apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

【Fix】fix deepep dispatch (#5036)

Browse Source 
* fix dispatch

* fix dispatch

---------

Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com>
This commit is contained in:
yangjianfengo1
2025-11-17 10:34:01 +08:00
committed by GitHub
parent 3b80a799ab
commit 3afb717995
3 changed files with 21 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
custom_ops/utils/auto_gen_w4afp8_gemm_kernel.py
View File

@@ -174,7 +174,7 @@ for type in dtype:
template_head_file.write(
""" } else { \\
PADDLE_THROW(phi::errors::Unimplemented("W4aFp8 not supported m=%d k=%d experts=%d token_padding_size=%d kBlockN=%d groupsize=%d, please add [%d, %d, %d, %d, %d, %d] to the gemm_case array in the custom_ops/utils/auto_gen_w4afp8_gemm_kernel.py file and recompile it\\n", _M, _K, _EXPERTS, _TokenPaddingSize, _kBlockN, _GROUPSIZE, _M, _K, _EXPERTS, _TokenPaddingSize, _kBlockN, _GROUPSIZE)); \\
PADDLE_THROW(phi::errors::Unimplemented("W4aFp8 not supported m=%d k=%d experts=%d token_padding_size=%d kBlockN=%d groupsize=%d, please add [%d, %d, %d, %d, %d] to the gemm_case array in the custom_ops/utils/auto_gen_w4afp8_gemm_kernel.py file and recompile it\\n", _M, _K, _EXPERTS, _TokenPaddingSize, _kBlockN, _GROUPSIZE, _M, _K, _EXPERTS, _TokenPaddingSize, _GROUPSIZE)); \\
} \\
}"""
)