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 branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/release.yml
#	app/llama.cpp
#	build-xcframework.sh
#	docs/speculative.md
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/set_rows.wgsl
#	requirements/requirements-server-bench.txt
#	scripts/server-bench.py
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-31 02:06:39 +08:00
parent 478e64e549 d6588daa80
commit c1b817032e
34 changed files with 1405 additions and 509 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+5 -5
View File
@@ -542,16 +542,16 @@ struct ggml_backend_meta_split_state llama_meta_device_get_split_state(const str
auto get_tensor_config = [&]() -> tensor_config {
// standard attention
if (std::regex_match(tensor_name, pattern_q_weight) || std::regex_match(tensor_name, pattern_kv_weight)) {
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_1, "attn_output.weight");
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_1, "attn_output.weight", "ssm_out.weight");
}
if (std::regex_match(tensor_name, pattern_q_bias) || std::regex_match(tensor_name, pattern_kv_bias)) {
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_0, "attn_output.weight");
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_0, "attn_output.weight", "ssm_out.weight");
}
if (std::regex_match(tensor_name, pattern_qkv_weight)) {
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_1);
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_1, "attn_output.weight", "ssm_out.weight");
}
if ( std::regex_match(tensor_name, pattern_qkv_bias)) {
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_0);
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_0, "attn_output.weight", "ssm_out.weight");
}
if (std::regex_match(tensor_name, pattern_qk_norm)) {
return get_tensor_config_impl(tensor->ne[1] == 1 ? GGML_BACKEND_SPLIT_AXIS_MIRRORED : GGML_BACKEND_SPLIT_AXIS_1, "attn_output.weight");
@@ -567,7 +567,7 @@ struct ggml_backend_meta_split_state llama_meta_device_get_split_state(const str
}
if (std::regex_match(tensor_name, pattern_attn_gate_weight)) {
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_1);
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_1, "attn_output.weight", "ssm_out.weight");
}
if (std::regex_match(tensor_name, pattern_ssm_dt) || std::regex_match(tensor_name, pattern_ssm_a)) {
return get_tensor_config_impl(GGML_BACKEND_SPLIT_AXIS_0, "ssm_out.weight");