.. |
guided_decoding
|
7a072de555
outline: whitespace pattern
|
7 月之前 |
layers
|
9e73559eba
make use of batched rotary embedding kernels to support long context lora
|
7 月之前 |
model_loader
|
f970f3f3fb
add base class for VLMs
|
7 月之前 |
models
|
f970f3f3fb
add base class for VLMs
|
7 月之前 |
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 月之前 |
pooling_metadata.py
|
be8154a8a0
feat: proper embeddings API with e5-mistral-7b support
|
7 月之前 |
sampling_metadata.py
|
35ae01d7ba
refactor: attention metadata term
|
7 月之前 |
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 月之前 |