| .. |
|
backend
|
60e257e5f1
fix: set default values for gpu_memory_utilization and model in vllm_analyze.py
|
2 months ago |
|
cli
|
0f47a22bb3
refactor: update option names and server script for vLLM engine integration
|
2 months ago |
|
data
|
6f8a961087
feat: implement S3 data reader and writer with multi-bucket support
|
6 months ago |
|
model
|
f2553dd89a
fix: add default arguments for port and GPU memory utilization in server.py
|
2 months ago |
|
resources
|
e853541093
feat: update Gradio app to improve Markdown conversion and enhance HTML header
|
5 months ago |
|
utils
|
55eaad224d
feat: add support for vlm 2.5
|
2 months ago |
|
__init__.py
|
cbba27b4f5
refactor: reorganize project structure and update import paths
|
6 months ago |
|
version.py
|
a5687394d5
Update version.py with new version
|
2 months ago |