline::meta-reference - inline::meta-reference
telemetry: telemetry:

2
llama_stack/templates/nvidia/nvidia.py
View file

@ -18,7 +18,7 @@ def get_distribution_template() -> DistributionTemplate:
providers = { providers = {
"inference": ["remote::nvidia"], "inference": ["remote::nvidia"],
"vector_io": ["inline::faiss"], "vector_io": ["inline::faiss"],
"safety": ["inline::llama-guard"], "safety": ["remote::fiddlecube"],
"agents": ["inline::meta-reference"], "agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"], "telemetry": ["inline::meta-reference"],
"eval": ["inline::meta-reference"], "eval": ["inline::meta-reference"],

4
llama_stack/templates/nvidia/run.yaml
View file

@ -26,8 +26,8 @@ providers:
namespace: null namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db
safety: safety:
- provider_id: llama-guard - provider_id: fiddlecube
provider_type: inline::llama-guard provider_type: remote::fiddlecube
config: {} config: {}
agents: agents:
- provider_id: meta-reference - provider_id: meta-reference

2
llama_stack/templates/sambanova/build.yaml
View file

@ -9,7 +9,7 @@ distribution_spec:
- remote::chromadb - remote::chromadb
- remote::pgvector - remote::pgvector
safety: safety:
- inline::llama-guard - remote::fiddlecube
agents: agents:
- inline::meta-reference - inline::meta-reference
telemetry: telemetry:

4
llama_stack/templates/sambanova/run.yaml
View file

@ -29,8 +29,8 @@ providers:
provider_type: remote::pgvector provider_type: remote::pgvector
config: {} config: {}
safety: safety:
- provider_id: llama-guard - provider_id: fiddlecube
provider_type: inline::llama-guard provider_type: remote::fiddlecube
config: {} config: {}
agents: agents:
- provider_id: meta-reference - provider_id: meta-reference

2
llama_stack/templates/sambanova/sambanova.py
View file

@ -24,7 +24,7 @@ def get_distribution_template() -> DistributionTemplate:
providers = { providers = {
"inference": ["remote::sambanova"], "inference": ["remote::sambanova"],
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"], "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"safety": ["inline::llama-guard"], "safety": ["remote::fiddlecube"],
"agents": ["inline::meta-reference"], "agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"], "telemetry": ["inline::meta-reference"],
"tool_runtime": [ "tool_runtime": [