mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-04-29 12:19:50 +00:00
* 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
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
#!/usr/bin/env python
|
|
# coding=utf-8
|
|
'''
|
|
Description : Implement singleton
|
|
Author : unicornchan
|
|
Date : 2024-06-11 17:08:36
|
|
Version : 1.0.0
|
|
LastEditors : chenxl
|
|
LastEditTime : 2024-07-27 01:55:56
|
|
'''
|
|
import abc
|
|
|
|
class Singleton(abc.ABCMeta, type):
|
|
"""_summary_
|
|
|
|
Args:
|
|
abc.ABCMeta: Provide a mechanism for defining abstract methods and properties,
|
|
enforcing subclasses to implement these methods and properties.
|
|
type: Inherit from 'type' to make 'Singleton' a metaclass,
|
|
enabling the implementation of the Singleton
|
|
"""
|
|
_instances = {}
|
|
|
|
def __call__(cls, *args, **kwds):
|
|
if cls not in cls._instances:
|
|
cls._instances[cls] = super(Singleton, cls).__call__(*args, **kwds)
|
|
return cls._instances[cls]
|
|
|
|
class AbstractSingleton(abc.ABC, metaclass=Singleton):
|
|
"""Provided an abstract Singleton base class, any class inheriting from
|
|
this base class will automatically become a Singleton class.
|
|
|
|
Args:
|
|
abc.ABC: Abstract base class, it cannot be instantiated, only inherited.
|
|
"""
|