Commit c75fba30c for llama.cpp

commit c75fba30cf7d6c39af987205f9bae6cbd3281231
Author: Daniel Bevenius <daniel.bevenius@gmail.com>
Date:   Tue Nov 10 05:08:15 2026 -0800

    cuda : remove unused quantize_cuda_t typedef (#31884)

    This commit removes the unused quantize_cuda_t from quantize.cuh.

    The motivation for this is that the usage of this typedef as a function
    parameter was removed in Commit 74976e1aefd8d64845ae5510674b36079c855c0c
    ("CUDA: remove -sm row, refactor cuBLAS (#24216)") and there is no longer
    any usages of it.

diff --git a/ggml/src/ggml-cuda/quantize.cuh b/ggml/src/ggml-cuda/quantize.cuh
index 5f08dcbfe..cd761f10a 100644
--- a/ggml/src/ggml-cuda/quantize.cuh
+++ b/ggml/src/ggml-cuda/quantize.cuh
@@ -11,11 +11,6 @@
 static_assert(MATRIX_ROW_PADDING %    CUDA_QUANTIZE_BLOCK_SIZE      == 0, "Risk of out-of-bounds access.");
 static_assert(MATRIX_ROW_PADDING % (4*CUDA_QUANTIZE_BLOCK_SIZE_MMQ) == 0, "Risk of out-of-bounds access.");

-typedef void (*quantize_cuda_t)(
-        const float * x, const int32_t * ids, void * vy,
-        ggml_type type_src0, int64_t ne00, int64_t s01, int64_t s02, int64_t s03,
-        int64_t ne0, int64_t ne1, int64_t ne2, int64_t ne3, cudaStream_t stream);
-
 void quantize_row_q8_1_cuda(
         const float * x, const int32_t * ids, void * vy,
         ggml_type type_src0, int64_t ne00, int64_t s01, int64_t s02, int64_t s03,