ggml

77dd6c9e - refactor soft_max, add soft_max_back (llama/16472)

refactor soft_max, add soft_max_back (llama/16472) * refactor to support soft_max_ext * fix error and support soft_max_back * rm unused functions * fix format issue --------- Co-authored-by: Zhang Jianyu <zhang.jianyu@outlook.com>