 AlpinDale
|
46d577f019
vlm: fix siglip layernorm and paligemma weight loading (#991)
|
2 weken geleden |
|
AlpinDale
|
f56d6b396a
vlm: fallback to SDPA for ViT models on CPU backend (#982)
|
2 weken geleden |
|
AlpinDale
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
2 weken geleden |
|
AlpinDale
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 weken geleden |
|
AlpinDale
|
09324ea2ea
vlm: fix incompatibility nested tensors and multi-image llava-next (#941)
|
2 weken geleden |
|
AlpinDale
|
8b42b58228
vlm: stack multimodal tensors to represent multiple images within each prompt (#937)
|
2 weken geleden |
|
AlpinDale
|
c50309d386
model: add support for paligemma2 (#936)
|
2 weken geleden |
|
AlpinDale
|
03bd85c950
chore: multi-image support for llava-next (#935)
|
2 weken geleden |
|
AlpinDale
|
653d1a08d4
feat: add support for audio models (#891)
|
3 weken geleden |
 50h100a
|
9022c6d869
remove progress_bar imports
|
2 maanden geleden |
|
50h100a
|
9576096b9d
iterate over weights normally
|
2 maanden geleden |
|
AlpinDale
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
4 maanden geleden |
|
AlpinDale
|
3693028340
feat: support for Audio modality (#698)
|
4 maanden geleden |
|
AlpinDale
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
4 maanden geleden |
|
AlpinDale
|
3f712cd287
feat: add progress bar for loading individual weight modules (#640)
|
4 maanden geleden |
|
AlpinDale
|
2573b36f6a
feat: allow image embeddings for VLM input (#686)
|
4 maanden geleden |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 maanden geleden |
