 AlpinDale
|
651678d2df
VLM: use `SequenceData.from_token_counts` to create dummy data (#1093)
|
hai 2 semanas |
|
AlpinDale
|
548e864404
models: add support for QwenVL (#995)
|
hai 1 mes |
|
AlpinDale
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
hai 1 mes |
|
AlpinDale
|
8b42b58228
vlm: stack multimodal tensors to represent multiple images within each prompt (#937)
|
hai 1 mes |
|
AlpinDale
|
653d1a08d4
feat: add support for audio models (#891)
|
hai 1 mes |
|
AlpinDale
|
2f61644f6e
SPMD optimizations (#824)
|
hai 2 meses |
 50h100a
|
9022c6d869
remove progress_bar imports
|
hai 3 meses |
|
50h100a
|
9576096b9d
iterate over weights normally
|
hai 3 meses |
|
AlpinDale
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
hai 5 meses |
|
AlpinDale
|
3693028340
feat: support for Audio modality (#698)
|
hai 5 meses |
|
AlpinDale
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
hai 5 meses |
|
AlpinDale
|
3f712cd287
feat: add progress bar for loading individual weight modules (#640)
|
hai 5 meses |
|
AlpinDale
|
f5cca12da8
feat: multi-image input for minicpmv (#628)
|
hai 5 meses |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 5 meses |
