CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

sycl : offload of get_rows set to 0 (#10432)

Browse Source
This commit is contained in:
Alberto Cabrera Pérez
2024-11-29 12:38:45 +00:00
committed by GitHub
parent 266b8519ee
commit 0f77aae560
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-sycl/ggml-sycl.cpp
View File

@@ -4493,7 +4493,7 @@ static bool ggml_backend_sycl_device_supports_buft(ggml_backend_dev_t dev, ggml_
static int64_t get_op_batch_size(const ggml_tensor * op) {
switch (op->op) {
case GGML_OP_GET_ROWS:
return op->ne[1]; // this will increse the speed of prefill in test
return 0;
case GGML_OP_MUL_MAT:
return op->ne[1];
case GGML_OP_MUL_MAT_ID: