Iwan Kawrakow cf87ad6923 Fix q8_0 repacking issues on AVX2 ...

Q8_0 needs Q0_0_X4, but Q8_0_R8 needs Q8_2_X4.
So, if we decide to repack a Q8_0 MoE tensor to Q8_0_R8,
iqk_moe_fused_mul_unary fails because the activations were
prepared as Q0_0_X4, but we now need Q8_2_X4.

For now a simple fix: just take the slow path, do not repack.

2025-08-19 18:43:36 +03:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Revert "Better CPU prompt processing performance for SWA models (#696)" (#701)

2025-08-17 15:44:02 +03:00

src

Fix q8_0 repacking issues on AVX2

2025-08-19 18:43:36 +03:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00