Georgi Gerganov 3032209758 llama : deny -sm tensor for arches with moe amax rescaling (#31081) ...

The amax POOL_1D reduction spans the whole matmul row, so a device cannot
compute it from an axis-0 split. The Meta split-state case reported
MIRRORED, which gives each device a partial max of its own slice. Drop
that case and deny -sm tensor for the arches which build the amax graph,
see [TAG_MOE_AMAX_SCALE].

Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB)

2026-10-24 13:48:32 +03:00

..

cmake

sycl: fix compiler warnings - missing prototypes, dead code, extra semicolons (#30271)

2026-10-20 00:47:25 -04:00

include

ggml : allow MUL_MAT_ID -1 index to skip the computation (#26631)

2026-10-24 12:15:36 +02:00

src

llama : deny -sm tensor for arches with moe amax rescaling (#31081)

2026-10-24 13:48:32 +03:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml : bump version to 0.27.0

2026-10-15 16:20:14 +03:00