I3eg1nner f266648fa9 spacemit : fix wrong transpose function for int16 data (#25161) ...

The `sizeof(int16_t)` branch in `permute_transpose_impl` calls
`rvv_transposed_s32_mn_to_nm` instead of `rvv_transposed_s16_mn_to_nm`.
This is a copy-paste bug from the `sizeof(int32_t)` branch above it.

The s32 function uses 32-bit segment load/stores (`vssseg8e32.v`) on 16-bit
data, reading 2x bytes per element and producing completely wrong
transposition results -- 14 out of 16 positions are corrupted for a 4x4
int16 matrix.

The correct function `rvv_transposed_s16_mn_to_nm` already exists (line 390)
and is used elsewhere in flash attention (line 1488).

2026-09-16 14:19:47 +03:00

..

cmake

CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)

2026-09-09 12:50:08 +02:00

include

qwen4exp: add hc ops (#28901)

2026-09-16 16:00:01 +08:00

src

spacemit : fix wrong transpose function for int16 data (#25161)

2026-09-16 14:19:47 +03:00

.gitignore

…

CMakeLists.txt

ggml : bump version to 0.24.0 (ggml/1627)

2026-09-14 16:45:33 +03:00