"tests/vscode:/vscode.git/clone" did not exist on "325e795a18bec66595bca59708b42b726c8f8d22"
  • Daniël de Kok's avatar
    Factor out sharding of packed tensors (#2059) · bcb3faa1
    Daniël de Kok authored
    For Phi-3-Small I need to shard a packed QKV bias tensor, for which
    I implemented the `Weights.get_packed_sharded` method. However, this
    method can also replace the `Weights._get_qweight` method and the
    custom sharding code from `Weights.get_weights_col_packed`.
    bcb3faa1
weights.py 30.2 KB