 AlpinDale
|
a5bfc2bc3d
VLM: add support for LLaVA-Onevision model (#1100)
|
1 hete |
|
AlpinDale
|
7ce3174039
VLM: refactor blip models to support composite weight loading (#1098)
|
1 hete |
|
AlpinDale
|
651678d2df
VLM: use `SequenceData.from_token_counts` to create dummy data (#1093)
|
1 hete |
|
AlpinDale
|
4d14bd1fe5
vlm: add multi-input support for LLaVA and InternVL models (#1002)
|
1 hónapja |
|
AlpinDale
|
f56d6b396a
vlm: fallback to SDPA for ViT models on CPU backend (#982)
|
1 hónapja |
|
AlpinDale
|
b4a1e2fd02
vlm: add tensor parallel support for vision transformer models (#971)
|
1 hónapja |
|
AlpinDale
|
03bd85c950
chore: multi-image support for llava-next (#935)
|
1 hónapja |
|
AlpinDale
|
653d1a08d4
feat: add support for audio models (#891)
|
1 hónapja |
|
AlpinDale
|
2f61644f6e
SPMD optimizations (#824)
|
2 hónapja |
|
AlpinDale
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
4 hónapja |
|
AlpinDale
|
2573b36f6a
feat: allow image embeddings for VLM input (#686)
|
4 hónapja |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
5 hónapja |
