vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update ggml-backend-impl.h

Browse source 
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
slaren 2024-03-16 18:48:45 +01:00 • committed by GitHub
parent c0fe6298ae
commit 8e717e8cb8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-backend-impl.h
View file

@ -103,7 +103,7 @@ extern "C" {
// check if the backend supports an operation // check if the backend supports an operation
bool (*GGML_CALL supports_op)(ggml_backend_t backend, const struct ggml_tensor * op); bool (*GGML_CALL supports_op)(ggml_backend_t backend, const struct ggml_tensor * op);
// check if the backend want to run an operation, even if the weights are allocated in a CPU buffer // check if the backend wants to run an operation, even if the weights are allocated in a CPU buffer
// these should be expensive operations with large batch sizes that may benefit from running on this backend // these should be expensive operations with large batch sizes that may benefit from running on this backend
// even if the weight has to be copied from the CPU temporarily // even if the weight has to be copied from the CPU temporarily
bool (*GGML_CALL offload_op)(ggml_backend_t backend, const struct ggml_tensor * op); bool (*GGML_CALL offload_op)(ggml_backend_t backend, const struct ggml_tensor * op);