 AlpinDale
|
766ea79b89
vlm: fix feature size calculation for llava-next models (#1079)
|
2 周之前 |
|
AlpinDale
|
4d14bd1fe5
vlm: add multi-input support for LLaVA and InternVL models (#1002)
|
1 月之前 |
|
AlpinDale
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
1 月之前 |
|
AlpinDale
|
09324ea2ea
vlm: fix incompatibility nested tensors and multi-image llava-next (#941)
|
1 月之前 |
|
AlpinDale
|
8b42b58228
vlm: stack multimodal tensors to represent multiple images within each prompt (#937)
|
1 月之前 |
|
AlpinDale
|
03bd85c950
chore: multi-image support for llava-next (#935)
|
1 月之前 |
|
AlpinDale
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
4 月之前 |
|
AlpinDale
|
3693028340
feat: support for Audio modality (#698)
|
4 月之前 |
|
AlpinDale
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
4 月之前 |
|
AlpinDale
|
2573b36f6a
feat: allow image embeddings for VLM input (#686)
|
4 月之前 |
|
AlpinDale
|
30d7effc7c
feat: add siglip encoder for llava family (#626)
|
4 月之前 |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 月之前 |
