Skip to content

chore : fix models indent after refactor #16992

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 4, 2025
Merged

chore : fix models indent after refactor #16992

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
226 changes: 113 additions & 113 deletions src/models/gemma2-iswa.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,125 +1,125 @@
#include "models.h"

llm_build_gemma2_iswa::llm_build_gemma2_iswa(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_tensor * cur;
ggml_tensor * inpL;

inpL = build_inp_embd(model.tok_embd);

inpL = ggml_scale(ctx0, inpL, sqrtf(n_embd));
cb(inpL, "inp_scaled", -1);

// inp_pos - contains the positions
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) {
// 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 = 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);

Qcur = ggml_scale(ctx0, Qcur, hparams.f_attention_scale);

cur = build_attn(inp_attn,
model.layers[il].wo, NULL,
Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f, il);
}
if (il == n_layer - 1 && inp_out_ids) {
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
}
cur = build_norm(cur,
model.layers[il].attn_post_norm, NULL,
LLM_NORM_RMS, il);
cb(cur, "attn_post_norm", il);

ggml_tensor * sa_out = ggml_add(ctx0, cur, inpL);
cb(sa_out, "sa_out", il);

cur = build_norm(sa_out,
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,
model.layers[il].ffn_gate, NULL, NULL,
model.layers[il].ffn_down, NULL, NULL,
NULL,
LLM_FFN_GELU, LLM_FFN_PAR, il);
cb(cur, "ffn_out", il);
}
cur = build_norm(cur,
model.layers[il].ffn_post_norm, NULL,
LLM_NORM_RMS, -1);
cb(cur, "ffn_post_norm", -1);

cur = ggml_add(ctx0, cur, sa_out);

cur = build_cvec(cur, il);
cb(cur, "l_out", il);

// input for next layer
inpL = cur;
}
cur = inpL;
const int64_t n_embd_head = hparams.n_embd_head_k;

ggml_tensor * cur;
ggml_tensor * inpL;

inpL = build_inp_embd(model.tok_embd);

inpL = ggml_scale(ctx0, inpL, sqrtf(n_embd));
cb(inpL, "inp_scaled", -1);

// inp_pos - contains the positions
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) {
// 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 = 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);

Qcur = ggml_scale(ctx0, Qcur, hparams.f_attention_scale);

cur = build_attn(inp_attn,
model.layers[il].wo, NULL,
Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f, il);
}
if (il == n_layer - 1 && inp_out_ids) {
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
}
cur = build_norm(cur,
model.output_norm, NULL,
model.layers[il].attn_post_norm, NULL,
LLM_NORM_RMS, il);
cb(cur, "attn_post_norm", il);

ggml_tensor * sa_out = ggml_add(ctx0, cur, inpL);
cb(sa_out, "sa_out", il);

cur = build_norm(sa_out,
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,
model.layers[il].ffn_gate, NULL, NULL,
model.layers[il].ffn_down, NULL, NULL,
NULL,
LLM_FFN_GELU, LLM_FFN_PAR, il);
cb(cur, "ffn_out", il);
}
cur = build_norm(cur,
model.layers[il].ffn_post_norm, NULL,
LLM_NORM_RMS, -1);
cb(cur, "ffn_post_norm", -1);

cur = ggml_add(ctx0, cur, sa_out);

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;
cb(cur, "result_norm", -1);
res->t_embd = cur;

// lm_head
cur = build_lora_mm(model.output, cur);
// lm_head
cur = build_lora_mm(model.output, cur);

// final logit soft-capping
cur = ggml_scale(ctx0, cur, 1.0f / hparams.f_final_logit_softcapping);
cur = ggml_tanh(ctx0, cur);
cur = ggml_scale(ctx0, cur, hparams.f_final_logit_softcapping);
// final logit soft-capping
cur = ggml_scale(ctx0, cur, 1.0f / hparams.f_final_logit_softcapping);
cur = ggml_tanh(ctx0, cur);
cur = ggml_scale(ctx0, cur, hparams.f_final_logit_softcapping);

cb(cur, "result_output", -1);
res->t_logits = cur;
cb(cur, "result_output", -1);
res->t_logits = cur;

ggml_build_forward_expand(gf, cur);
ggml_build_forward_expand(gf, cur);
}
Loading
Loading