mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

model: move load_hparams and load_tensors to per-model definition (#22004)

Browse Source 
* git-friendly migration

* add build_graph

* nits

* exclude old code from build

* wip

* add llm_arch_model_i

* prepare downstream functions

* nits

* nits

* wip

* wip

* add back create_tensor_qkv

* fix files missing include

* enforce one llm_build per arch

* cmake: use glob

* missing model params

* nits

* wip

* wip (2)

* wip (3)

* test-llama-archs is happy

* improve switch case

* move more stuff into llm_arch_model_i

* fix downstream code

* nits

* nits (2)

* fix order

* llama_model_base

* LLAMA_LOAD_LOCALS

* small fix

* fix build errors

* auto

* rm migration script and ifdef
This commit is contained in:
Xuan-Son Nguyen
2026-05-04 12:36:59 +02:00
committed by GitHub
parent c84e6d6db5
commit 994118a183
129 changed files with 10667 additions and 8117 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/gptneox.cpp
+84 -1
View File
@@ -1,6 +1,89 @@
#include "models.h"
llm_build_gptneox::llm_build_gptneox(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
void llama_model_gptneox::load_arch_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
ml.get_key(LLM_KV_USE_PARALLEL_RESIDUAL, hparams.use_par_res);
switch (hparams.n_layer) {
case 6:
switch (hparams.n_ff()) {
case 512: type = LLM_TYPE_14M; break;
case 2048: type = LLM_TYPE_70M; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 12:
switch (hparams.n_ff()) {
case 3072: type = LLM_TYPE_160M; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 16:
switch (hparams.n_ff()) {
case 8192: type = LLM_TYPE_1B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 24:
switch (hparams.n_ff()) {
case 4096: type = LLM_TYPE_410M; break;
case 8192: type = LLM_TYPE_1_4B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 32:
switch (hparams.n_ff()) {
case 10240: type = LLM_TYPE_2_8B; break;
case 16384: type = LLM_TYPE_6_9B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 36:
switch (hparams.n_ff()) {
case 20480: type = LLM_TYPE_12B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
case 44:
switch (hparams.n_ff()) {
case 24576: type = LLM_TYPE_20B; break;
default: type = LLM_TYPE_UNKNOWN;
} break;
default: type = LLM_TYPE_UNKNOWN;
}
}
void llama_model_gptneox::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}, 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.attn_norm_b = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "bias", 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.wqkv_b = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}, 0);
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
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_down_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, 0);
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 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_gptneox::build_arch_graph(const llm_graph_params & params) const {
return std::make_unique<graph>(*this, params);
}
llama_model_gptneox::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());