happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Reenabled i8mm non-generic codepath for ARM

This commit is contained in:
Alberto Cabrera 2026-01-26 13:16:26 +00:00
parent c06f48dcf0
commit aaec188927
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cpu/arch/arm/repack.cpp
View File

@ -805,7 +805,7 @@ void ggml_gemv_q5_K_8x8_q8_K(int n,
UNUSED(ncols_interleaved);
UNUSED(blocklen);
#if 0 && defined(__aarch64__) && defined(__ARM_NEON) && defined(__ARM_FEATURE_DOTPROD)
#if defined(__aarch64__) && defined(__ARM_NEON) && defined(__ARM_FEATURE_DOTPROD)
constexpr int col_pairs = ncols_interleaved / 2;
const uint8x16_t m4b = vdupq_n_u8(0x0f);
const uint8x16_t mone = vdupq_n_u8(1);
@ -3248,7 +3248,7 @@ void ggml_gemm_q5_K_8x8_q8_K(int n,
UNUSED(ncols_interleaved);
UNUSED(blocklen);
#if 0 && defined(__aarch64__) && defined(__ARM_NEON) && defined(__ARM_FEATURE_MATMUL_INT8)
#if defined(__aarch64__) && defined(__ARM_NEON) && defined(__ARM_FEATURE_MATMUL_INT8)
constexpr int q8_k_blocklen = 4;
constexpr int col_pairs = ncols_interleaved / 2;
const uint8x16_t m4b = vdupq_n_u8(0x0f);