forked from deepspeedai/DeepSpeed
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy path_config.yml
More file actions
121 lines (109 loc) · 2.91 KB
/
Copy path_config.yml
File metadata and controls
121 lines (109 loc) · 2.91 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
title: DeepSpeed
email: [email protected]
description: >-
DeepSpeed is a deep learning optimization library that makes distributed
training easy, efficient, and effective.
locale : "en-US"
logo: /assets/images/deepspeed-logo-uppercase-bold-white-1.15.svg
repository: microsoft/DeepSpeed
baseurl: "/" # the subpath of your site, e.g. /blog
url: "https://www.deepspeed.ai" # the base hostname & protocol for your site, e.g. http://example.com
# Build settings
remote_theme: "mmistakes/[email protected]"
minimal_mistakes_skin : "air"
search: true
plugins:
- jekyll-feed
- jekyll-include-cache
- jekyll-paginate
#paginate: 10
#paginate_path: /blog/page:num
include: ["_pages"]
exclude: ["code-docs"]
collections:
tutorials:
output: true
permalink: /:collection/:path/
order:
- advanced-install.md
- getting-started.md
- azure.md
- automatic-tensor-parallelism.md
- bert-finetuning.md
- bert-pretraining.md
- cifar-10.md
- curriculum-learning.md
- data-efficiency.md
- ds4sci_evoformerattention.md
- flops-profiler.md
- pytorch-profiler.md
- autotuning.md
- gan.md
- lrrt.md
- megatron.md
- mixture-of-experts.md
- mixture-of-experts-nlg.md
- mixture-of-experts-inference.md
- model-compression.md
- monitor.md
- comms-logging.md
- one-cycle.md
- onebit-adam.md
- zero-one-adam.md
- onebit-lamb.md
- pipeline.md
- progressive_layer_dropping.md
- sparse-attention.md
- transformer_kernel.md
- zero-offload.md
- zero.md
defaults:
- scope:
path: ""
values:
layout: single
author_profile: false
read_time: false
comments: false
share: false
related: false
sneak_preview: false
toc: true
toc_label: "Contents"
sidebar:
nav: "lnav"
- scope:
path: "_pages"
values:
permalink: /docs/:basename/
toc: true
toc_label: "Contents"
- scope:
path: ""
type: posts
values:
layout: single-full
author_profile: false
read_time: false
comments: false
share: true
related: false
toc: true
toc_label: "Contents"
toc_sticky: true
show_date: true
- scope:
path: ""
type: tutorials
values:
layout: single
toc_sticky: true
analytics:
provider: "google-gtag"
google:
tracking_id: "UA-169781858-1"
timezone: America/Los_Angeles
breadcrumbs: true
press_release_v3: https://www.microsoft.com/en-us/research/blog/deepspeed-extreme-scale-model-training-for-everyone/
press_release_v5: https://www.microsoft.com/en-us/research/blog/deepspeed-powers-8x-larger-moe-model-training-with-high-performance/
press_release_v6: https://www.microsoft.com/en-us/research/blog/deepspeed-advancing-moe-inference-and-training-to-power-next-generation-ai-scale/