CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : fix batch size for MUL_MAT_ID

Browse Source
This commit is contained in:
Georgi Gerganov
2025-09-08 21:01:25 +03:00
parent c5637cf39c
commit bdff7729b1
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-metal/ggml-metal.m
View File

@@ -6743,8 +6743,9 @@ static bool ggml_backend_metal_device_supports_buft(ggml_backend_dev_t dev, ggml
static int64_t get_op_batch_size(const struct ggml_tensor * op) { static int64_t get_op_batch_size(const struct ggml_tensor * op) {
switch (op->op) { switch (op->op) {
case GGML_OP_MUL_MAT: case GGML_OP_MUL_MAT:
case GGML_OP_MUL_MAT_ID:
return op->ne[1]; return op->ne[1];
case GGML_OP_MUL_MAT_ID:
return op->ne[2];
default: default:
return ggml_nrows(op); return ggml_nrows(op);
} }