vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-13 00:29:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Support IQ4_XS dequantize

Browse source
This commit is contained in:
Yap Sok Ann 2024-09-02 09:03:42 +07:00
parent 022b893819
commit be356c1b8d
5 changed files with 93 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/ktransformers_ext/cuda/binding.cpp
View file

@ -31,6 +31,8 @@ PYBIND11_MODULE(KTransformersOps, m) {
py::arg("data"), py::arg("blk_size"), py::arg("device"));
m.def("dequantize_q2_k", &dequantize_q2_k, "Function to dequantize q2_k data.",
py::arg("data"), py::arg("blk_size"), py::arg("device"));
m.def("dequantize_iq4_xs", &dequantize_iq4_xs, "Function to dequantize iq4_xs data.",
py::arg("data"), py::arg("blk_size"), py::arg("device"));
m.def("gptq_marlin_gemm", &gptq_marlin_gemm, "Function to perform GEMM using Marlin quantization.",
py::arg("a"), py::arg("b_q_weight"), py::arg("b_scales"), py::arg("g_idx"),
py::arg("perm"), py::arg("workspace"), py::arg("num_bits"), py::arg("size_m"),