root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 21:39:52 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

cuda : mark BF16 CONT as unsupported

Browse Source
This commit is contained in:
Georgi Gerganov 2024-08-28 17:08:03 +03:00
parent efe6a83e30
commit 51d964a4ef
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda.cu
View File

@ -2887,7 +2887,9 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
case GGML_OP_SIN: case GGML_OP_SIN:
case GGML_OP_COS: case GGML_OP_COS:
case GGML_OP_CLAMP: case GGML_OP_CLAMP:
return true;
case GGML_OP_CONT: case GGML_OP_CONT:
return op->src[0]->type != GGML_TYPE_BF16;
case GGML_OP_DIAG_MASK_INF: case GGML_OP_DIAG_MASK_INF:
case GGML_OP_SOFT_MAX: case GGML_OP_SOFT_MAX:
return true; return true;