model: move load_hparams and load_tensors to per-model definition (#22004)

* git-friendly migration * add build_graph * nits * exclude old code from build * wip * add llm_arch_model_i * prepare downstream functions * nits * nits * wip * wip * add back create_tensor_qkv * fix files missing include * enforce one llm_build per arch * cmake: use glob * missing model params * nits * wip * wip (2) * wip (3) * test-llama-archs is happy * improve switch case * move more stuff into llm_arch_model_i * fix downstream code * nits * nits (2) * fix order * llama_model_base * LLAMA_LOAD_LOCALS * small fix * fix build errors * auto * rm migration script and ifdef
2026-05-04 12:36:59 +02:00
parent c84e6d6db5
commit 994118a183
129 changed files with 10667 additions and 8117 deletions
@@ -1,6 +1,90 @@
 #include "models.h"

-llm_build_mamba::llm_build_mamba(const llama_model & model, const llm_graph_params & params) : llm_build_mamba_base(params) {
+void llama_model_mamba::load_arch_hparams(llama_model_loader & ml) {
+    ml.get_key(LLM_KV_SSM_CONV_KERNEL,    hparams.ssm_d_conv);
+    ml.get_key(LLM_KV_SSM_INNER_SIZE,     hparams.ssm_d_inner);
+    ml.get_key(LLM_KV_SSM_STATE_SIZE,     hparams.ssm_d_state);
+    ml.get_key(LLM_KV_SSM_TIME_STEP_RANK, hparams.ssm_dt_rank);
+    ml.get_key(LLM_KV_SSM_DT_B_C_RMS,     hparams.ssm_dt_b_c_rms, false);
+
+    ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
+
+    switch (hparams.n_layer) {
+        case 24:
+            switch (hparams.n_embd) {
+                case 768: type = LLM_TYPE_SMALL; break;
+                default: type = LLM_TYPE_UNKNOWN;
+            } break;
+        case 48:
+            switch (hparams.n_embd) {
+                case 1024: type = LLM_TYPE_MEDIUM; break;
+                case 1536: type = LLM_TYPE_LARGE; break;
+                case 2048: type = LLM_TYPE_XL; break;
+                default:   type = LLM_TYPE_UNKNOWN;
+            } break;
+        case 64:
+            switch (hparams.n_embd) {
+                case 2560: type = LLM_TYPE_3B; break;
+                default: type = LLM_TYPE_UNKNOWN;
+            } break;
+        default: type = LLM_TYPE_UNKNOWN;
+    }
+}
+
+void llama_model_mamba::load_arch_tensors(llama_model_loader &) {
+    LLAMA_LOAD_LOCALS;
+
+    const int64_t d_conv  = hparams.ssm_d_conv;
+    const int64_t d_inner = hparams.ssm_d_inner;
+    const int64_t d_state = hparams.ssm_d_state;
+    const int64_t dt_rank = hparams.ssm_dt_rank;
+
+    // only an expansion factor of 2 is supported for now
+    if (2 * n_embd != d_inner) {
+        throw std::runtime_error("only an expansion factor of 2 is supported for now");
+    }
+
+    tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
+
+    // output
+    output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
+
+    output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
+    // if output is NULL, init from the input tok embed, duplicated to allow offloading
+    if (output == NULL) {
+        output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
+    }
+
+    for (int i = 0; i < n_layer; ++i) {
+        auto & layer = layers[i];
+
+        // norm
+        layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
+
+        layer.ssm_in = create_tensor(tn(LLM_TENSOR_SSM_IN, "weight", i), {n_embd, 2*d_inner}, 0);
+
+        layer.ssm_conv1d = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {d_conv, d_inner}, 0);
+        layer.ssm_conv1d_b = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {d_inner}, 0);
+
+        layer.ssm_x = create_tensor(tn(LLM_TENSOR_SSM_X, "weight", i), {d_inner, dt_rank + 2*d_state}, 0);
+
+        layer.ssm_dt = create_tensor(tn(LLM_TENSOR_SSM_DT, "weight", i), {dt_rank, d_inner}, 0);
+        layer.ssm_dt_b = create_tensor(tn(LLM_TENSOR_SSM_DT, "bias", i), {d_inner}, 0);
+
+        // no "weight" suffix for these
+        layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A, i), {d_state, d_inner}, 0);
+        layer.ssm_d = create_tensor(tn(LLM_TENSOR_SSM_D, i), {d_inner}, 0);
+
+        // out_proj
+        layer.ssm_out = create_tensor(tn(LLM_TENSOR_SSM_OUT, "weight", i), {d_inner, n_embd}, 0);
+    }
+}
+
+std::unique_ptr<llm_graph_context> llama_model_mamba::build_arch_graph(const llm_graph_params & params) const {
+    return std::make_unique<graph>(*this, params);
+}
+
+llama_model_mamba::graph::graph(const llama_model & model, const llm_graph_params & params) : llm_build_mamba_base(params) {
    ggml_tensor * cur;
    ggml_tensor * inpL;

@@ -51,4 +135,3 @@ llm_build_mamba::llm_build_mamba(const llama_model & model, const llm_graph_para

    ggml_build_forward_expand(gf, cur);
 }
-