This doc servers as a quick reference for the _scaled_mm API and how it has changed overtime for each major version of PyTorch.
NOTE The leading underscore is intended here and we make no current FC/BC guarantees on this API. That being said it is currently the only OP that has native support for FP8 matmuls within the PyTorch Libary. We are planning to make an official Public api for this. Until then this is subject to change but you can use this doc as a reference.
| import time | |
| import argparse | |
| import numpy as np | |
| import mxnet as mx | |
| import gluonnlp as nlp | |
| import tvm | |
| from tvm import relay | |
| import tvm.contrib.graph_runtime as runtime | |
| def timer(thunk, repeat=1, number=10, dryrun=3, min_repeat_ms=1000): |
| import argparse | |
| import json | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument('in_file', type=str) | |
| parser.add_argument('out_file', type=str) | |
| args = parser.parse_args() | |
| def transform(line): |
| /* | |
| * Copyright (c) 2009-2017, Farooq Mela | |
| * All rights reserved. | |
| * | |
| * Redistribution and use in source and binary forms, with or without | |
| * modification, are permitted provided that the following conditions are met: | |
| * | |
| * 1. Redistributions of source code must retain the above copyright | |
| * notice, this list of conditions and the following disclaimer. | |
| * 2. Redistributions in binary form must reproduce the above copyright |
