.. |
activation.cpp
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
attention.cpp
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
cache.cpp
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
cpu_types.hpp
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
cpu_types_vsx.hpp
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
cpu_types_x86.hpp
|
f2b6dc3872
cpu: add support for W8A8 quantization via compressed-tensor (#1017)
|
1 week ago |
dnnl_helper.hpp
|
f2b6dc3872
cpu: add support for W8A8 quantization via compressed-tensor (#1017)
|
1 week ago |
layernorm.cpp
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
pos_encoding.cpp
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
quant.cpp
|
8976805f90
kernel: asymmetric AQ AZP quantization kernels (#1048)
|
1 week ago |
torch_bindings.cpp
|
8976805f90
kernel: asymmetric AQ AZP quantization kernels (#1048)
|
1 week ago |
utils.cpp
|
f2b6dc3872
cpu: add support for W8A8 quantization via compressed-tensor (#1017)
|
1 week ago |