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 '2948e6049a4ad0f96a4ab15246db2d2086b80703' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	CONTRIBUTING.md
#	docs/backend/VirtGPU/development.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	embd_res/templates/GigaChat3-10B-A1.8B.jinja
#	embd_res/templates/GigaChat3.1-10B-A1.8B.jinja
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo
2026-03-15 11:21:24 +08:00
parent 67c9798d0b 2948e6049a
commit b1c500ae2b
72 changed files with 2338 additions and 430 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+49 -7
View File
@@ -5168,23 +5168,23 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
layer.attn_sub_norm = create_tensor(tn(LLM_TENSOR_ATTN_SUB_NORM, "weight", i), {n_embd}, 0);
layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}, 0);
layer.wq_scale = create_tensor(tn(LLM_TENSOR_ATTN_Q, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.wq_s = create_tensor(tn(LLM_TENSOR_ATTN_Q, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.wk = create_tensor(tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}, 0);
layer.wk_scale = create_tensor(tn(LLM_TENSOR_ATTN_K, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.wk_s = create_tensor(tn(LLM_TENSOR_ATTN_K, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.wv = create_tensor(tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}, 0);
layer.wv_scale = create_tensor(tn(LLM_TENSOR_ATTN_V, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.wv_s = create_tensor(tn(LLM_TENSOR_ATTN_V, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
layer.wo_scale = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.wo_s = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
layer.ffn_sub_norm = create_tensor(tn(LLM_TENSOR_FFN_SUB_NORM, "weight", i), {n_ff}, 0);
layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
layer.ffn_gate_scale = create_tensor(tn(LLM_TENSOR_FFN_GATE, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.ffn_gate_s = create_tensor(tn(LLM_TENSOR_FFN_GATE, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, 0);
layer.ffn_down_scale = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.ffn_down_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
layer.ffn_up_scale = create_tensor(tn(LLM_TENSOR_FFN_UP, "scale", i), {1}, TENSOR_NOT_REQUIRED);
layer.ffn_up_s = create_tensor(tn(LLM_TENSOR_FFN_UP, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
} break;
case LLM_ARCH_T5:
@@ -7601,6 +7601,48 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
default:
throw std::runtime_error("unknown architecture");
}
// generic pass: load optional per-tensor/per-expert ".scale" tensors (e.g. NVFP4 scale2)
// this avoids having to add scale loading to every architecture
for (int i = 0; i < n_layer; ++i) {
auto & layer = layers[i];
// attention weight scales (per-tensor, shape {1})
if (!layer.wq_s && layer.wq) {
layer.wq_s = create_tensor(tn(LLM_TENSOR_ATTN_Q, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.wk_s && layer.wk) {
layer.wk_s = create_tensor(tn(LLM_TENSOR_ATTN_K, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.wv_s && layer.wv) {
layer.wv_s = create_tensor(tn(LLM_TENSOR_ATTN_V, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.wo_s && layer.wo) {
layer.wo_s = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
// dense FFN weight scales (per-tensor, shape {1})
if (!layer.ffn_gate_s && layer.ffn_gate) {
layer.ffn_gate_s = create_tensor(tn(LLM_TENSOR_FFN_GATE, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_down_s && layer.ffn_down) {
layer.ffn_down_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_up_s && layer.ffn_up) {
layer.ffn_up_s = create_tensor(tn(LLM_TENSOR_FFN_UP, "scale", i), {1}, TENSOR_NOT_REQUIRED);
}
// MoE expert weight scales (per-expert, shape {n_expert})
if (!layer.ffn_gate_exps_s && layer.ffn_gate_exps) {
layer.ffn_gate_exps_s = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_down_exps_s && layer.ffn_down_exps) {
layer.ffn_down_exps_s = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
}
if (!layer.ffn_up_exps_s && layer.ffn_up_exps) {
layer.ffn_up_exps_s = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
}
}
}
ml.done_getting_tensors();