Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'ded446b34c0cd803a0122446b848619adbb458cf' into concedo_experimental

Browse Source 
# Conflicts:
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2026-03-29 01:24:31 +08:00
parent 8760d22a84 ded446b34c
commit 3eedde8ab5
15 changed files with 553 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+59
View File
@@ -7736,6 +7736,65 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
if (!layer.ssm_beta_s && layer.ssm_beta) {
layer.ssm_beta_s = create_tensor(tn(LLM_TENSOR_SSM_BETA, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
// input scales
if (!layer.wq_in_s && layer.wq) {
layer.wq_in_s = create_tensor(tn(LLM_TENSOR_ATTN_Q, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.wk_in_s && layer.wk) {
layer.wk_in_s = create_tensor(tn(LLM_TENSOR_ATTN_K, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.wv_in_s && layer.wv) {
layer.wv_in_s = create_tensor(tn(LLM_TENSOR_ATTN_V, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.wo_in_s && layer.wo) {
layer.wo_in_s = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.wqkv_in_s && layer.wqkv) {
layer.wqkv_in_s = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.wqkv_gate_in_s && layer.wqkv_gate) {
layer.wqkv_gate_in_s = create_tensor(tn(LLM_TENSOR_ATTN_GATE, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_gate_in_s && layer.ffn_gate) {
layer.ffn_gate_in_s = create_tensor(tn(LLM_TENSOR_FFN_GATE, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_down_in_s && layer.ffn_down) {
layer.ffn_down_in_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_up_in_s && layer.ffn_up) {
layer.ffn_up_in_s = create_tensor(tn(LLM_TENSOR_FFN_UP, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_gate_exps_in_s && layer.ffn_gate_exps) {
layer.ffn_gate_exps_in_s = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "input_scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_down_exps_in_s && layer.ffn_down_exps) {
layer.ffn_down_exps_in_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "input_scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_up_exps_in_s && layer.ffn_up_exps) {
layer.ffn_up_exps_in_s = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "input_scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_gate_shexp_in_s && layer.ffn_gate_shexp) {
layer.ffn_gate_shexp_in_s = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_down_shexp_in_s && layer.ffn_down_shexp) {
layer.ffn_down_shexp_in_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_up_shexp_in_s && layer.ffn_up_shexp) {
layer.ffn_up_shexp_in_s = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ssm_in_in_s && layer.ssm_in) {
layer.ssm_in_in_s = create_tensor(tn(LLM_TENSOR_SSM_IN, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ssm_out_in_s && layer.ssm_out) {
layer.ssm_out_in_s = create_tensor(tn(LLM_TENSOR_SSM_OUT, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ssm_alpha_in_s && layer.ssm_alpha) {
layer.ssm_alpha_in_s = create_tensor(tn(LLM_TENSOR_SSM_ALPHA, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ssm_beta_in_s && layer.ssm_beta) {
layer.ssm_beta_in_s = create_tensor(tn(LLM_TENSOR_SSM_BETA, "input_scale", i), {1}, TENSOR_NOT_REQUIRED);
}
}
}