mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-11 01:24:36 +00:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # .github/workflows/build.yml # ci/run.sh # docs/function-calling.md # examples/gritlm/gritlm.cpp # ggml/CMakeLists.txt # ggml/cmake/common.cmake # ggml/src/CMakeLists.txt # ggml/src/ggml-cpu/CMakeLists.txt # ggml/src/ggml-cpu/ggml-cpu.c # ggml/src/ggml-hip/CMakeLists.txt # ggml/src/ggml-vulkan/CMakeLists.txt # ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt # requirements/requirements-compare-llama-bench.txt # scripts/compare-llama-bench.py # tests/CMakeLists.txt
This commit is contained in:
Concedo
commit
4356a00f4a
47 changed files with 1526 additions and 301 deletions
|
|
@ -85,6 +85,7 @@ const char * llm_type_name(llm_type type) {
|
|||
case LLM_TYPE_40B: return "40B";
|
||||
case LLM_TYPE_65B: return "65B";
|
||||
case LLM_TYPE_70B: return "70B";
|
||||
case LLM_TYPE_142B: return "142B";
|
||||
case LLM_TYPE_236B: return "236B";
|
||||
case LLM_TYPE_290B: return "290B";
|
||||
case LLM_TYPE_314B: return "314B";
|
||||
|
|
@ -603,6 +604,16 @@ void llama_model::load_hparams(llama_model_loader & ml) {
|
|||
hparams.use_kq_norm = false;
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_ARCEE:
|
||||
{
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
|
||||
|
||||
// Arcee uses the same structure as Llama
|
||||
switch (hparams.n_layer) {
|
||||
case 36: type = LLM_TYPE_4B; break;
|
||||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_DECI:
|
||||
{
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
|
||||
|
|
@ -743,6 +754,16 @@ void llama_model::load_hparams(llama_model_loader & ml) {
|
|||
}
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_NEO_BERT:
|
||||
{
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
|
||||
ml.get_key(LLM_KV_ATTENTION_CAUSAL, hparams.causal_attn);
|
||||
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type);
|
||||
|
||||
if (hparams.n_layer == 28) {
|
||||
type = LLM_TYPE_250M;
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_BLOOM:
|
||||
{
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
|
||||
|
|
@ -1449,6 +1470,20 @@ void llama_model::load_hparams(llama_model_loader & ml) {
|
|||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_DOTS1:
|
||||
{
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
|
||||
ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead);
|
||||
ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp);
|
||||
ml.get_key(LLM_KV_EXPERT_SHARED_COUNT, hparams.n_expert_shared);
|
||||
ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale);
|
||||
ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false);
|
||||
ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func, false);
|
||||
switch (hparams.n_layer) {
|
||||
case 62: type = LLM_TYPE_142B; break;
|
||||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
} break;
|
||||
default: throw std::runtime_error("unsupported model architecture");
|
||||
}
|
||||
|
||||
|
|
@ -2283,6 +2318,32 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
|
|||
layer.layer_out_norm_b = create_tensor(tn(LLM_TENSOR_LAYER_OUT_NORM, "bias", i), {n_embd}, 0);
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_NEO_BERT:
|
||||
{
|
||||
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
|
||||
|
||||
cls = create_tensor(tn(LLM_TENSOR_CLS, "weight"), {n_embd, n_embd}, TENSOR_NOT_REQUIRED);
|
||||
cls_b = create_tensor(tn(LLM_TENSOR_CLS, "bias"), {n_embd}, TENSOR_NOT_REQUIRED);
|
||||
|
||||
cls_out = create_tensor(tn(LLM_TENSOR_CLS_OUT, "weight"), {n_embd, hparams.n_cls_out}, TENSOR_NOT_REQUIRED);
|
||||
cls_out_b = create_tensor(tn(LLM_TENSOR_CLS_OUT, "bias"), {hparams.n_cls_out}, TENSOR_NOT_REQUIRED);
|
||||
|
||||
output_norm_enc = create_tensor(tn(LLM_TENSOR_ENC_OUTPUT_NORM, "weight"), {n_embd}, 0);
|
||||
|
||||
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.wqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, 0);
|
||||
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
|
||||
|
||||
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
|
||||
|
||||
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff*2}, 0);
|
||||
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, 0);
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_JINA_BERT_V2:
|
||||
{
|
||||
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0); // word_embeddings
|
||||
|
|
@ -4219,6 +4280,89 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
|
|||
layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0);
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_DOTS1:
|
||||
{
|
||||
const int64_t n_ff_exp = hparams.n_ff_exp;
|
||||
const int64_t n_expert_shared = hparams.n_expert_shared;
|
||||
|
||||
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);
|
||||
|
||||
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_head_k * n_head}, 0);
|
||||
layer.wv = create_tensor(tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_head_k * n_head}, 0);
|
||||
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd}, 0);
|
||||
|
||||
layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd_head_k}, 0);
|
||||
layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd_head_k}, 0);
|
||||
|
||||
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
|
||||
|
||||
if (i < (int) hparams.n_layer_dense_lead) {
|
||||
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);
|
||||
} else {
|
||||
layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0);
|
||||
layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, TENSOR_NOT_REQUIRED);
|
||||
|
||||
if (n_expert == 0) {
|
||||
throw std::runtime_error("n_expert must be > 0");
|
||||
}
|
||||
if (n_expert_used == 0) {
|
||||
throw std::runtime_error("n_expert_used must be > 0");
|
||||
}
|
||||
|
||||
// MoE branch
|
||||
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);
|
||||
|
||||
// Shared expert branch
|
||||
layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0);
|
||||
layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), { n_ff_exp * n_expert_shared, n_embd}, 0);
|
||||
layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0);
|
||||
}
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_ARCEE:
|
||||
{
|
||||
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.rope_freqs = create_tensor(tn(LLM_TENSOR_ROPE_FREQS, "weight", i), {n_rot/2}, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 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");
|
||||
}
|
||||
|
|
@ -6174,6 +6318,117 @@ struct llm_build_bert : public llm_graph_context {
|
|||
}
|
||||
};
|
||||
|
||||
struct llm_build_neo_bert : public llm_graph_context {
|
||||
llm_build_neo_bert(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;
|
||||
const int64_t n_embd_gqa = hparams.n_embd_v_gqa();
|
||||
|
||||
GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
|
||||
|
||||
ggml_tensor * cur;
|
||||
ggml_tensor * inpL;
|
||||
ggml_tensor * inp_pos = build_inp_pos();
|
||||
|
||||
// construct input embeddings (token, type, position)
|
||||
inpL = build_inp_embd(model.tok_embd);
|
||||
cb(inpL, "inp_embd", -1);
|
||||
|
||||
auto * inp_attn = build_attn_inp_no_cache();
|
||||
|
||||
// iterate layers
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
ggml_tensor * cur = inpL;
|
||||
|
||||
ggml_tensor * Qcur;
|
||||
ggml_tensor * Kcur;
|
||||
ggml_tensor * Vcur;
|
||||
|
||||
// pre-norm
|
||||
cur = build_norm(inpL,
|
||||
model.layers[il].attn_norm, NULL,
|
||||
LLM_NORM_RMS, il);
|
||||
|
||||
// self-attention
|
||||
cur = build_lora_mm(model.layers[il].wqkv, cur);
|
||||
cb(cur, "wqkv", il);
|
||||
|
||||
Qcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd, n_tokens, cur->nb[1], 0*sizeof(float)*(n_embd)));
|
||||
Kcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd)));
|
||||
Vcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd + n_embd_gqa)));
|
||||
|
||||
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);
|
||||
|
||||
// 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, nullptr,
|
||||
Qcur, Kcur, Vcur, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);
|
||||
cb(cur, "kqv_out", il);
|
||||
|
||||
if (il == n_layer - 1 && pooling_type == LLAMA_POOLING_TYPE_NONE) {
|
||||
// skip computing output for unused tokens
|
||||
ggml_tensor * inp_out_ids = build_inp_out_ids();
|
||||
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
|
||||
inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
|
||||
}
|
||||
|
||||
// re-add the layer input
|
||||
cur = ggml_add(ctx0, cur, inpL);
|
||||
|
||||
ggml_tensor * ffn_inp = cur;
|
||||
cb(ffn_inp, "ffn_inp", il);
|
||||
|
||||
// pre-norm
|
||||
cur = build_norm(ffn_inp,
|
||||
model.layers[il].ffn_norm, NULL,
|
||||
LLM_NORM_RMS, il);
|
||||
cb(cur, "ffn_norm", il);
|
||||
|
||||
// feed-forward network
|
||||
cur = build_ffn(cur,
|
||||
model.layers[il].ffn_up,
|
||||
NULL, NULL, NULL, NULL, NULL,
|
||||
model.layers[il].ffn_down,
|
||||
NULL, NULL, NULL,
|
||||
LLM_FFN_SWIGLU, LLM_FFN_SEQ, il);
|
||||
|
||||
// attentions bypass the intermediate layer
|
||||
cur = ggml_add(ctx0, cur, ffn_inp);
|
||||
|
||||
// input for next layer
|
||||
inpL = cur;
|
||||
}
|
||||
|
||||
cur = inpL;
|
||||
|
||||
cur = build_norm(cur,
|
||||
model.output_norm_enc, NULL,
|
||||
LLM_NORM_RMS, -1);
|
||||
|
||||
cb(cur, "result_embd", -1);
|
||||
res->t_embd = cur;
|
||||
|
||||
ggml_build_forward_expand(gf, cur);
|
||||
}
|
||||
};
|
||||
|
||||
struct llm_build_bloom : public llm_graph_context {
|
||||
llm_build_bloom(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;
|
||||
|
|
@ -13294,6 +13549,291 @@ struct llm_build_bailingmoe : public llm_graph_context {
|
|||
}
|
||||
};
|
||||
|
||||
struct llm_build_dots1 : public llm_graph_context {
|
||||
llm_build_dots1(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();
|
||||
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
ggml_tensor * inpSA = inpL;
|
||||
|
||||
// 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);
|
||||
|
||||
ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
|
||||
cb(Kcur, "Kcur", il);
|
||||
|
||||
ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
|
||||
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);
|
||||
|
||||
Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, NULL, LLM_NORM_RMS, il);
|
||||
cb(Qcur, "Qcur_normed", il);
|
||||
|
||||
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 = build_norm(Kcur, model.layers[il].attn_k_norm, NULL, LLM_NORM_RMS, il);
|
||||
cb(Kcur, "Kcur_normed", il);
|
||||
|
||||
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, 1.0f/sqrtf(float(n_embd_head)), il);
|
||||
}
|
||||
|
||||
if (il == n_layer - 1) {
|
||||
// skip computing output for unused tokens
|
||||
ggml_tensor * inp_out_ids = build_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);
|
||||
|
||||
// MoE branch
|
||||
cur = build_norm(ffn_inp,
|
||||
model.layers[il].ffn_norm, NULL,
|
||||
LLM_NORM_RMS, il);
|
||||
cb(cur, "ffn_norm", il);
|
||||
|
||||
if ((uint32_t) il < hparams.n_layer_dense_lead) {
|
||||
cur = build_ffn(cur,
|
||||
model.layers[il].ffn_up, NULL, NULL,
|
||||
model.layers[il].ffn_gate, NULL, NULL,
|
||||
model.layers[il].ffn_down, NULL, NULL,
|
||||
NULL,
|
||||
LLM_FFN_SILU, LLM_FFN_PAR, il);
|
||||
cb(cur, "ffn_out", il);
|
||||
} else {
|
||||
ggml_tensor * moe_out =
|
||||
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,
|
||||
model.layers[il].ffn_exp_probs_b,
|
||||
n_expert, n_expert_used,
|
||||
LLM_FFN_SILU, hparams.expert_weights_norm,
|
||||
true, hparams.expert_weights_scale,
|
||||
(llama_expert_gating_func_type) hparams.expert_gating_func,
|
||||
il);
|
||||
cb(moe_out, "ffn_moe_out", il);
|
||||
|
||||
{
|
||||
ggml_tensor * ffn_shexp = build_ffn(cur,
|
||||
model.layers[il].ffn_up_shexp, NULL, NULL,
|
||||
model.layers[il].ffn_gate_shexp, NULL, NULL,
|
||||
model.layers[il].ffn_down_shexp, NULL, NULL,
|
||||
NULL,
|
||||
LLM_FFN_SILU, LLM_FFN_PAR, il);
|
||||
cb(ffn_shexp, "ffn_shexp", il);
|
||||
|
||||
cur = ggml_add(ctx0, moe_out, ffn_shexp);
|
||||
cb(cur, "ffn_out", il);
|
||||
}
|
||||
}
|
||||
|
||||
cur = ggml_add(ctx0, cur, ffn_inp);
|
||||
|
||||
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);
|
||||
|
||||
cb(cur, "result_output", -1);
|
||||
res->t_logits = cur;
|
||||
|
||||
ggml_build_forward_expand(gf, cur);
|
||||
}
|
||||
};
|
||||
|
||||
struct llm_build_arcee : public llm_graph_context {
|
||||
llm_build_arcee(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;
|
||||
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
ggml_tensor * inpSA = inpL;
|
||||
|
||||
// norm
|
||||
cur = build_norm(inpL,
|
||||
model.layers[il].attn_norm, NULL,
|
||||
LLM_NORM_RMS, il);
|
||||
cb(cur, "attn_norm", il);
|
||||
|
||||
// self-attention
|
||||
{
|
||||
// rope freq factors for llama3; may return nullptr for llama2 and other models
|
||||
ggml_tensor * rope_factors = model.get_rope_factors(cparams, il);
|
||||
|
||||
// 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);
|
||||
|
||||
Qcur = ggml_rope_ext(
|
||||
ctx0, Qcur, inp_pos, rope_factors,
|
||||
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, rope_factors,
|
||||
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) {
|
||||
// skip computing output for unused tokens
|
||||
ggml_tensor * inp_out_ids = build_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
|
||||
// ARCEE uses relu^2 instead of silu
|
||||
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, NULL, NULL,
|
||||
NULL, NULL, NULL,
|
||||
model.layers[il].ffn_down, NULL, NULL,
|
||||
NULL,
|
||||
LLM_FFN_RELU_SQR, LLM_FFN_SEQ, 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);
|
||||
|
||||
cb(cur, "result_output", -1);
|
||||
res->t_logits = cur;
|
||||
|
||||
ggml_build_forward_expand(gf, cur);
|
||||
}
|
||||
};
|
||||
|
||||
llama_memory_i * llama_model::create_memory(const llama_memory_params & params, llama_cparams & cparams) const {
|
||||
llama_memory_i * res;
|
||||
|
||||
|
|
@ -13302,6 +13842,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
|
|||
case LLM_ARCH_JINA_BERT_V2:
|
||||
case LLM_ARCH_NOMIC_BERT:
|
||||
case LLM_ARCH_NOMIC_BERT_MOE:
|
||||
case LLM_ARCH_NEO_BERT:
|
||||
case LLM_ARCH_WAVTOKENIZER_DEC:
|
||||
{
|
||||
res = nullptr;
|
||||
|
|
@ -13410,6 +13951,10 @@ llm_graph_result_ptr llama_model::build_graph(
|
|||
{
|
||||
llm = std::make_unique<llm_build_bert>(*this, params, gf);
|
||||
} break;
|
||||
case LLM_ARCH_NEO_BERT:
|
||||
{
|
||||
llm = std::make_unique<llm_build_neo_bert>(*this, params, gf);
|
||||
} break;
|
||||
case LLM_ARCH_BLOOM:
|
||||
{
|
||||
llm = std::make_unique<llm_build_bloom>(*this, params, gf);
|
||||
|
|
@ -13632,6 +14177,14 @@ llm_graph_result_ptr llama_model::build_graph(
|
|||
{
|
||||
llm = std::make_unique<llm_build_bailingmoe>(*this, params, gf);
|
||||
} break;
|
||||
case LLM_ARCH_DOTS1:
|
||||
{
|
||||
llm = std::make_unique<llm_build_dots1>(*this, params, gf);
|
||||
} break;
|
||||
case LLM_ARCH_ARCEE:
|
||||
{
|
||||
llm = std::make_unique<llm_build_arcee>(*this, params, gf);
|
||||
} break;
|
||||
default:
|
||||
GGML_ABORT("fatal error");
|
||||
}
|
||||
|
|
@ -13781,6 +14334,8 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
|
|||
case LLM_ARCH_GRANITE_MOE:
|
||||
case LLM_ARCH_CHAMELEON:
|
||||
case LLM_ARCH_BAILINGMOE:
|
||||
case LLM_ARCH_NEO_BERT:
|
||||
case LLM_ARCH_ARCEE:
|
||||
return LLAMA_ROPE_TYPE_NORM;
|
||||
|
||||
// the pairs of head values are offset by n_rot/2
|
||||
|
|
@ -13814,6 +14369,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
|
|||
case LLM_ARCH_NEMOTRON:
|
||||
case LLM_ARCH_EXAONE:
|
||||
case LLM_ARCH_MINICPM3:
|
||||
case LLM_ARCH_DOTS1:
|
||||
return LLAMA_ROPE_TYPE_NEOX;
|
||||
|
||||
case LLM_ARCH_QWEN2VL:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue