Hugging Face's logo

hfendpoints-images
/
whisper-vllm-gpu

Automatic Speech Recognition
inference_endpoints
audio
transcription
Model card Files Community
1
Morgan Funtowicz commited on
Commit
177efa8
·
1 Parent(s): 8ae7bdd

misc(whisper): update vllm version

Browse files
Files changed (2) hide show
  1. Dockerfile +1 -1
  2. requirements.txt +1 -1
Dockerfile CHANGED
@@ -1,4 +1,4 @@
1
- FROM vllm/vllm-openai:v0.8.3
2
 
3
  RUN --mount=type=bind,from=huggingface/endpoints-sdk:v1.0.0-beta-py312-manylinux,source=/opt/endpoints/dist,target=/opt/endpoints/dist \
4
  --mount=type=bind,source=requirements.txt,target=/tmp/requirements.txt \
 
1
+ FROM vllm/vllm-openai:v0.8.4
2
 
3
  RUN --mount=type=bind,from=huggingface/endpoints-sdk:v1.0.0-beta-py312-manylinux,source=/opt/endpoints/dist,target=/opt/endpoints/dist \
4
  --mount=type=bind,source=requirements.txt,target=/tmp/requirements.txt \
requirements.txt CHANGED
@@ -1,4 +1,4 @@
1
  librosa>=0.11.0
2
  loguru>=0.7.0
3
- vllm>=0.8.3
4
  transformers>=4.50.0
 
1
  librosa>=0.11.0
2
  loguru>=0.7.0
3
+ vllm>=0.8.4
4
  transformers>=4.50.0