mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-05-03 06:01:35 +00:00
Refactor: restructure repository to focus on kt-kernel and KT-SFT modulesq recon (#1581)
* refactor: move legacy code to archive/ directory - Moved ktransformers, csrc, third_party, merge_tensors to archive/ - Moved build scripts and configurations to archive/ - Kept kt-kernel, KT-SFT, doc, and README files in root - Preserved complete git history for all moved files * refactor: restructure repository to focus on kt-kernel and KT-SFT modules * fix README * fix README * fix README * fix README * docs: add performance benchmarks to kt-kernel section Add comprehensive performance data for kt-kernel to match KT-SFT's presentation: - AMX kernel optimization: 21.3 TFLOPS (3.9× faster than PyTorch) - Prefill phase: up to 20× speedup vs baseline - Decode phase: up to 4× speedup - NUMA optimization: up to 63% throughput improvement - Multi-GPU (8×L20): 227.85 tokens/s total throughput with DeepSeek-R1 FP8 Source: https://lmsys.org/blog/2025-10-22-KTransformers/ This provides users with concrete performance metrics for both core modules, making it easier to understand the capabilities of each component. * refactor: improve kt-kernel performance data with specific hardware and models Replace generic performance descriptions with concrete benchmarks: - Specify exact hardware: 8×L20 GPU + Xeon Gold 6454S, Single/Dual-socket Xeon + AMX - Include specific models: DeepSeek-R1-0528 (FP8), DeepSeek-V3 (671B) - Show detailed metrics: total throughput, output throughput, concurrency details - Match KT-SFT presentation style for consistency This provides users with actionable performance data they can use to evaluate hardware requirements and expected performance for their use cases. * fix README * docs: clean up performance table and improve formatting * add pic for README * refactor: simplify .gitmodules and backup legacy submodules - Remove 7 legacy submodules from root .gitmodules (archive/third_party/*) - Keep only 2 active submodules for kt-kernel (llama.cpp, pybind11) - Backup complete .gitmodules to archive/.gitmodules - Add documentation in archive/README.md for researchers who need legacy submodules This reduces initial clone size by ~500MB and avoids downloading unused dependencies. * refactor: move doc/ back to root directory Keep documentation in root for easier access and maintenance. * refactor: consolidate all images to doc/assets/ - Move kt-kernel/assets/heterogeneous_computing.png to doc/assets/ - Remove KT-SFT/assets/ (images already in doc/assets/) - Update KT-SFT/README.md image references to ../doc/assets/ - Eliminates ~7.9MB image duplication - Centralizes all documentation assets in one location * fix pic path for README
This commit is contained in:
Jiaqi Liao
GitHub
parent
8729435d85
commit
57d14d22bc
510 changed files with 711 additions and 334 deletions
71
archive/csrc/ktransformers_ext/cuda/binding.cpp
Normal file
71
archive/csrc/ktransformers_ext/cuda/binding.cpp
Normal file
|
|
@ -0,0 +1,71 @@
|
|||
/**
|
||||
* @Description :
|
||||
* @Author : Azure-Tang, Boxin Zhang
|
||||
* @Date : 2024-07-25 13:38:30
|
||||
* @Version : 0.2.2
|
||||
* @Copyright (c) 2024 by KVCache.AI, All Rights Reserved.
|
||||
**/
|
||||
|
||||
#include "custom_gguf/ops.h"
|
||||
#ifdef KTRANSFORMERS_USE_CUDA
|
||||
#include "gptq_marlin/ops.h"
|
||||
#endif
|
||||
// Python bindings
|
||||
#include <pybind11/pybind11.h>
|
||||
#include <pybind11/stl.h>
|
||||
#include <torch/library.h>
|
||||
#include <torch/extension.h>
|
||||
#include <torch/torch.h>
|
||||
// namespace py = pybind11;
|
||||
|
||||
PYBIND11_MODULE(KTransformersOps, m) {
|
||||
|
||||
m.def("dequantize_q8_0", [](const intptr_t data, int num_bytes, int blk_size, const int ele_per_blk, torch::Device device, py::object target_dtype) {
|
||||
torch::Dtype dtype = torch::python::detail::py_object_to_dtype(target_dtype);
|
||||
return dequantize_q8_0((int8_t*)data, num_bytes, blk_size, ele_per_blk, device, dtype);
|
||||
}, "Function to dequantize q8_0 data.",
|
||||
py::arg("data"), py::arg("num_bytes"), py::arg("blk_size"), py::arg("ele_per_blk"), py::arg("device"), py::arg("target_dtype"));
|
||||
|
||||
m.def("dequantize_q6_k", [](const intptr_t data, int num_bytes, int blk_size, const int ele_per_blk, torch::Device device, py::object target_dtype) {
|
||||
torch::Dtype dtype = torch::python::detail::py_object_to_dtype(target_dtype);
|
||||
return dequantize_q6_k((int8_t*)data, num_bytes, blk_size, ele_per_blk, device, dtype);
|
||||
}, "Function to dequantize q6_k data.",
|
||||
py::arg("data"), py::arg("num_bytes"), py::arg("blk_size"), py::arg("ele_per_blk"), py::arg("device"), py::arg("target_dtype"));
|
||||
|
||||
m.def("dequantize_q5_k", [](const intptr_t data, int num_bytes, int blk_size, const int ele_per_blk, torch::Device device, py::object target_dtype) {
|
||||
torch::Dtype dtype = torch::python::detail::py_object_to_dtype(target_dtype);
|
||||
return dequantize_q5_k((int8_t*)data, num_bytes, blk_size, ele_per_blk, device, dtype);
|
||||
}, "Function to dequantize q5_k data.",
|
||||
py::arg("data"), py::arg("num_bytes"), py::arg("blk_size"), py::arg("ele_per_blk"), py::arg("device"), py::arg("target_dtype"));
|
||||
|
||||
m.def("dequantize_q4_k", [](const intptr_t data, int num_bytes, int blk_size, const int ele_per_blk, torch::Device device, py::object target_dtype) {
|
||||
torch::Dtype dtype = torch::python::detail::py_object_to_dtype(target_dtype);
|
||||
return dequantize_q4_k((int8_t*)data, num_bytes, blk_size, ele_per_blk, device, dtype);
|
||||
}, "Function to dequantize q4_k data.",
|
||||
py::arg("data"), py::arg("num_bytes"), py::arg("blk_size"), py::arg("ele_per_blk"), py::arg("device"), py::arg("target_dtype"));
|
||||
|
||||
m.def("dequantize_q3_k", [](const intptr_t data, int num_bytes, int blk_size, const int ele_per_blk, torch::Device device, py::object target_dtype) {
|
||||
torch::Dtype dtype = torch::python::detail::py_object_to_dtype(target_dtype);
|
||||
return dequantize_q3_k((int8_t*)data, num_bytes, blk_size, ele_per_blk, device, dtype);
|
||||
}, "Function to dequantize q3_k data.",
|
||||
py::arg("data"), py::arg("num_bytes"), py::arg("blk_size"), py::arg("ele_per_blk"), py::arg("device"), py::arg("target_dtype"));
|
||||
|
||||
m.def("dequantize_q2_k", [](const intptr_t data, int num_bytes, int blk_size, const int ele_per_blk, torch::Device device, py::object target_dtype) {
|
||||
torch::Dtype dtype = torch::python::detail::py_object_to_dtype(target_dtype);
|
||||
return dequantize_q2_k((int8_t*)data, num_bytes, blk_size, ele_per_blk, device, dtype);
|
||||
}, "Function to dequantize q2_k data.",
|
||||
py::arg("data"), py::arg("num_bytes"), py::arg("blk_size"), py::arg("ele_per_blk"), py::arg("device"), py::arg("target_dtype"));
|
||||
|
||||
m.def("dequantize_iq4_xs", [](const intptr_t data, int num_bytes, int blk_size, const int ele_per_blk, torch::Device device, py::object target_dtype) {
|
||||
torch::Dtype dtype = torch::python::detail::py_object_to_dtype(target_dtype);
|
||||
return dequantize_iq4_xs((int8_t*)data, num_bytes, blk_size, ele_per_blk, device, dtype);
|
||||
}, "Function to dequantize iq4_xs data.",
|
||||
py::arg("data"), py::arg("num_bytes"), py::arg("blk_size"), py::arg("ele_per_blk"), py::arg("device"), py::arg("target_dtype"));
|
||||
|
||||
#ifdef KTRANSFORMERS_USE_CUDA
|
||||
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"),
|
||||
py::arg("size_n"), py::arg("size_k"), py::arg("is_k_full"));
|
||||
#endif
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue