CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921)

Browse Source 
* backend-cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Charles Xu
2024-11-15 01:28:50 +01:00
committed by GitHub
parent ae8de6d50a
commit 1607a5e5b0
9 changed files with 273 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@@ -7254,7 +7254,7 @@ static llama_model::buft_list_t make_cpu_buft_list(llama_model & model) {
auto * cpu_dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);
auto * cpu_reg = ggml_backend_dev_backend_reg(cpu_dev);
auto ggml_backend_dev_get_extra_bufts_fn = (ggml_backend_dev_get_extra_bufts_t)
ggml_backend_reg_get_proc_address(cpu_reg, "ggml_backend_cpu_get_extra_bufts");
ggml_backend_reg_get_proc_address(cpu_reg, "ggml_backend_dev_get_extra_bufts");
if (ggml_backend_dev_get_extra_bufts_fn) {
ggml_backend_buffer_type_t * extra_bufts = ggml_backend_dev_get_extra_bufts_fn(cpu_dev);
while (extra_bufts && *extra_bufts) {