phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-28 15:02:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

kill distribution/templates

Browse source
This commit is contained in:
Xi Yan 2024-10-18 17:32:11 -07:00
parent c830235936
commit 955743ba7a
15 changed files with 0 additions and 273 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/distribution/templates/build_configs/local-bedrock-conda-example-build.yaml
View file

@ -1,10 +0,0 @@
name: local-bedrock-conda-example
distribution_spec:
description: Use Amazon Bedrock APIs.
providers:
inference: remote::bedrock
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

15
llama_stack/distribution/templates/build_configs/local-cpu-docker-build.yaml
View file

@ -1,15 +0,0 @@
name: local-cpu
distribution_spec:
description: remote inference + local safety/agents/memory
docker_image: null
providers:
inference:
- remote::ollama
- remote::tgi
- remote::together
- remote::fireworks
safety: meta-reference
agents: meta-reference
memory: meta-reference
telemetry: meta-reference
image_type: docker

10
llama_stack/distribution/templates/build_configs/local-databricks-build.yaml
View file

@ -1,10 +0,0 @@
name: local-databricks
distribution_spec:
description: Use Databricks for running LLM inference
providers:
inference: remote::databricks
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-fireworks-build.yaml
View file

@ -1,10 +0,0 @@
name: local-fireworks
distribution_spec:
description: Use Fireworks.ai for running LLM inference
providers:
inference: remote::fireworks
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-gpu-docker-build.yaml
View file

@ -1,10 +0,0 @@
name: local-gpu
distribution_spec:
description: Use code from `llama_stack` itself to serve all llama stack APIs
providers:
inference: meta-reference
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: docker

10
llama_stack/distribution/templates/build_configs/local-hf-endpoint-build.yaml
View file

@ -1,10 +0,0 @@
name: local-hf-endpoint
distribution_spec:
description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
providers:
inference: remote::hf::endpoint
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-hf-serverless-build.yaml
View file

@ -1,10 +0,0 @@
name: local-hf-serverless
distribution_spec:
description: "Like local, but use Hugging Face Inference API (serverless) for running LLM inference.\nSee https://hf.co/docs/api-inference."
providers:
inference: remote::hf::serverless
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

13
llama_stack/distribution/templates/build_configs/local-ollama-build.yaml
View file

@ -1,13 +0,0 @@
name: local-ollama
distribution_spec:
description: Like local, but use ollama for running LLM inference
providers:
inference: remote::ollama
memory:
- meta-reference
- remote::chromadb
- remote::pgvector
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-tgi-build.yaml
View file

@ -1,10 +0,0 @@
name: local-tgi
distribution_spec:
description: Like local, but use a TGI server for running LLM inference.
providers:
inference: remote::tgi
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

11
llama_stack/distribution/templates/build_configs/local-tgi-chroma-docker-build.yaml
View file

@ -1,11 +0,0 @@
name: local-tgi-chroma
distribution_spec:
description: remote tgi inference + chromadb memory
docker_image: null
providers:
inference: remote::tgi
safety: meta-reference
agents: meta-reference
memory: remote::chromadb
telemetry: meta-reference
image_type: docker

10
llama_stack/distribution/templates/build_configs/local-together-build.yaml
View file

@ -1,10 +0,0 @@
name: local-together
distribution_spec:
description: Use Together.ai for running LLM inference
providers:
inference: remote::together
memory: meta-reference
safety: remote::together
agents: meta-reference
telemetry: meta-reference
image_type: conda

10
llama_stack/distribution/templates/build_configs/local-vllm-build.yaml
View file

@ -1,10 +0,0 @@
name: local-vllm
distribution_spec:
description: Like local, but use vLLM for running LLM inference
providers:
inference: vllm
memory: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda

50
llama_stack/distribution/templates/run_configs/local-run.yaml
View file

@ -1,50 +0,0 @@
version: '2'
built_at: '2024-10-08T17:40:45.325529'
image_name: local
docker_image: null
conda_env: local
apis:
- shields
- agents
- models
- memory
- memory_banks
- inference
- safety
providers:
inference:
- provider_id: meta-reference
provider_type: meta-reference
config:
model: Llama3.1-8B-Instruct
quantization: null
torch_seed: null
max_seq_len: 4096
max_batch_size: 1
safety:
- provider_id: meta-reference
provider_type: meta-reference
config:
llama_guard_shield:
model: Llama-Guard-3-1B
excluded_categories: []
disable_input_check: false
disable_output_check: false
prompt_guard_shield:
model: Prompt-Guard-86M
memory:
- provider_id: meta-reference
provider_type: meta-reference
config: {}
agents:
- provider_id: meta-reference
provider_type: meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta-reference
provider_type: meta-reference
config: {}

48
llama_stack/distribution/templates/run_configs/local-tgi-chroma-run.yaml
View file

@ -1,48 +0,0 @@
version: '2'
built_at: '2024-10-08T17:40:45.325529'
image_name: local
docker_image: null
conda_env: local
apis:
- shields
- agents
- models
- memory
- memory_banks
- inference
- safety
providers:
inference:
- provider_id: tgi0
provider_type: remote::tgi
config:
url: http://127.0.0.1:5009
safety:
- provider_id: meta-reference
provider_type: meta-reference
config:
llama_guard_shield:
model: Llama-Guard-3-1B
excluded_categories: []
disable_input_check: false
disable_output_check: false
prompt_guard_shield:
model: Prompt-Guard-86M
memory:
- provider_id: chroma0
provider_type: remote::chromadb
config:
host: localhost
port: 6000
agents:
- provider_id: meta-reference
provider_type: meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta-reference
provider_type: meta-reference
config: {}

46
llama_stack/distribution/templates/run_configs/local-tgi-run.yaml
View file

@ -1,46 +0,0 @@
version: '2'
built_at: '2024-10-08T17:40:45.325529'
image_name: local
docker_image: null
conda_env: local
apis:
- shields
- agents
- models
- memory
- memory_banks
- inference
- safety
providers:
inference:
- provider_id: tgi0
provider_type: remote::tgi
config:
url: http://127.0.0.1:5009
safety:
- provider_id: meta-reference
provider_type: meta-reference
config:
llama_guard_shield:
model: Llama-Guard-3-1B
excluded_categories: []
disable_input_check: false
disable_output_check: false
prompt_guard_shield:
model: Prompt-Guard-86M
memory:
- provider_id: meta-reference
provider_type: meta-reference
config: {}
agents:
- provider_id: meta-reference
provider_type: meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/kvstore.db
telemetry:
- provider_id: meta-reference
provider_type: meta-reference
config: {}