| .. |
|
guided_decoding
|
fde2cda047
chore: update outlines integration from `FSM` to `Guide`
|
7 月之前 |
|
layers
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
7 月之前 |
|
model_loader
|
690110a051
feat: bitsandbytes quantization
|
7 月之前 |
|
models
|
ab5ffb228c
fp8: `act_scale` -> `input_scale`
|
7 月之前 |
|
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 月之前 |
|
_custom_op.py
|
814c1ddeba
feat: add CustomOp interface for device portability
|
7 月之前 |
|
pooling_metadata.py
|
be8154a8a0
feat: proper embeddings API with e5-mistral-7b support
|
7 月之前 |
|
sampling_metadata.py
|
b9a5a0ae79
fix: avoid copying prompt/output tokens if penalties arent used
|
7 月之前 |
|
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 月之前 |
AlpinDale
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)