admin/ai-service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add vLLM audio image for transcription models
All checks were successful
CI / test (push) Successful in 13s
Details
Build and Deploy / build-and-deploy (push) Successful in 22s
Details

Browse Source
This commit is contained in:
Grendgi
2026-06-09 13:38:08 +03:00
parent 76ac9b8896
commit 2ef71a822b
2 changed files with 11 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
deploy/ai-server/docker-compose.audio.yml
View File

@@ -1,6 +1,9 @@
services: services:
qwen-audio: qwen-audio:
image: vllm/vllm-openai:latest build:
context: .
dockerfile: vllm-audio.Dockerfile
image: vllm-audio:local
container_name: qwen-audio container_name: qwen-audio
profiles: profiles:
- qwen-audio - qwen-audio
@@ -53,7 +56,10 @@ services:
start_period: 900s start_period: 900s
voxtral-small: voxtral-small:
image: vllm/vllm-openai:latest build:
context: .
dockerfile: vllm-audio.Dockerfile
image: vllm-audio:local
container_name: voxtral-small container_name: voxtral-small
profiles: profiles:
- voxtral-small - voxtral-small

3
deploy/ai-server/vllm-audio.Dockerfile Normal file
View File

@@ -0,0 +1,3 @@
FROM vllm/vllm-openai:latest
RUN python3 -m pip install --no-cache-dir av soundfile librosa