Commit fd27b2034 for llama.cpp

commit fd27b2034905f8dadd8bd6d2cc44595f4929d391
Author: Yonghye Kwon <developer.0hye@gmail.com>
Date:   Sat Nov 7 12:05:24 2026 +0900

    meta : raise the compute view limit for buffers with few tensors (#31447)

    * ggml-backend-meta : minimum number of compute views per buffer

    Assisted-by: Claude Opus 5.5

    * tests : revert the deepseek41 test model to 6 layers

    Assisted-by: Claude Opus 5.5

diff --git a/ggml/src/ggml-backend-meta.cpp b/ggml/src/ggml-backend-meta.cpp
index aba004646..991398316 100644
--- a/ggml/src/ggml-backend-meta.cpp
+++ b/ggml/src/ggml-backend-meta.cpp
@@ -1808,13 +1808,14 @@ static ggml_backend_buffer_t ggml_backend_meta_buffer_type_alloc_buffer_n(ggml_b
     const size_t n_simple_bufts = ggml_backend_meta_buft_n_bufts(buft);

     constexpr size_t compute_headroom = 16; // Maximum number of views per statically allocated tensor that can be created between evals.
+    constexpr size_t compute_headroom_min = 256; // A buffer with few tensors can still get many views, e.g. a KV cache shared by many layers.
     const ggml_init_params params_static = {
         /*.mem_size   =*/ n_tensors * ggml_tensor_overhead(),
         /*.mem_buffer =*/ nullptr,
         /*.no_alloc   =*/ true,
     };
     const ggml_init_params params_compute = {
-        /*.mem_size   =*/ compute_headroom * n_tensors * ggml_tensor_overhead(),
+        /*.mem_size   =*/ std::max(compute_headroom * n_tensors, compute_headroom_min) * ggml_tensor_overhead(),
         /*.mem_buffer =*/ nullptr,
         /*.no_alloc   =*/ true,
     };