Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-04 02:37:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

ggml : add MUL_MAT to the list of ops that may need additional memory (for WebGPU) (#28071)

Browse Source 
Co-authored-by: Stanisław Szymczyk <[email protected]>
This commit is contained in:
fairydreaming
2026-08-31 10:17:23 +02:00
committed by GitHub
co-authored by Stanisław Szymczyk
parent daef7b6874
commit 557614e029
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-backend.cpp
+1
View File
@@ -2115,6 +2115,7 @@ ggml_backend_t ggml_backend_sched_get_tensor_backend(ggml_backend_sched_t sched,
bool ggml_backend_op_alloc_size_may_expand(enum ggml_op op) {
switch (op) {
case GGML_OP_FLASH_ATTN_EXT:
case GGML_OP_MUL_MAT:
case GGML_OP_MUL_MAT_ID:
case GGML_OP_CUMSUM:
case GGML_OP_ARGSORT: