Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	docs/build.md
#	docs/ops.md
#	docs/ops/CPU.csv
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-cpu/repack.cpp
#	ggml/src/ggml-cpu/repack.h
#	src/llama-quant.cpp
#	tests/test-json-schema-to-grammar.cpp

src/llama-grammar.cpp

@@ -626,7 +626,7 @@ const char * llama_grammar_parser::parse_sequence(
                 throw std::runtime_error(std::string("expecting an int at ") + pos);
             }
             const char * int_end = parse_int(pos);
-            uint64_t min_times = std::stoul(std::string(pos, int_end - pos));
+            uint64_t min_times = std::stoull(std::string(pos, int_end - pos));
             pos = parse_space(int_end, is_nested);
 
             uint64_t max_times = UINT64_MAX; // default: no max limit
@@ -639,7 +639,7 @@ const char * llama_grammar_parser::parse_sequence(
 
                 if (is_digit_char(*pos)) {
                     const char * int_end = parse_int(pos);
-                    max_times = std::stoul(std::string(pos, int_end - pos));
+                    max_times = std::stoull(std::string(pos, int_end - pos));
                     pos = parse_space(int_end, is_nested);
                 }
 

src/models/mamba-base.cpp

@@ -168,8 +168,9 @@ ggml_tensor * llm_build_mamba_base::build_mamba2_layer(llm_graph_input_rs * inp,
     GGML_ASSERT(n_seqs != 0);
     GGML_ASSERT(ubatch.equal_seqs());
     GGML_ASSERT(ubatch.n_tokens == n_seq_tokens * n_seqs);
-    GGML_ASSERT(d_inner % n_head == 0);
-    GGML_ASSERT(d_inner % (n_group*d_state) == 0);
+    GGML_ASSERT(d_inner % n_head  == 0);
+    GGML_ASSERT(d_inner % d_state == 0);
+    GGML_ASSERT(d_inner % n_group == 0);
 
     ggml_tensor * conv_states_all = mctx_cur->get_r_l(il);
     ggml_tensor * ssm_states_all  = mctx_cur->get_s_l(il);