model: M3: Move MSA into a new memory implementation (#26338)

* Move MSA logic from llama-kv-cache into llama-kv-cache-msa

* cont : minor

* cont : ws fix

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

src/llama-model.cpp

@@ -11,6 +11,7 @@
 #include "llama-kv-cache.h"
 #include "llama-kv-cache-iswa.h"
 #include "llama-kv-cache-dsa.h"
+#include "llama-kv-cache-msa.h"
 #include "llama-kv-cache-dsv4.h"
 #include "llama-memory-hybrid.h"
 #include "llama-memory-hybrid-iswa.h"
@@ -2071,6 +2072,28 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
             {
                 res = nullptr;
             } break;
+        case LLM_ARCH_MINIMAX_M3:
+            {
+                // sparse (MSA) layers carry an indexer key cache, but leading dense layers do not
+                llama_kv_cache::layer_filter_cb filter_idx =
+                    [&](int32_t il) { return (uint32_t) il >= hparams.n_layer_dense_lead; };
+
+                res = new llama_kv_cache_msa(
+                        *this,
+                        params.type_k,
+                        params.type_v,
+                        !cparams.flash_attn,
+                        cparams.offload_kqv,
+                        cparams.kv_unified,
+                        cparams.n_ctx_seq,
+                        cparams.n_seq_max,
+                        1,
+                        hparams.n_swa,
+                        hparams.swa_type,
+                        nullptr,
+                        filter_idx,
+                        nullptr);
+            } break;
         case LLM_ARCH_GLM_DSA:
         case LLM_ARCH_DEEPSEEK32:
             {