Lucas Wilkinson cd7edc4e87

[Bugfix] Fix empty (nullptr) channelwise scales when loading wNa16 using compressed tensors (#6798)

2024-07-25 15:05:09 -07:00

..

schemes

[Bugfix] Fix empty (nullptr) channelwise scales when loading wNa16 using compressed tensors (#6798)

2024-07-25 15:05:09 -07:00

__init__.py

[Kernel] Initial Activation Quantization Support (#4525)

2024-05-23 21:29:18 +00:00

compressed_tensors.py

[ Misc ] fp8-marlin channelwise via compressed-tensors (#6524)

2024-07-25 09:46:04 -07:00

utils.py

[Misc] Add ignored layers for fp8 quantization (#6657)

2024-07-23 14:04:04 -04:00