llama.cpp
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0()
#10567
Merged
Merged
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0() #10567
max-krasnyansky
merged
1 commit into
ggml-org:master
from
angt:ggml-cpu-replace-aarch64-neon-assembly-with-intrinsics
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_…
aaa6682a
slaren
approved these changes
on 2024-11-30
Login to write a write a comment.
Login via GitHub