jmikola

<?php

$m = new MongoClient();
$c = $m->test->foo;
$c->drop();
$c->insert(['_id' => 1, 'x' => str_repeat('z', 1024*1024*4)]);
$c->insert(['_id' => 2, 'x' => str_repeat('z', 1024*1024*4)]);
$c->insert(['_id' => 3, 'x' => str_repeat('z', 1024*1024*4)]);
$c->insert(['_id' => 4, 'x' => str_repeat('z', 1024*1024*4)]);
$c->insert(['_id' => 5, 'x' => str_repeat('z', 1024*1024*4)]);

michilu

#!/usr/bin/env python
from functools32 import lru_cache
from time import time
import random
import sys

def benchtime(fn):
    oldtime = time()
    fn()
    return time() - oldtime

vinhkhuc

"""
Vanilla Char-RNN using TensorFlow by Vinh Khuc (@knvinh).
Adapted from Karpathy's min-char-rnn.py
https://gist.github.com/karpathy/d4dee566867f8291f086
Requires tensorflow>=1.0
BSD License
"""
import random
import numpy as np
import tensorflow as tf

gmr

module("resty.consul", package.seeall)

_VERSION = '0.1.0'

function service_nodes(service)
  local http = require "resty.http"
  local json = require "cjson"
  local hc = http:new()

  local upstream = ""

jmp84

import argparse
import logging

import torch
from fairseq.checkpoint_utils import load_model_ensemble_and_task
from fairseq.sequence_generator import SequenceGenerator


def get_args():
    parser = argparse.ArgumentParser(

lsawaniewski

# Htop
sudo apt install -y htop

# Byobu
sudo apt install -y byobu

# Gdebi
sudo apt install -y gdebi-core

# GIT

Reddine

sudo apt-get install build-essential
sudo apt-get update
# BLAS → LAPACK → ATLAS → numpy → scipy → Theano
# remove numpy and scipy
sudo apt-get remove python-numpy
sudo apt-get remove python-scipy
# Instalation commands
sudo apt-get install gfortran
sudo apt-get install libopenblas-dev
sudo apt-get install liblapack-dev

mingfeima

benchmark

Based on huggingface repo for performance evaluation, actual benchmark run script placed at repo. How to reproduce performance:

1. prepare dataset according to link.
2. update GLUE_DIR to actual dataset path in run_inference.sh.
3. change env settings, the default setting is using 20 cores;

MKL v.s. MKLDNN

Inference performance result on Xeon 6148 (2x20 cores), single socket and single thread.

wphicks

akurniawan

import itertools
import torch
from torchtext.experimental.datasets.translation import DATASETS, TranslationDataset
from torchtext.vocab import build_vocab_from_iterator
from torchtext.experimental.functional import (
    vocab_func,
    totensor,
    sequential_transforms,
)
from torchtext.data.utils import get_tokenizer