Merge commit '8dcc3662a292c14f003be2c465895d40c9460511' into concedo_experimental

Keep changes from https://github.com/ggml-org/llama.cpp/pull/18096 without https://github.com/ggml-org/llama.cpp/pull/14904
Reason is to maintain compatibility with 2023 w64devkit

# Conflicts:
# .github/ISSUE_TEMPLATE/019-bug-misc.yml
# examples/model-conversion/scripts/causal/run-org-model.py
# examples/speculative/speculative.cpp
# ggml/src/ggml-cpu/arch-fallback.h
# ggml/src/ggml-cpu/repack.cpp
# ggml/src/ggml-cpu/repack.h
# ggml/src/ggml-hexagon/ggml-hexagon.cpp
# ggml/src/ggml-hexagon/htp/act-ops.c
# ggml/src/ggml-hexagon/htp/htp-msg.h
# ggml/src/ggml-hexagon/htp/hvx-utils.c
# ggml/src/ggml-hexagon/htp/hvx-utils.h
# ggml/src/ggml-hexagon/htp/main.c

src/llama-sampling.cpp

@@ -362,23 +362,39 @@ const char * llama_sampler_name(const struct llama_sampler * smpl) {
 }
 
 void llama_sampler_accept(struct llama_sampler * smpl, llama_token token) {
+    if (!smpl) {
+        return;
+    }
+
     if (smpl->iface->accept) {
         smpl->iface->accept(smpl, token);
     }
 }
 
 void llama_sampler_apply(struct llama_sampler * smpl, struct llama_token_data_array * cur_p) {
+    if (!smpl) {
+        return;
+    }
+
     GGML_ASSERT(smpl->iface->apply);
     smpl->iface->apply(smpl, cur_p);
 }
 
 void llama_sampler_reset(struct llama_sampler * smpl) {
+    if (!smpl) {
+        return;
+    }
+
     if (smpl->iface->reset) {
         smpl->iface->reset(smpl);
     }
 }
 
 struct llama_sampler * llama_sampler_clone(const struct llama_sampler * smpl) {
+    if (!smpl) {
+        return nullptr;
+    }
+
     if (smpl->iface->clone) {
         return smpl->iface->clone(smpl);
     }

src/llama.cpp

@@ -566,6 +566,7 @@ static void llama_params_fit_impl(
             } else {
                 assert(ngl_per_device_high[id].n_layer == n_unassigned);
                 ngl_per_device = ngl_per_device_high;
+                mem            = mem_high;
                 LLAMA_LOG_DEBUG("%s: set ngl_per_device[%d].n_layer=%" PRIu32 "\n", __func__, id, ngl_per_device[id].n_layer);
             }
         }
@@ -653,6 +654,7 @@ static void llama_params_fit_impl(
             }
         } else {
             ngl_per_device = ngl_per_device_high;
+            mem            = mem_high;
             id_dense_start = id_dense_start_high;
             LLAMA_LOG_DEBUG("%s: set ngl_per_device[%zu].(n_layer, n_part)=(%" PRIu32 ", %" PRIu32 "), id_dense_start=%zu\n",
                 __func__, id, ngl_per_device[id].n_layer, ngl_per_device[id].n_part, id_dense_start);