Something went wrong. Try again.
llama.cpp fork for Ternary Bonsai 2 27B: MTP speculation, suffix cache reuse (SCR), q8 KV, two-slot fairness, fused DeltaNet kernels
Something went wrong. Try again.
5.7 kB · 158 lines
C++
at main
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159#include "models.h"
void llama_model_starcoder2::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
switch (hparams.n_layer()) { case 30: type = LLM_TYPE_3B; break; case 32: type = LLM_TYPE_7B; break; case 40: type = LLM_TYPE_15B; break; case 52: type = LLM_TYPE_20B; break; // granite case 88: type = LLM_TYPE_34B; break; // granite default: type = LLM_TYPE_UNKNOWN; }}
void llama_model_starcoder2::load_arch_tensors(llama_model_loader &) { LLAMA_LOAD_LOCALS;
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_norm_b = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {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.attn_norm_b = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}, 0);
create_tensor_qkv(layer, i, n_embd, n_embd, n_embd_gqa, n_embd_gqa, 0); layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
// optional bias tensors layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, 0);
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0); layer.ffn_norm_b = create_tensor(tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}, 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);
// optional bias tensors layer.ffn_down_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, 0); layer.ffn_up_b = create_tensor(tn(LLM_TENSOR_FFN_UP , "bias", i), { n_ff}, 0); }}
std::unique_ptr<llm_graph_context> llama_model_starcoder2::build_arch_graph(const llm_graph_params & params) const { return std::make_unique<graph>(*this, params);}
llama_model_starcoder2::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_v();
GGML_ASSERT(n_embd_head == hparams.n_embd_head_k()); GGML_ASSERT(n_embd_head == 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();
ggml_tensor * inp_out_ids = build_inp_out_ids();
for (int il = 0; il < n_layer; ++il) { ggml_tensor * inpSA = inpL;
// norm cur = build_norm(inpL, model.layers[il].attn_norm, model.layers[il].attn_norm_b, LLM_NORM, il); cb(cur, "attn_norm", il);
// self-attention { // compute Q and K and RoPE them auto [Qcur, Kcur, Vcur] = build_qkv(model.layers[il], cur, n_embd_head, n_head, n_head_kv, 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 = 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, model.layers[il].wo, model.layers[il].wo_b, model.layers[il].wo_s, Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), 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, model.layers[il].ffn_norm_b, LLM_NORM, il); cb(cur, "ffn_norm", il);
cur = build_ffn(cur, model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL, NULL, NULL, NULL, model.layers[il].ffn_down, model.layers[il].ffn_down_b, NULL, NULL, LLM_FFN_GELU, LLM_FFN_SEQ, il); 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, model.output_norm_b, LLM_NORM, -1);
cb(cur, "result_norm", -1); res->t_embd = cur;
// lm_head 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);}