Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-cache.yml
#	.github/workflows/build-cmake-pkg.yml
#	.github/workflows/build-linux-cross.yml
#	.github/workflows/build.yml
#	.github/workflows/check-vendor.yml
#	.github/workflows/close-issue.yml
#	.github/workflows/copilot-setup-steps.yml
#	.github/workflows/docker.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/gguf-publish.yml
#	.github/workflows/labeler.yml
#	.github/workflows/pre-tokenizer-hashes.yml
#	.github/workflows/python-check-requirements.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/python-type-check.yml
#	.github/workflows/release.yml
#	.github/workflows/server-webui.yml
#	.github/workflows/server.yml
#	.github/workflows/update-ops-docs.yml
#	.github/workflows/winget.yml
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	requirements/requirements-tool_bench.txt
#	src/CMakeLists.txt
#	src/llama-quant.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/cli/cli.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-01-23 14:27:04 +08:00
parent 5c6cc02985 a3e812811d
commit e8e7c357c9
54 changed files with 2348 additions and 1040 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.cpp
+6 -2
View File
@@ -1594,6 +1594,10 @@ ggml_cgraph * llama_kv_cache::build_graph_shift(llm_graph_result * res, llama_co
const auto & n_embd_head_k = hparams.n_embd_head_k;
//const auto & n_embd_head_v = hparams.n_embd_head_v;
const auto & n_rot = hparams.n_rot;
const auto n_embd_nope = hparams.n_lora_kv > 0 ? n_embd_head_k - n_rot : 0;
auto inp = std::make_unique<llm_graph_input_k_shift>(this);
inp->k_shift = ggml_new_tensor_1d(ctx, GGML_TYPE_I32, (int64_t) get_size()*n_stream);
@@ -1614,10 +1618,10 @@ ggml_cgraph * llama_kv_cache::build_graph_shift(llm_graph_result * res, llama_co
ggml_tensor * k =
ggml_view_3d(ctx, layer.k,
n_embd_head_k, n_head_kv, get_size()*n_stream,
n_rot, n_head_kv, get_size()*n_stream,
ggml_row_size(layer.k->type, n_embd_head_k),
ggml_row_size(layer.k->type, n_embd_k_gqa),
0);
ggml_row_size(layer.k->type, n_embd_nope));
ggml_tensor * cur = build_rope_shift(cparams, ctx, k, inp->k_shift, rope_factors, freq_base_l, freq_scale_l);