phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update provider types and prefix with inline::

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-12 12:54:44 -08:00
parent 896b304e62
commit 2c294346ae
12 changed files with 32 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

2
distributions/dell-tgi/run.yaml
View file

@ -29,7 +29,7 @@ providers:
model: Prompt-Guard-86M model: Prompt-Guard-86M
memory: memory:
- provider_id: meta0 - provider_id: meta0
provider_type: inline::meta-reference provider_type: inline::faiss
config: {} config: {}
agents: agents:
- provider_id: meta0 - provider_id: meta0

4
llama_stack/templates/bedrock/build.yaml
View file

@ -5,5 +5,5 @@ distribution_spec:
inference: remote::bedrock inference: remote::bedrock
memory: inline::faiss memory: inline::faiss
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

6
llama_stack/templates/fireworks/build.yaml
View file

@ -4,8 +4,8 @@ distribution_spec:
providers: providers:
inference: remote::fireworks inference: remote::fireworks
memory: memory:
- meta-reference - inline::faiss
- remote::weaviate - remote::weaviate
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

4
llama_stack/templates/hf-endpoint/build.yaml
View file

@ -5,5 +5,5 @@ distribution_spec:
inference: remote::hf::endpoint inference: remote::hf::endpoint
memory: inline::faiss memory: inline::faiss
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

4
llama_stack/templates/hf-serverless/build.yaml
View file

@ -5,5 +5,5 @@ distribution_spec:
inference: remote::hf::serverless inference: remote::hf::serverless
memory: inline::faiss memory: inline::faiss
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

8
llama_stack/templates/inline-vllm/build.yaml
View file

@ -3,11 +3,11 @@ distribution_spec:
docker_image: pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime docker_image: pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime
description: Use code from `llama_stack` itself to serve all llama stack APIs description: Use code from `llama_stack` itself to serve all llama stack APIs
providers: providers:
inference: meta-reference inference: inline::meta-reference
memory: memory:
- meta-reference - inline::faiss
- remote::chromadb - remote::chromadb
- remote::pgvector - remote::pgvector
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

6
llama_stack/templates/meta-reference-gpu/build.yaml
View file

@ -5,9 +5,9 @@ distribution_spec:
providers: providers:
inference: meta-reference inference: meta-reference
memory: memory:
- meta-reference - inline::faiss
- remote::chromadb - remote::chromadb
- remote::pgvector - remote::pgvector
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

6
llama_stack/templates/meta-reference-quantized-gpu/build.yaml
View file

@ -5,9 +5,9 @@ distribution_spec:
providers: providers:
inference: meta-reference-quantized inference: meta-reference-quantized
memory: memory:
- meta-reference - inline::faiss
- remote::chromadb - remote::chromadb
- remote::pgvector - remote::pgvector
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

6
llama_stack/templates/ollama/build.yaml
View file

@ -4,9 +4,9 @@ distribution_spec:
providers: providers:
inference: remote::ollama inference: remote::ollama
memory: memory:
- meta-reference - inline::faiss
- remote::chromadb - remote::chromadb
- remote::pgvector - remote::pgvector
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

6
llama_stack/templates/remote-vllm/build.yaml
View file

@ -4,9 +4,9 @@ distribution_spec:
providers: providers:
inference: remote::vllm inference: remote::vllm
memory: memory:
- meta-reference - inline::faiss
- remote::chromadb - remote::chromadb
- remote::pgvector - remote::pgvector
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

6
llama_stack/templates/tgi/build.yaml
View file

@ -4,9 +4,9 @@ distribution_spec:
providers: providers:
inference: remote::tgi inference: remote::tgi
memory: memory:
- meta-reference - inline::faiss
- remote::chromadb - remote::chromadb
- remote::pgvector - remote::pgvector
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference

6
llama_stack/templates/together/build.yaml
View file

@ -4,8 +4,8 @@ distribution_spec:
providers: providers:
inference: remote::together inference: remote::together
memory: memory:
- meta-reference - inline::faiss
- remote::weaviate - remote::weaviate
safety: inline::llama-guard safety: inline::llama-guard
agents: meta-reference agents: inline::meta-reference
telemetry: meta-reference telemetry: inline::meta-reference