vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 10:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/llama-cpp-cuda.srpm.spec
#	.devops/llama-cpp.srpm.spec
#	.devops/nix/package.nix
#	.devops/rocm.Dockerfile
#	.github/ISSUE_TEMPLATE/020-enhancement.yml
#	.github/ISSUE_TEMPLATE/030-research.yml
#	.github/ISSUE_TEMPLATE/040-refactor.yml
#	.github/ISSUE_TEMPLATE/config.yml
#	.github/pull_request_template.md
#	.github/workflows/bench.yml.disabled
#	.github/workflows/build.yml
#	.github/workflows/labeler.yml
#	CONTRIBUTING.md
#	Makefile
#	README.md
#	SECURITY.md
#	ci/README.md
#	common/CMakeLists.txt
#	docs/android.md
#	docs/backend/SYCL.md
#	docs/build.md
#	docs/cuda-fedora.md
#	docs/development/HOWTO-add-model.md
#	docs/docker.md
#	docs/install.md
#	docs/llguidance.md
#	examples/cvector-generator/README.md
#	examples/imatrix/README.md
#	examples/imatrix/imatrix.cpp
#	examples/llama.android/llama/src/main/cpp/CMakeLists.txt
#	examples/llama.swiftui/README.md
#	examples/llama.vim
#	examples/lookahead/README.md
#	examples/lookup/README.md
#	examples/main/README.md
#	examples/passkey/README.md
#	examples/pydantic_models_to_grammar_examples.py
#	examples/retrieval/README.md
#	examples/server/CMakeLists.txt
#	examples/server/README.md
#	examples/simple-cmake-pkg/README.md
#	examples/speculative/README.md
#	flake.nix
#	grammars/README.md
#	pyproject.toml
#	scripts/check-requirements.sh
This commit is contained in:
Concedo 2025-02-16 02:08:39 +08:00
commit f144b1f345
44 changed files with 276250 additions and 93 deletions
Download patch file Download diff file Expand all files Collapse all files

11
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
View file

@ -59,6 +59,8 @@ const std::vector<std::string> type_names = {
"q4_k",
"q5_k",
"q6_k",
"iq1_s",
"iq1_m",
"iq2_xxs",
"iq2_xs",
"iq2_s",
@ -186,6 +188,13 @@ std::string to_uppercase(const std::string& input) {
return result;
}
bool string_starts_with(const std::string& str, const std::string& prefix) {
if (prefix.size() > str.size()) {
return false;
}
return std::equal(prefix.begin(), prefix.end(), str.begin());
}
bool string_ends_with(const std::string& str, const std::string& suffix) {
if (suffix.size() > str.size()) {
return false;
@ -393,7 +402,7 @@ void process_shaders() {
for (const auto& tname : type_names) {
// mul mat vec
std::string data_a_key = "DATA_A_" + to_uppercase(tname);
std::string shader = (string_ends_with(tname, "_k")) ? "mul_mat_vec_" + tname + ".comp" : "mul_mat_vec.comp";
std::string shader = (string_ends_with(tname, "_k") || string_starts_with(tname, "iq1_")) ? "mul_mat_vec_" + tname + ".comp" : "mul_mat_vec.comp";
string_to_spv("mul_mat_vec_" + tname + "_f32_f32", shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "float"}, {"B_TYPE_VEC2", "vec2"}, {"B_TYPE_VEC4", "vec4"}, {"D_TYPE", "float"}}));
string_to_spv("mul_mat_vec_" + tname + "_f16_f32", shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "float16_t"}, {"B_TYPE_VEC2", "f16vec2"}, {"B_TYPE_VEC4", "f16vec4"}, {"D_TYPE", "float"}}));