.. |
__init__.py
|
11a02608a3
Add support for quantization with bitsandbytes (#490)
|
2 years ago |
adaptive.py
|
724cdfe5e2
Convert hivemind.server to libp2p backend (#470)
|
3 years ago |
base.py
|
25e0f407c5
Support torch.bfloat16 in hivemind.compression (#524)
|
2 years ago |
floating.py
|
1f54faf82f
Split compression strategies into separate classes (#366)
|
4 years ago |
quantization.py
|
25e0f407c5
Support torch.bfloat16 in hivemind.compression (#524)
|
2 years ago |
serialization.py
|
11a02608a3
Add support for quantization with bitsandbytes (#490)
|
2 years ago |