 AlpinDale
|
acbdc50a71
fix: `vocab_size` field access in llava
|
5 bulan lalu |
|
AlpinDale
|
e26a4ac698
chore: avoid loading the unused layers and init the VLM up to the required feature space
|
5 bulan lalu |
|
AlpinDale
|
7e99578712
fix: cleanup validation and update docs for vlm
|
5 bulan lalu |
|
AlpinDale
|
c11a8bdaad
fix: calculate max number of multi-modal tokens automatically
|
5 bulan lalu |
|
AlpinDale
|
4f7d212b70
feat: remove vision language config
|
5 bulan lalu |
|
AlpinDale
|
4599c98f99
feat: dynamic image size support for VLMs
|
5 bulan lalu |
 AlpinDale
|
0f4a9ee77b
quantized lm_head (#582)
|
5 bulan lalu |
|
AlpinDale
|
ae04f57ec1
feat: Pipeline Parallel support (#581)
|
6 bulan lalu |
|
AlpinDale
|
3a0fdf7b9b
chore: remove `image_input_type` from VLM config
|
6 bulan lalu |
|
AlpinDale
|
4cdc810b1c
fix: minor TP issues with vision models
|
6 bulan lalu |
|
AlpinDale
|
c0c336aaa3
refactor: registry for processing model inputs; quick_gelu; clip model support
|
6 bulan lalu |
|
AlpinDale
|
c5d8028668
fix: no need to redefine supports_vision and supports_lora in model class
|
6 bulan lalu |
|
AlpinDale
|
56e0b8223c
chore: add base class for LoRA-supported models
|
6 bulan lalu |
|
AlpinDale
|
190276865a
feat: llava-next support
|
6 bulan lalu |
|
AlpinDale
|
8d77c69cbd
feat: support image processor and add llava example
|
6 bulan lalu |
|
AlpinDale
|
24a2d9c2c8
minor llava refactoring
|
6 bulan lalu |
|
AlpinDale
|
f970f3f3fb
add base class for VLMs
|
6 bulan lalu |
|
AlpinDale
|
50b7c13db0
refactor: attention selector (#552)
|
6 bulan lalu |
|
AlpinDale
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
6 bulan lalu |
|
AlpinDale
|
fca911ee0a
vLLM Upstream Sync (#526)
|
7 bulan lalu |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
9 bulan lalu |
