| .. |
|
guided_decoding
|
0256ed236b
feat: windows support (#790)
|
2 月之前 |
|
layers
|
ba2c3fc88d
feat: add Tencent Hunyuan model support
|
2 月之前 |
|
model_loader
|
0f1af04cf5
frontend: minor logging improvements (#787)
|
2 月之前 |
|
models
|
ba2c3fc88d
feat: add Tencent Hunyuan model support
|
2 月之前 |
|
__init__.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
4 月之前 |
|
_custom_op.py
|
5d37ec1016
suppress tpu import warning (#696)
|
4 月之前 |
|
parameter.py
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
2 月之前 |
|
pooling_metadata.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 月之前 |
|
sampling_metadata.py
|
ed87b5dd32
remove special-case values for prompt sequences
|
3 月之前 |
|
utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 月之前 |
AlpinDale
ba2c3fc88d
feat: add Tencent Hunyuan model support