thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

Updated docs and renamig kp::Constants

Browse source 
Signed-off-by: Alejandro Saucedo <axsauze@gmail.com>
This commit is contained in:
Alejandro Saucedo 2021-09-12 16:51:43 +01:00
parent 990ccd5f3b
commit 932620091c
14 changed files with 162 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

12
python/src/docstrings.hpp
View file

@ -36,9 +36,9 @@ tensors (optional) The tensors to use to create the descriptor
resources @param spirv (optional) The spirv code to use to create the
algorithm @param workgroup (optional) The kp::Workgroup to use for the
dispatch which defaults to kp::Workgroup(tensor[0].size(), 1, 1) if
not set. @param specializationConstants (optional) The kp::Constants
not set. @param specializationConstants (optional) The std::vector<float>
to use to initialize the specialization constants which cannot be
changed once set. @param pushConstants (optional) The kp::Constants to
changed once set. @param pushConstants (optional) The std::vector<float> to
use when initializing the pipeline, which set the size of the push
constants - these can be modified but all new values must have the
same vector size as this initial value.)doc";
@ -54,12 +54,12 @@ static const char *__doc_kp_Algorithm_destroy = R"doc()doc";
static const char *__doc_kp_Algorithm_getPush =
R"doc(Gets the specialization constants of the current algorithm.
@returns The kp::Constants currently set for push constants)doc";
@returns The std::vector<float> currently set for push constants)doc";
static const char *__doc_kp_Algorithm_getSpecializationConstants =
R"doc(Gets the specialization constants of the current algorithm.
@returns The kp::Constants currently set for specialization constants)doc";
@returns The std::vector<float> currently set for specialization constants)doc";
static const char *__doc_kp_Algorithm_getTensors =
R"doc(Gets the current tensors that are used in the algorithm.
@ -127,9 +127,9 @@ parameters to create the underlying resources.
@param spirv The spirv code to use to create the algorithm @param
workgroup (optional) The kp::Workgroup to use for the dispatch which
defaults to kp::Workgroup(tensor[0].size(), 1, 1) if not set. @param
specializationConstants (optional) The kp::Constants to use to
specializationConstants (optional) The std::vector<float> to use to
initialize the specialization constants which cannot be changed once
set. @param pushConstants (optional) The kp::Constants to use when
set. @param pushConstants (optional) The std::vector<float> to use when
initializing the pipeline, which set the size of the push constants -
these can be modified but all new values must have the same vector
size as this initial value.)doc";

4
python/src/main.cpp
View file

@ -74,9 +74,9 @@ PYBIND11_MODULE(kp, m) {
py::class_<kp::OpAlgoDispatch, std::shared_ptr<kp::OpAlgoDispatch>>(
m, "OpAlgoDispatch", py::base<kp::OpBase>(), DOC(kp, OpAlgoDispatch))
.def(py::init<const std::shared_ptr<kp::Algorithm>&,const kp::Constants&>(),
.def(py::init<const std::shared_ptr<kp::Algorithm>&,const std::vector<float>&>(),
DOC(kp, OpAlgoDispatch, OpAlgoDispatch),
py::arg("algorithm"), py::arg("push_consts") = kp::Constants())
py::arg("algorithm"), py::arg("push_consts") = std::vector<float>())
.def(py::init(&opAlgoDispatchPyInit),
DOC(kp, OpAlgoDispatch, OpAlgoDispatch),
py::arg("algorithm"), py::arg("push_consts"));