forked from phoenix-oss/llama-stack-mirror
Update more distribution docs to be simpler and partially codegen'ed
This commit is contained in:
parent
e84d4436b5
commit
2411a44833
51 changed files with 1188 additions and 291 deletions
19
llama_stack/templates/vllm-gpu/build.yaml
Normal file
19
llama_stack/templates/vllm-gpu/build.yaml
Normal file
|
@ -0,0 +1,19 @@
|
|||
version: '2'
|
||||
name: vllm-gpu
|
||||
distribution_spec:
|
||||
description: Use a built-in vLLM engine for running LLM inference
|
||||
docker_image: null
|
||||
providers:
|
||||
inference:
|
||||
- inline::vllm
|
||||
memory:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety:
|
||||
- inline::llama-guard
|
||||
agents:
|
||||
- inline::meta-reference
|
||||
telemetry:
|
||||
- inline::meta-reference
|
||||
image_type: conda
|
Loading…
Add table
Add a link
Reference in a new issue