PR #1067 Support transformers loading quantized moe model

Support transformers loading quantized moe model

mengniwang95 committed 33 days ago

add ut

mengniwang95 committed 32 days ago

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 32 days ago

Update test_moe_model.py

mengniwang95 committed 32 days ago

Update test_moe_model.py

mengniwang95 committed 32 days ago

Update convert_model.py

mengniwang95 committed 32 days ago

fix ut and add cuda ut

mengniwang95 committed 31 days ago

[pre-commit.ci] auto fixes from pre-commit.com hooks

pre-commit-ci[bot] committed 31 days ago

Merge branch 'main' into mengni/tf_load

mengniwang95 committed 31 days ago

auto-round Support transformers loading quantized moe model #1067 Merged