metal : remove mul_mm_id amax rescaling (#30924) The src1 power-of-two rescale in kernel_mul_mm_id is superseded by the per expert-token amax scaling done in the compute graph (ref: https://github.com/ggml-org/llama.cpp/pull/30861), which keeps the MoE down-projection activations within f16 range before the op runs. Drop the two-stage reduction kernels, their scratch buffer and the GGML_PREC_F32 dispatch added in https://github.com/ggml-org/llama.cpp/pull/26223, as well as the test cases that drive MUL_MAT_ID src1 out of f16 range. Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11866/llama-b11866-bin-macos-arm64.tar.
AI NEWS JOURNAL
llama.cpp releasesAI NEWS / JOURNAL
llama.cpp · b11866
metal : remove mul_mm_id amax rescaling (#30924) The src1 power-of-two rescale in kernel_mul_mm_id is superseded by the per expert-token amax scaling done in the compute graph (ref: https://github.com/ggml-org/llama.cpp/pull/30861), which keeps the MoE down-projection activations within f16 range before the op runs. Drop the two-stage reduction kernels, their scratch buffer and the GGML_PREC_F32 dispatch added in https://github.com/ggml-org/llama.cpp/pull/26223, as well as the test cases that drive MUL_MAT_ID src1 out of f16 range. Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11866/llama-b11866-bin-macos-arm64.tar.