phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 13:09:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Convert TGI

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-17 14:49:41 -08:00
parent 9bb07ce298
commit 028530546f
14 changed files with 485 additions and 160 deletions
Download patch file Download diff file Expand all files Collapse all files

17
llama_stack/templates/tgi/build.yaml
View file

@ -1,12 +1,19 @@
version: '2'
name: tgi
distribution_spec:
description: Use TGI for running LLM inference
description: Use (an external) TGI server for running LLM inference
docker_image: llamastack/distribution-remote-tgi:test-0.0.52rc3
providers:
inference: remote::tgi
inference:
- remote::tgi
memory:
- inline::faiss
- remote::chromadb
- remote::pgvector
safety: inline::llama-guard
agents: inline::meta-reference
telemetry: inline::meta-reference
safety:
- inline::llama-guard
agents:
- inline::meta-reference
telemetry:
- inline::meta-reference
image_type: conda