phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 09:32:36 +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

10
distributions/remote-vllm/compose.yaml
View file

@ -1,13 +1,3 @@
# NOTES:
#
# This Docker Compose (and the associated run.yaml) assumes you will be
# running in the default "bridged" network mode.
#
# If you need "host" network mode, please uncomment
# - network_mode: "host"
#
# Similarly change "host.docker.internal" to "localhost" in the run.yaml file
#
services:
vllm-inference:
image: vllm/vllm-openai:latest

6
distributions/remote-vllm/run-with-safety.yaml
View file

@ -1,14 +1,14 @@
version: '2'
built_at: 2024-11-17 14:07:24.568750
built_at: 2024-11-17 14:48:55.487270
image_name: remote-vllm
docker_image: llamastack/distribution-remote-vllm:test-0.0.52rc3
conda_env: null
apis:
- safety
- agents
- telemetry
- safety
- inference
- memory
- inference
providers:
inference:
- provider_id: vllm-inference

6
distributions/remote-vllm/run.yaml
View file

@ -1,14 +1,14 @@
version: '2'
built_at: 2024-11-17 14:07:24.563541
built_at: 2024-11-17 14:48:55.476058
image_name: remote-vllm
docker_image: llamastack/distribution-remote-vllm:test-0.0.52rc3
conda_env: null
apis:
- safety
- agents
- telemetry
- safety
- inference
- memory
- inference
providers:
inference:
- provider_id: vllm-inference