LLM inference in C/C++
C++ ggml
llama: add Maple 20B-A1B ternary MoE architecture (CPU) (#27000)
Alex3d10bcd19785
diff --git a/conversion/__init__.py b/conversion/__init__.pyindex 4d58bcd106..9c5d984388 100644--- a/conversion/__init__.py+++ b/conversion/__init__.py@@ -168,6 +168,7 @@ TEXT_MODEL_MAP: dict[str, str] = {"Mamba2ForCausalLM": "mamba","MambaForCausalLM": "mamba","MambaLMHeadModel": "mamba",+ "MapleForCausalLM": "maple","MellumForCausalLM": "mellum","MiMoV2FlashForCausalLM": "mimo","MiMoV2ForCausalLM": "mimo",diff --git a/conversion/maple.py b/conversion/maple.pynew file mode 100644index 0000000000..fb0e87804d--- /dev/null+++ b/conversion/maple.py@@ -0,0 +1,87 @@+from __future__ import annotations++from typing import Iterable, TYPE_CHECKING, cast++import torch++if TYPE_CHECKING:+ from torch import Tensor++from .base import LazyTorchTensor, ModelBase, TextModel, gguf++[email protected]("MapleForCausalLM")[email protected]("deepgrove/maple-preview")+class MapleModel(TextModel):+ model_arch = gguf.MODEL_ARCH.MAPLE++ def set_gguf_parameters(self):+ super().set_gguf_parameters()+ hparams = self.hparams++ assert hparams["hidden_act"] == "silu"+ assert hparams.get("num_shared_experts", 0) == 0+ assert hparams.get("norm_topk_prob", True)+ assert hparams.get("nope_on_global_attention", False)++ head_dim = hparams.get("head_dim", hparams["hidden_size"] // hparams["num_attention_heads"])+ partial_rotary_factor = self.rope_parameters.get("partial_rotary_factor", 1.0)++ self.gguf_writer.add_vocab_size(hparams["vocab_size"])+ self.gguf_writer.add_rope_dimension_count(int(head_dim * partial_rotary_factor))+ self.gguf_writer.add_sliding_window(hparams["sliding_window"])+ self.gguf_writer.add_sliding_window_pattern([layer_type == "sliding_attention" for layer_type in hparams["layer_types"]])+ self.gguf_writer.add_expert_feed_forward_length(hparams["moe_intermediate_size"])+ # the reference clamps the MoE SwiGLU gate/up at 7.0 (modeling_maple.py)+ self.gguf_writer.add_swiglu_clamp_exp([7.0] * self.block_count)++ _experts: list[dict[str, Tensor]] | None = None++ @staticmethod+ def _stack_experts(tensors: list[Tensor]) -> Tensor:+ shape = (len(tensors), *tensors[0].shape)+ dtype = tensors[0].dtype+ meta = LazyTorchTensor.meta_with_dtype_and_shape(dtype, shape)++ # tensors goes through args, not the closure, so that `func` matches+ # LazyBase's single-argument shape+ def stack(ts: list[Tensor]) -> Tensor:+ result = torch.empty(shape, dtype=dtype)+ for expert_id, tensor in enumerate(ts):+ result[expert_id].copy_(LazyTorchTensor.to_eager(tensor))+ ts.clear()+ return result++ return cast(torch.Tensor, LazyTorchTensor(meta=meta, args=(tensors,), func=stack))++ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:+ if "mlp.experts" in name:+ n_experts = self.hparams["num_experts"]+ assert bid is not None++ if self._experts is None:+ self._experts = [{} for _ in range(self.block_count)]++ self._experts[bid][name] = data_torch++ if len(self._experts[bid]) >= n_experts * 3:+ for weight_name in ("down_proj", "gate_proj", "up_proj"):+ tensors = []++ for expert_id in range(n_experts):+ expert_name = f"model.layers.{bid}.mlp.experts.{expert_id}.{weight_name}.weight"+ tensors.append(self._experts[bid].pop(expert_name))++ merged_name = f"model.layers.{bid}.mlp.experts.{weight_name}.weight"+ yield from super().modify_tensors(self._stack_experts(tensors), merged_name, bid)+ return++ yield from super().modify_tensors(data_torch, name, bid)++ def prepare_tensors(self):+ super().prepare_tensors()++ if self._experts is not None:+ experts = [name for layer in self._experts for name in layer]+ if experts:+ raise ValueError(f"Unprocessed experts: {experts}")diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.pyindex d3a639f374..e54ee5a0fd 100644--- a/gguf-py/gguf/constants.py+++ b/gguf-py/gguf/constants.py@@ -541,6 +541,7 @@ class MODEL_ARCH(IntEnum):ARWKV7 = auto()MAMBA = auto()MAMBA2 = auto()+ MAPLE = auto()JAMBA = auto()XVERSE = auto()COMMAND_R = auto()@@ -1295,6 +1296,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {MODEL_ARCH.ARWKV7: "arwkv7",MODEL_ARCH.MAMBA: "mamba",MODEL_ARCH.MAMBA2: "mamba2",+ MODEL_ARCH.MAPLE: "maple",MODEL_ARCH.JAMBA: "jamba",MODEL_ARCH.XVERSE: "xverse",MODEL_ARCH.COMMAND_R: "command-r",@@ -3487,6 +3489,23 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {MODEL_TENSOR.SSM_NORM,MODEL_TENSOR.SSM_OUT,],+ MODEL_ARCH.MAPLE: [+ MODEL_TENSOR.TOKEN_EMBD,+ MODEL_TENSOR.OUTPUT_NORM,+ MODEL_TENSOR.OUTPUT,+ MODEL_TENSOR.ATTN_NORM,+ MODEL_TENSOR.ATTN_Q,+ MODEL_TENSOR.ATTN_Q_NORM,+ MODEL_TENSOR.ATTN_K,+ MODEL_TENSOR.ATTN_K_NORM,+ MODEL_TENSOR.ATTN_V,+ MODEL_TENSOR.ATTN_OUT,+ MODEL_TENSOR.FFN_NORM,+ MODEL_TENSOR.FFN_GATE_INP,+ MODEL_TENSOR.FFN_GATE_EXP,+ MODEL_TENSOR.FFN_DOWN_EXP,+ MODEL_TENSOR.FFN_UP_EXP,+ ],MODEL_ARCH.JAMBA: [MODEL_TENSOR.TOKEN_EMBD,MODEL_TENSOR.OUTPUT_NORM,diff --git a/src/llama-arch.cpp b/src/llama-arch.cppindex b5efb72065..0fac27efc0 100644--- a/src/llama-arch.cpp+++ b/src/llama-arch.cpp@@ -62,6 +62,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {{ LLM_ARCH_STARCODER2, "starcoder2" },{ LLM_ARCH_MAMBA, "mamba" },{ LLM_ARCH_MAMBA2, "mamba2" },+ { LLM_ARCH_MAPLE, "maple" },{ LLM_ARCH_JAMBA, "jamba" },{ LLM_ARCH_FALCON_H1, "falcon-h1" },{ LLM_ARCH_XVERSE, "xverse" },diff --git a/src/llama-arch.h b/src/llama-arch.hindex f1d173a575..6e67f5d659 100644--- a/src/llama-arch.h+++ b/src/llama-arch.h@@ -67,6 +67,7 @@ enum llm_arch {LLM_ARCH_STARCODER2,LLM_ARCH_MAMBA,LLM_ARCH_MAMBA2,+ LLM_ARCH_MAPLE,LLM_ARCH_JAMBA,LLM_ARCH_FALCON_H1,LLM_ARCH_XVERSE,diff --git a/src/llama-graph.cpp b/src/llama-graph.cppindex 5855393ef7..fd4290cf05 100644--- a/src/llama-graph.cpp+++ b/src/llama-graph.cpp@@ -2225,7 +2225,7 @@ ggml_tensor * llm_graph_context::build_moe_ffn(const float limit = hparams.swiglu_clamp_exp[il];constexpr float eps = 1e-6f;if (limit > eps) {- if (arch == LLM_ARCH_DEEPSEEK4 || (arch == LLM_ARCH_DFLASH && hparams.dsv4_hc_mult > 0) || arch == LLM_ARCH_HY_V4) {+ if (arch == LLM_ARCH_MAPLE || arch == LLM_ARCH_DEEPSEEK4 || (arch == LLM_ARCH_DFLASH && hparams.dsv4_hc_mult > 0) || arch == LLM_ARCH_HY_V4) {cur = ggml_swiglu_clamp(ctx0, cur, up, limit);} else {up = ggml_clamp(ctx0, up, -limit, limit);diff --git a/src/llama-model-saver.cpp b/src/llama-model-saver.cppindex 66f8bdec37..59a8ff84f8 100644--- a/src/llama-model-saver.cpp+++ b/src/llama-model-saver.cpp@@ -33,6 +33,7 @@ bool llama_model_saver_supports_arch(llm_arch arch) {case LLM_ARCH_LAGUNA:case LLM_ARCH_GRANITE_SWA:case LLM_ARCH_DOTS3NOTE: // TODO: need to handle SWA pattern and MLA+SWA config+ case LLM_ARCH_MAPLE:return false;default:return true;diff --git a/src/llama-model.cpp b/src/llama-model.cppindex f9e9a8bcb0..3b2536283c 100644--- a/src/llama-model.cpp+++ b/src/llama-model.cpp@@ -162,6 +162,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_paramsreturn new llama_model_mamba(params);case LLM_ARCH_MAMBA2:return new llama_model_mamba2(params);+ case LLM_ARCH_MAPLE:+ return new llama_model_maple(params);case LLM_ARCH_JAMBA:return new llama_model_jamba(params);case LLM_ARCH_XVERSE:@@ -3019,6 +3021,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {case LLM_ARCH_SPARK2_5:case LLM_ARCH_TALKIE:case LLM_ARCH_MELLUM:+ case LLM_ARCH_MAPLE:return LLAMA_ROPE_TYPE_NEOX;case LLM_ARCH_DFLASH:diff --git a/src/models/maple.cpp b/src/models/maple.cppnew file mode 100644index 0000000000..7604b7dfee--- /dev/null+++ b/src/models/maple.cpp@@ -0,0 +1,150 @@+#include "models.h"++void llama_model_maple::load_arch_hparams(llama_model_loader & ml) {+ hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;++ ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);+ ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa);+ ml.get_key_or_arr(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp_arr, hparams.n_layer_all);++ ml.get_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl);++ hparams.rope_freq_base_train_swa = hparams.rope_freq_base_train;+ hparams.rope_freq_scale_train_swa = hparams.rope_freq_scale_train;+ ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false);++ ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp, hparams.n_layer_all);++ switch (hparams.n_layer()) {+ case 24: type = LLM_TYPE_20B; break;+ default: type = LLM_TYPE_UNKNOWN;+ }+}++void llama_model_maple::load_arch_tensors(llama_model_loader &) {+ LLAMA_LOAD_LOCALS;++ const int64_t n_ff_exp = hparams.n_ff_exp();+ const int64_t head_dim = hparams.n_embd_head_k();++ tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);++ 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}, 0);++ if (n_expert == 0) {+ throw std::runtime_error("n_expert must be > 0 for Maple");+ }+ if (n_expert_used == 0) {+ throw std::runtime_error("n_expert_used must be > 0 for Maple");+ }++ 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);++ create_tensor_qkv(layer, i, n_embd, n_head * head_dim, n_head_kv * head_dim, n_head_kv * head_dim, 0);+ layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_head * head_dim, n_embd}, 0);++ layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {head_dim}, 0);+ layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {head_dim}, 0);+ layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);++ layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0);+ layer.ffn_gate_exps = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0);+ layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp, n_embd, n_expert}, 0);+ layer.ffn_up_exps = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0);+ }+}++std::unique_ptr<llm_graph_context> llama_model_maple::build_arch_graph(const llm_graph_params & params) const {+ return std::make_unique<graph>(*this, params);+}++llama_model_maple::graph::graph(const llama_model & model, const llm_graph_params & params) :+ llm_graph_context(params) {+ const int64_t n_embd_head = hparams.n_embd_head_k();++ GGML_ASSERT(n_embd_head == hparams.n_embd_head_v());++ ggml_tensor * inpL = build_inp_embd(model.tok_embd);+ ggml_tensor * inp_pos = build_inp_pos();+ auto * inp_attn = build_attn_inp_kv_iswa();+ ggml_tensor * inp_out_ids = build_inp_out_ids();++ for (int il = 0; il < n_layer; ++il) {+ ggml_tensor * inpSA = inpL;++ ggml_tensor * cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il);+ cb(cur, "attn_norm", il);++ {+ auto [Qcur, Kcur, Vcur] = build_qkv(model.layers[il], cur, n_embd_head, n_head, n_head_kv, il);++ Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, nullptr, LLM_NORM_RMS, il);+ Kcur = build_norm(Kcur, model.layers[il].attn_k_norm, nullptr, LLM_NORM_RMS, il);+ cb(Qcur, "Qcur_normed", il);+ cb(Kcur, "Kcur_normed", il);++ if (hparams.is_swa(il)) {+ const int64_t n_rot_l = hparams.n_rot(il);+ const float freq_base_l = model.get_rope_freq_base(cparams, il);+ const float freq_scale_l = model.get_rope_freq_scale(cparams, il);++ Qcur = ggml_rope_ext(ctx0, Qcur, inp_pos, nullptr, n_rot_l, rope_type, n_ctx_orig, freq_base_l,+ freq_scale_l, ext_factor, attn_factor, beta_fast, beta_slow);+ Kcur = ggml_rope_ext(ctx0, Kcur, inp_pos, nullptr, n_rot_l, rope_type, n_ctx_orig, freq_base_l,+ freq_scale_l, 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,+ model.layers[il].wo, nullptr, model.layers[il].wo_s,+ Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), 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);++ cur = build_norm(ffn_inp, model.layers[il].ffn_norm, nullptr, LLM_NORM_RMS, il);+ cb(cur, "ffn_norm", il);++ cur = build_moe_ffn(cur,+ model.layers[il].ffn_gate_inp,+ model.layers[il].ffn_up_exps,+ model.layers[il].ffn_gate_exps,+ model.layers[il].ffn_down_exps,+ nullptr,+ n_expert, n_expert_used,+ LLM_FFN_SILU, true,+ 1.0f,+ LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,+ il);+ cb(cur, "ffn_moe_out", il);++ cur = ggml_add(ctx0, cur, ffn_inp);+ cur = build_cvec(cur, il);+ cb(cur, "l_out", il);++ inpL = cur;+ }++ ggml_tensor * cur = build_norm(inpL, model.output_norm, nullptr, LLM_NORM_RMS, -1);+ cb(cur, "result_norm", -1);+ res->t_embd = cur;++ cur = build_lora_mm(model.output, cur, model.output_s);+ cb(cur, "result_output", -1);+ res->t_logits = cur;++ ggml_build_forward_expand(gf, cur);+}diff --git a/src/models/models.h b/src/models/models.hindex 87195fddd1..da519dcfdc 100644--- a/src/models/models.h+++ b/src/models/models.h@@ -945,6 +945,19 @@ struct llama_model_mamba2 : public llama_model_base {};+struct llama_model_maple : public llama_model_base {+ llama_model_maple(const struct llama_model_params & params) : llama_model_base(params) {}+ void load_arch_hparams(llama_model_loader & ml) override;+ void load_arch_tensors(llama_model_loader & ml) override;++ struct graph : public llm_graph_context {+ graph(const llama_model & model, const llm_graph_params & params);+ };++ std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;+};++struct llama_model_jamba : public llama_model_base {llama_model_jamba(const struct llama_model_params & params) : llama_model_base(params) {}void load_arch_hparams(llama_model_loader & ml) override;diff --git a/tests/test-llama-archs.cpp b/tests/test-llama-archs.cppindex 018ff1f42c..90a6a71623 100644--- a/tests/test-llama-archs.cpp+++ b/tests/test-llama-archs.cpp@@ -239,7 +239,8 @@ static gguf_context_ptr get_gguf_ctx(const llm_arch arch, const bool moe) {// SWA pattern: every 5th layer is full attention (matches E2B layer_types)ms.add_kv(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, uint32_t(5));} else if (arch == LLM_ARCH_COHERE2MOE || arch == LLM_ARCH_MIMO2 || arch == LLM_ARCH_STEP35 || arch == LLM_ARCH_SPARK2_5 ||- arch == LLM_ARCH_MUSE_GLIMMER || arch == LLM_ARCH_GRANITE_SWA || arch == LLM_ARCH_DOTS3NOTE) {+ arch == LLM_ARCH_MUSE_GLIMMER || arch == LLM_ARCH_GRANITE_SWA || arch == LLM_ARCH_DOTS3NOTE ||+ arch == LLM_ARCH_MAPLE) {std::vector<uint32_t> pattern;pattern.reserve(n_layer);for (uint32_t il = 0; il < n_layer; il++) {@@ -323,6 +324,11 @@ static gguf_context_ptr get_gguf_ctx(const llm_arch arch, const bool moe) {ms.add_kv(LLM_KV_EXPERT_WEIGHTS_SCALE, 1.0f);ms.add_kv(LLM_KV_EXPERT_WEIGHTS_NORM, true);}++ if (arch == LLM_ARCH_MAPLE) {+ ms.add_kv(LLM_KV_SWIGLU_CLAMP_EXP, 7.0f);+ }+ms.add_kv(LLM_KV_TOKENIZER_MODEL, "no_vocab");// ms.add_kv(LLM_KV_DENSE_2_FEAT_OUT, n_embd);// ms.add_kv(LLM_KV_DENSE_3_FEAT_IN, n_embd);@@ -505,6 +511,7 @@ static bool moe_mandatory(const llm_arch arch) {case LLM_ARCH_MISTRAL4:case LLM_ARCH_MELLUM:case LLM_ARCH_LAGUNA:+ case LLM_ARCH_MAPLE:return true;default:return false;