Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-02 02:51:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CONTRIBUTING.md
#	docs/backend/CANN.md
#	examples/eval-callback/eval-callback.cpp
#	examples/model-conversion/requirements.txt
#	examples/model-conversion/scripts/causal/run-org-model.py
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	models/templates/README.md
#	requirements/requirements-convert_hf_to_gguf.txt
#	requirements/requirements-convert_legacy_llama.txt
#	requirements/requirements-tool_bench.txt
#	tests/.gitignore
#	tests/test-backend-ops.cpp
#	tests/test-chat-parser.cpp
#	tests/test-chat.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tests/test-tokenizer-random.py
This commit is contained in:
Concedo
2025-09-11 22:34:45 +08:00
parent 5de51b77c1 24a6734daf
commit 6463f5c26b
62 changed files with 3507 additions and 2153 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+22 -4
View File
@@ -1547,6 +1547,9 @@ void llama_model::load_hparams(llama_model_loader & ml) {
hparams.dec_start_token_id = dec_start_token_id;
}
hparams.dec_n_layer = hparams.n_layer;
ml.get_key(LLM_KV_DECODER_BLOCK_COUNT, hparams.dec_n_layer, false);
switch (hparams.n_layer) {
case 6: type = LLM_TYPE_60M; break; // t5-small
case 8: type = LLM_TYPE_80M; break; // flan-t5-small
@@ -4510,6 +4513,14 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
}
// n_layer: number of encoder_layers
// dec_n_layer: number of decoder_layers
const int dec_n_layer = hparams.dec_n_layer;
if (dec_n_layer > n_layer) {
layers.resize(dec_n_layer);
}
// load encoder layers
for (int i = 0; i < n_layer; ++i) {
auto & layer = layers[i];
@@ -4525,6 +4536,11 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
layer.ffn_gate_enc = create_tensor(tn(LLM_TENSOR_ENC_FFN_GATE, "weight", i), {n_embd, n_ff}, TENSOR_NOT_REQUIRED);
layer.ffn_down_enc = create_tensor(tn(LLM_TENSOR_ENC_FFN_DOWN, "weight", i), { n_ff, n_embd}, 0);
layer.ffn_up_enc = create_tensor(tn(LLM_TENSOR_ENC_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
}
// load decoder layers
for (int i = 0; i < dec_n_layer; ++i) {
auto & layer = layers[i];
layer.attn_norm = create_tensor(tn(LLM_TENSOR_DEC_ATTN_NORM, "weight", i), {n_embd}, 0);
layer.attn_rel_b = create_tensor(tn(LLM_TENSOR_DEC_ATTN_REL_B, "weight", i), {n_head, n_rel_attn_bkts}, TENSOR_NOT_REQUIRED);
@@ -13609,7 +13625,9 @@ struct llm_build_t5_dec : public llm_graph_context {
ggml_tensor * inp_out_ids = build_inp_out_ids();
for (int il = 0; il < n_layer; ++il) {
const int64_t dec_n_layer = hparams.dec_n_layer;
for (int il = 0; il < dec_n_layer; ++il) {
ggml_tensor * inpSA = inpL;
// norm
@@ -13700,7 +13718,7 @@ struct llm_build_t5_dec : public llm_graph_context {
//cb(cur, "kqv_out", il);
}
if (il == n_layer - 1 && inp_out_ids) {
if (il == dec_n_layer - 1 && inp_out_ids) {
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
inpCA = ggml_get_rows(ctx0, inpCA, inp_out_ids);
}
@@ -13721,8 +13739,8 @@ struct llm_build_t5_dec : public llm_graph_context {
model.layers[il].ffn_gate, NULL, NULL,
model.layers[il].ffn_down, NULL, NULL,
NULL,
model.layers[il].ffn_gate_enc ? LLM_FFN_GELU : LLM_FFN_RELU,
model.layers[il].ffn_gate_enc ? LLM_FFN_PAR : LLM_FFN_SEQ,
model.layers[il].ffn_gate ? LLM_FFN_GELU : LLM_FFN_RELU,
model.layers[il].ffn_gate ? LLM_FFN_PAR : LLM_FFN_SEQ,
il);
cb(cur, "ffn_out", il);
}