phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 19:04:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: vllm starter name

Browse source 
Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-06-04 11:55:26 +02:00
parent ed69c1b3cc
commit af0d6014c1
No known key found for this signature in database
4 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.github/workflows/providers-build.yml vendored
View file

@ -10,6 +10,7 @@ on:
- 'llama_stack/distribution/build.*' - 'llama_stack/distribution/build.*'
- 'llama_stack/distribution/*.sh' - 'llama_stack/distribution/*.sh'
- '.github/workflows/providers-build.yml' - '.github/workflows/providers-build.yml'
- 'llama_stack/templates/**'
pull_request: pull_request:
paths: paths:
- 'llama_stack/cli/stack/build.py' - 'llama_stack/cli/stack/build.py'
@ -17,6 +18,7 @@ on:
- 'llama_stack/distribution/build.*' - 'llama_stack/distribution/build.*'
- 'llama_stack/distribution/*.sh' - 'llama_stack/distribution/*.sh'
- '.github/workflows/providers-build.yml' - '.github/workflows/providers-build.yml'
- 'llama_stack/templates/**'
concurrency: concurrency:
group: ${{ github.workflow }}-${{ github.ref }} group: ${{ github.workflow }}-${{ github.ref }}

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

@ -11,7 +11,7 @@ distribution_spec:
- remote::gemini - remote::gemini
- remote::groq - remote::groq
- remote::sambanova - remote::sambanova
- remote::remote-vllm - remote::vllm
- inline::sentence-transformers - inline::sentence-transformers
vector_io: vector_io:
- inline::sqlite-vec - inline::sqlite-vec

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

@ -48,8 +48,8 @@ providers:
config: config:
url: https://api.sambanova.ai/v1 url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:} api_key: ${env.SAMBANOVA_API_KEY:}
- provider_id: remote-vllm - provider_id: vllm
provider_type: remote::remote-vllm provider_type: remote::vllm
config: config:
url: ${env.VLLM_URL:http://localhost:8000/v1} url: ${env.VLLM_URL:http://localhost:8000/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:4096} max_tokens: ${env.VLLM_MAX_TOKENS:4096}

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

@ -108,7 +108,7 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
SambaNovaImplConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:}"), SambaNovaImplConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:}"),
), ),
( (
"remote-vllm", "vllm",
[], [],
VLLMInferenceAdapterConfig.sample_run_config( VLLMInferenceAdapterConfig.sample_run_config(
url="${env.VLLM_URL:http://localhost:8000/v1}", url="${env.VLLM_URL:http://localhost:8000/v1}",