| .. |
|
__init__.py
|
11a02608a3
Add support for quantization with bitsandbytes (#490)
|
%!s(int64=2) %!d(string=hai) anos |
|
adaptive.py
|
724cdfe5e2
Convert hivemind.server to libp2p backend (#470)
|
%!s(int64=3) %!d(string=hai) anos |
|
base.py
|
25e0f407c5
Support torch.bfloat16 in hivemind.compression (#524)
|
%!s(int64=2) %!d(string=hai) anos |
|
floating.py
|
1f54faf82f
Split compression strategies into separate classes (#366)
|
%!s(int64=4) %!d(string=hai) anos |
|
quantization.py
|
25e0f407c5
Support torch.bfloat16 in hivemind.compression (#524)
|
%!s(int64=2) %!d(string=hai) anos |
|
serialization.py
|
11a02608a3
Add support for quantization with bitsandbytes (#490)
|
%!s(int64=2) %!d(string=hai) anos |
Alexander Borzunov
25e0f407c5
Support torch.bfloat16 in hivemind.compression (#524)