test-model-random : fix seq_id buffer overflow

It makes the test longer for little benefit.

convert_hf_to_gguf.py

@@ -6687,6 +6687,11 @@ class HunYuanMoEModel(TextModel):
             if len(experts) > 0:
                 raise ValueError(f"Unprocessed experts: {experts}")
 
+
+@ModelBase.register("SmolLM3ForCausalLM")
+class SmolLM3Model(LlamaModel):
+    model_arch = gguf.MODEL_ARCH.SMOLLM3
+
 ###### CONVERSION LOGIC ######
 
 

docs/development/HOWTO-add-model.md

@@ -83,20 +83,22 @@ NOTE: Tensor names must end with `.weight` or `.bias` suffixes, that is the conv
 
 ### 2. Define the model architecture in `llama.cpp`
 
-The model params and tensors layout must be defined in `llama.cpp`:
-1. Define a new `llm_arch`
-2. Define the tensors layout in `LLM_TENSOR_NAMES`
-3. Add any non-standard metadata in `llm_load_hparams`
-4. Create the tensors for inference in `llm_load_tensors`
-5. If the model has a RoPE operation, add the rope type in `llama_rope_type`
+The model params and tensors layout must be defined in `llama.cpp` source files:
+1. Define a new `llm_arch` enum value in `src/llama-arch.h`.
+2. In `src/llama-arch.cpp`:
+    - Add the architecture name to the `LLM_ARCH_NAMES` map.
+    - Add the tensor mappings to the `LLM_TENSOR_NAMES` map.
+3. Add any non-standard metadata loading in the `llama_model_loader` constructor in `src/llama-model-loader.cpp`.
+4. If the model has a RoPE operation, add a case for the architecture in `llama_model_rope_type` function in `src/llama-model.cpp`.
 
 NOTE: The dimensions in `ggml` are typically in the reverse order of the `pytorch` dimensions.
 
 ### 3. Build the GGML graph implementation
 
-This is the funniest part, you have to provide the inference graph implementation of the new model architecture in `llama_build_graph`.
-
-Have a look at existing implementations like `build_llama`, `build_dbrx` or `build_bert`.
+This is the funniest part, you have to provide the inference graph implementation of the new model architecture in `src/llama-model.cpp`.
+Create a new struct that inherits from `llm_graph_context` and implement the graph-building logic in its constructor.
+Have a look at existing implementations like `llm_build_llama`, `llm_build_dbrx` or `llm_build_bert`.
+Then, in the `llama_model::build_graph` method, add a case for your architecture to instantiate your new graph-building struct.
 
 Some `ggml` backends do not support all operations. Backend implementations can be added in a separate PR.
 

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -2706,7 +2706,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
     ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_IQ4_NL],  "get_rows_iq4_nl_f32",  get_rows_iq4_nl_f32_len,  get_rows_iq4_nl_f32_data,  "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);
 
     ggml_vk_create_pipeline(device, device->pipeline_matmul_split_k_reduce, "split_k_reduce", split_k_reduce_len, split_k_reduce_data, "main", 2, 2 * sizeof(uint32_t), {256 * 4, 1, 1}, {}, 1);
-    ggml_vk_create_pipeline(device, device->pipeline_flash_attn_split_k_reduce, "fa_split_k_reduce", fa_split_k_reduce_len, fa_split_k_reduce_data, "main", 2, 3 * sizeof(uint32_t), {1, 1, 1}, {}, 1, true);
+    ggml_vk_create_pipeline(device, device->pipeline_flash_attn_split_k_reduce, "fa_split_k_reduce", fa_split_k_reduce_len, fa_split_k_reduce_data, "main", 2, 4 * sizeof(uint32_t), {1, device->subgroup_size, 1}, {device->subgroup_size}, 1, true);
     ggml_vk_create_pipeline(device, device->pipeline_quantize_q8_1, "quantize_q8_1", quantize_q8_1_len, quantize_q8_1_data, "main", 2, 1 * sizeof(uint32_t), {32 * device->subgroup_size / 8, 1, 1}, { device->subgroup_size }, 1);
 
     for (uint32_t i = 0; i < p021_max_gqa_ratio; ++i) {
@@ -6252,13 +6252,13 @@ static void ggml_vk_flash_attn(ggml_backend_vk_context * ctx, vk_context& subctx
     const uint32_t shader_core_count = ctx->device->shader_core_count ? ctx->device->shader_core_count : 16;
 
     // Try to use split_k when KV is large enough to be worth the overhead
-    if (workgroups_x == 1 && shader_core_count > 0 && KV >= 512) {
+    if (workgroups_x == 1 && shader_core_count > 0) {
         // Try to run two workgroups per SM.
         split_k = shader_core_count * 2 / (workgroups_y * workgroups_z);
         if (split_k > 1) {
             // Try to evenly split KV into split_k chunks, but it needs to be a multiple
             // of "align", so recompute split_k based on that.
-            split_kv = ROUNDUP_POW2(KV / split_k, pipelines[1]->align);
+            split_kv = ROUNDUP_POW2(std::max(1u, KV / split_k), pipelines[1]->align);
             split_k = CEIL_DIV(KV, split_kv);
             workgroups_x = split_k;
         }
@@ -6392,7 +6392,7 @@ static void ggml_vk_flash_attn(ggml_backend_vk_context * ctx, vk_context& subctx
                                         vk_subbuffer{ctx->prealloc_split_k, 0, VK_WHOLE_SIZE},
                                         vk_subbuffer{d_D, d_buf_offset, VK_WHOLE_SIZE},
                                     },
-                                    pc2, { (uint32_t)ne1, 1, (uint32_t)ne3 });
+                                    pc2, { (uint32_t)ne1, HSV, (uint32_t)ne3 });
     } else {
         ggml_vk_dispatch_pipeline(ctx, subctx, pipeline,
                                     {

ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_split_k_reduce.comp

@@ -2,9 +2,9 @@
 
 #extension GL_EXT_control_flow_attributes : enable
 
-#define BLOCK_SIZE 32
+layout(constant_id = 0) const uint BLOCK_SIZE = 32;
 
-layout(local_size_x = BLOCK_SIZE, local_size_y = 1, local_size_z = 1) in;
+layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 
 layout (binding = 0) readonly buffer A {float data_a[];};
 layout (binding = 1) writeonly buffer D {float data_d[];};
@@ -16,6 +16,8 @@ layout (push_constant) uniform parameter {
     uint k_num;
 } p;
 
+shared float tmpsh[BLOCK_SIZE];
+
 void main() {
     // Each workgroup handles a row
     const uint n = gl_WorkGroupID.x;
@@ -32,23 +34,51 @@ void main() {
 
     // Compute the max m value for the row
     float m_max = -1.0/0.0;
-    [[unroll]] for (uint k = 0; k < k_num; ++k) {
-        float m = data_a[m_offset + k * lm_stride];
+    for (uint k = 0; k + tid < k_num; k += BLOCK_SIZE) {
+        float m = data_a[m_offset + (k + tid) * lm_stride];
         m_max = max(m_max, m);
     }
 
+    // reduce across the workgroup
+    tmpsh[tid] = m_max;
+    barrier();
+    [[unroll]] for (uint s = BLOCK_SIZE/2; s > 0; s >>= 1) {
+        if (tid < s) {
+            m_max = max(m_max, tmpsh[tid + s]);
+            tmpsh[tid] = m_max;
+        }
+        barrier();
+    }
+    m_max = tmpsh[0];
+
+    barrier();
+
     // Compute L based on m_max
     float L = 0;
-    [[unroll]] for (uint k = 0; k < k_num; ++k) {
-        float l = data_a[l_offset + k * lm_stride];
-        float m = data_a[m_offset + k * lm_stride];
+    for (uint k = 0; k + tid < k_num; k += BLOCK_SIZE) {
+        float l = data_a[l_offset + (k + tid) * lm_stride];
+        float m = data_a[m_offset + (k + tid) * lm_stride];
         L += exp(m - m_max) * l;
     }
 
+    // reduce across the workgroup
+    tmpsh[tid] = L;
+    barrier();
+    [[unroll]] for (uint s = BLOCK_SIZE/2; s > 0; s >>= 1) {
+        if (tid < s) {
+            L += tmpsh[tid + s];
+            tmpsh[tid] = L;
+        }
+        barrier();
+    }
+    L = tmpsh[0];
+
     L = 1.0 / L;
 
+    // D dimension is split across workgroups in the y dimension
+    uint d = tid + gl_WorkGroupID.y * BLOCK_SIZE;
     // Scale and sum the O contributions based on m_max and store the result to memory
-    for (uint d = tid; d < D; d += BLOCK_SIZE) {
+    if (d < D) {
         float O = 0.0;
         [[unroll]] for (uint k = 0; k < k_num; ++k) {
             uint o_offset = D * N * (k + iq3 * k_num) + D * n + d;

gguf-py/gguf/constants.py

@@ -358,6 +358,7 @@ class MODEL_ARCH(IntEnum):
     ARCEE            = auto()
     ERNIE4_5         = auto()
     HUNYUAN_MOE      = auto()
+    SMOLLM3          = auto()
 
 
 class VISION_PROJECTOR_TYPE(IntEnum):
@@ -662,6 +663,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
     MODEL_ARCH.ARCEE:            "arcee",
     MODEL_ARCH.ERNIE4_5:         "ernie4_5",
     MODEL_ARCH.HUNYUAN_MOE:      "hunyuan-moe",
+    MODEL_ARCH.SMOLLM3:          "smollm3",
 }
 
 VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = {
@@ -2234,6 +2236,22 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN_SHEXP,
         MODEL_TENSOR.FFN_UP_SHEXP,
     ],
+    MODEL_ARCH.SMOLLM3: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ROPE_FREQS,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.ATTN_ROT_EMBD,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+    ],
     # TODO
 }
 

src/llama-arch.cpp

@@ -79,6 +79,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
     { LLM_ARCH_ARCEE,            "arcee"            },
     { LLM_ARCH_ERNIE4_5,         "ernie4_5"         },
     { LLM_ARCH_HUNYUAN_MOE,      "hunyuan-moe"      },
+    { LLM_ARCH_SMOLLM3,          "smollm3"          },
     { LLM_ARCH_UNKNOWN,          "(unknown)"        },
 };
 
@@ -1724,6 +1725,23 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
             { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
         },
     },
+    {
+        LLM_ARCH_SMOLLM3,
+        {
+            { LLM_TENSOR_TOKEN_EMBD,     "token_embd"            },
+            { LLM_TENSOR_OUTPUT_NORM,    "output_norm"           },
+            { LLM_TENSOR_OUTPUT,         "output"                },
+            { LLM_TENSOR_ATTN_NORM,      "blk.%d.attn_norm"      },
+            { LLM_TENSOR_ATTN_Q,         "blk.%d.attn_q"         },
+            { LLM_TENSOR_ATTN_K,         "blk.%d.attn_k"         },
+            { LLM_TENSOR_ATTN_V,         "blk.%d.attn_v"         },
+            { LLM_TENSOR_ATTN_OUT,       "blk.%d.attn_output"    },
+            { LLM_TENSOR_FFN_NORM,       "blk.%d.ffn_norm"       },
+            { LLM_TENSOR_FFN_GATE,       "blk.%d.ffn_gate"       },
+            { LLM_TENSOR_FFN_DOWN,       "blk.%d.ffn_down"       },
+            { LLM_TENSOR_FFN_UP,         "blk.%d.ffn_up"         },
+        },
+    },
 };
 
 static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {

src/llama-arch.h

@@ -83,6 +83,7 @@ enum llm_arch {
     LLM_ARCH_ARCEE,
     LLM_ARCH_ERNIE4_5,
     LLM_ARCH_HUNYUAN_MOE,
+    LLM_ARCH_SMOLLM3,
     LLM_ARCH_UNKNOWN,
 };
 

src/llama-chat.cpp

@@ -680,9 +680,6 @@ int32_t llm_chat_apply_template(
                 ss << "<|startoftext|>" << message->content << "<|extra_0|>";
             }
         }
-        if (add_ass) {
-            ss << "<|startoftext|>";
-        }
     } else {
         // template not supported
         return -1;

src/llama-model.cpp

@@ -599,9 +599,11 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                 ml.get_key(LLM_KV_INTERLEAVE_MOE_LAYER_STEP,   hparams.n_moe_layer_step);
 
                 hparams.swa_type      = LLAMA_SWA_TYPE_CHUNKED;
-                hparams.n_swa         = 8192; // should this be a gguf kv? currently it's the same for Scout and Maverick
+                hparams.n_swa         = 8192; // currently it's the same for Scout and Maverick
                 hparams.set_swa_pattern(4);   // pattern: 3 chunked - 1 full
 
+                ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false); // for overrides in tests
+
                 switch (hparams.n_expert) {
                     case 16:  type = LLM_TYPE_17B_16E; break;
                     case 128: type = LLM_TYPE_17B_128E; break;
@@ -1561,6 +1563,16 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                     default: type = LLM_TYPE_UNKNOWN;
                 }
             } break;
+        case LLM_ARCH_SMOLLM3:
+            {
+                ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
+                hparams.n_no_rope_layer_step = 4;
+
+                switch (hparams.n_layer) {
+                    case 36: type = LLM_TYPE_3B; break;
+                    default: type = LLM_TYPE_UNKNOWN;
+                }
+            } break;
         default: throw std::runtime_error("unsupported model architecture");
     }
 
@@ -4524,6 +4536,35 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                         layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {hparams.n_ff_shexp, n_embd}, 0);
                     }
                 } break;
+            case LLM_ARCH_SMOLLM3:
+                {
+                    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
+                    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];
+
+                        layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
+
+                        layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "weight", i), {n_embd, n_embd_head_k * n_head}, 0);
+                        layer.wk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "weight", i), {n_embd, n_embd_k_gqa}, 0);
+                        layer.wv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "weight", i), {n_embd, n_embd_v_gqa}, 0);
+                        layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd}, 0);
+
+                        layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
+                        layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff}, 0);
+                        layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd}, 0);
+                        layer.ffn_up   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff}, 0);
+                    }
+                } break;
             default:
                 throw std::runtime_error("unknown architecture");
         }
@@ -14846,6 +14887,142 @@ struct llm_build_hunyuan_moe : public llm_graph_context {
         cb(cur, "result_norm", -1);
         res->t_embd = cur;
 
+        // lm_head
+        cur = build_lora_mm(model.output, cur);
+        cb(cur, "result_output", -1);
+        res->t_logits = cur;
+
+        ggml_build_forward_expand(gf, cur);
+    }
+};
+
+struct llm_build_smollm3 : public llm_graph_context {
+    llm_build_smollm3(const llama_model & model, const llm_graph_params & params, ggml_cgraph * gf) : llm_graph_context(params) {
+        const int64_t n_embd_head = hparams.n_embd_head_v;
+
+        GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
+        GGML_ASSERT(n_embd_head == hparams.n_rot);
+
+        ggml_tensor * cur;
+        ggml_tensor * inpL;
+
+        inpL = build_inp_embd(model.tok_embd);
+
+        // inp_pos - contains the positions
+        ggml_tensor * inp_pos = build_inp_pos();
+
+        auto * inp_attn = build_attn_inp_kv_unified();
+
+        const float kq_scale = hparams.f_attention_scale == 0.0f ? 1.0f/sqrtf(float(n_embd_head)) : hparams.f_attention_scale;
+
+        ggml_tensor * inp_out_ids = build_inp_out_ids();
+
+        for (int il = 0; il < n_layer; ++il) {
+            ggml_tensor * inpSA = inpL;
+
+            const bool use_rope = (il + 1) % hparams.n_no_rope_layer_step != 0;
+
+            // norm
+            cur = build_norm(inpL,
+                    model.layers[il].attn_norm, NULL,
+                    LLM_NORM_RMS, il);
+            cb(cur, "attn_norm", il);
+
+            // self-attention
+            {
+                // compute Q and K and RoPE them
+                ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
+                cb(Qcur, "Qcur", il);
+                if (model.layers[il].bq) {
+                    Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
+                    cb(Qcur, "Qcur", il);
+                }
+
+                ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
+                cb(Kcur, "Kcur", il);
+                if (model.layers[il].bk) {
+                    Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
+                    cb(Kcur, "Kcur", il);
+                }
+
+                ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
+                cb(Vcur, "Vcur", il);
+                if (model.layers[il].bv) {
+                    Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
+                    cb(Vcur, "Vcur", il);
+                }
+
+                Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head,    n_tokens);
+                Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
+                Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);
+
+                if (use_rope) {
+                    Qcur = ggml_rope_ext(
+                            ctx0, Qcur, inp_pos, nullptr,
+                            n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
+                            ext_factor, attn_factor, beta_fast, beta_slow
+                            );
+
+                    Kcur = ggml_rope_ext(
+                            ctx0, Kcur, inp_pos, nullptr,
+                            n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
+                            ext_factor, attn_factor, beta_fast, beta_slow
+                            );
+                }
+
+                cb(Qcur, "Qcur", il);
+                cb(Kcur, "Kcur", il);
+                cb(Vcur, "Vcur", il);
+
+                cur = build_attn(inp_attn, gf,
+                        model.layers[il].wo, model.layers[il].bo,
+                        Qcur, Kcur, Vcur, nullptr, nullptr, kq_scale, il);
+                cb(cur, "attn_out", il);
+            }
+
+            if (il == n_layer - 1 && inp_out_ids) {
+                cur   = ggml_get_rows(ctx0,   cur, inp_out_ids);
+                inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
+            }
+
+            ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
+            cb(ffn_inp, "ffn_inp", il);
+
+            // feed-forward network
+            {
+                cur = build_norm(ffn_inp,
+                        model.layers[il].ffn_norm, NULL,
+                        LLM_NORM_RMS, il);
+                cb(cur, "ffn_norm", il);
+
+                cur = build_ffn(cur,
+                        model.layers[il].ffn_up,   model.layers[il].ffn_up_b,   NULL,
+                        model.layers[il].ffn_gate, model.layers[il].ffn_gate_b, NULL,
+                        model.layers[il].ffn_down, model.layers[il].ffn_down_b, NULL,
+                        NULL,
+                        LLM_FFN_SILU, LLM_FFN_PAR, il);
+                cb(cur, "ffn_out", il);
+            }
+
+            cur = ggml_add(ctx0, cur, ffn_inp);
+            cb(cur, "ffn_out", il);
+
+            cur = build_cvec(cur, il);
+            cb(cur, "l_out", il);
+
+            // input for next layer
+            inpL = cur;
+        }
+
+        cur = inpL;
+
+        cur = build_norm(cur,
+                model.output_norm, NULL,
+                LLM_NORM_RMS, -1);
+
+        cb(cur, "result_norm", -1);
+        res->t_embd = cur;
+
         // lm_head
         cur = build_lora_mm(model.output, cur);
 
@@ -15240,6 +15417,10 @@ llm_graph_result_ptr llama_model::build_graph(
             {
                 llm = std::make_unique<llm_build_hunyuan_moe>(*this, params, gf);
             } break;
+        case LLM_ARCH_SMOLLM3:
+            {
+                llm = std::make_unique<llm_build_smollm3>(*this, params, gf);
+            } break;
         default:
             GGML_ABORT("fatal error");
     }
@@ -15391,6 +15572,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
         case LLM_ARCH_CHAMELEON:
         case LLM_ARCH_BAILINGMOE:
         case LLM_ARCH_NEO_BERT:
+        case LLM_ARCH_SMOLLM3:
         case LLM_ARCH_ARCEE:
         case LLM_ARCH_ERNIE4_5:
             return LLAMA_ROPE_TYPE_NORM;

tests/CMakeLists.txt

@@ -145,6 +145,7 @@ if (NOT WIN32 OR NOT BUILD_SHARED_LIBS)
     llama_build_and_test(test-grammar-integration.cpp)
     llama_build_and_test(test-llama-grammar.cpp)
     llama_build_and_test(test-chat.cpp)
+    llama_build_and_test(test-model-random.cpp)
     # TODO: disabled on loongarch64 because the ggml-ci node lacks Python 3.8
     if (NOT ${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
         llama_build_and_test(test-json-schema-to-grammar.cpp   WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})