This repository has been archived by the owner on Oct 11, 2024. It is now read-only.
forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 10
79 lines (72 loc) · 2.57 KB
/
nightly.yml
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
name: Nightly
run-name: ${{ github.actor }} triggered nightly on ${{ github.ref }}
on:
schedule:
# * is a special character in YAML so you have to quote this string
- cron: '0 0 * * *'
workflow_dispatch:
inputs:
push_benchmark_results_to_gh_pages:
description: "When set to true, the workflow pushes all benchmarking results to gh-pages UI "
type: choice
options:
- 'true'
- 'false'
default: 'false'
jobs:
NIGHTLY-MULTI:
uses: ./.github/workflows/build-test.yml
with:
label: aws-avx2-192G-4-a10g-96G
timeout: 240
gitref: ${{ github.ref }}
Gi_per_thread: 4
python: 3.10.12
test_skip_list:
secrets: inherit
NIGHTLY-SOLO:
uses: ./.github/workflows/build-test.yml
with:
label: aws-avx2-32G-a10g-24G
timeout: 300
gitref: ${{ github.ref }}
Gi_per_thread: 12
python: 3.11.4
test_skip_list:
secrets: inherit
# multi-gpu
# AWS-AVX2-192G-4-A10G-96G-Benchmark:
# uses: ./.github/workflows/nm-benchmark.yml
# with:
# label: aws-avx2-192G-4-a10g-96G
# benchmark_config_list_file: ./.github/data/nm_benchmark_nightly_configs_list.txt
# timeout: 480
# gitref: '${{ github.ref }}'
# Gi_per_thread: 4
# python: "3.10.12"
# # Always push if it is a scheduled job
# push_benchmark_results_to_gh_pages: "${{ github.event_name == 'schedule' || inputs.push_benchmark_results_to_gh_pages }}"
# secrets: inherit
# single gpu
AWS-AVX2-32G-A10G-24G-Benchmark:
uses: ./.github/workflows/nm-benchmark.yml
with:
label: aws-avx2-32G-a10g-24G
benchmark_config_list_file: ./.github/data/nm_benchmark_nightly_configs_list.txt
timeout: 720
gitref: '${{ github.ref }}'
Gi_per_thread: 12
python: "3.10.12"
# Always push if it is a scheduled job
push_benchmark_results_to_gh_pages: "${{ github.event_name == 'schedule' || inputs.push_benchmark_results_to_gh_pages }}"
secrets: inherit
# single gpu
AWS-AVX2-32G-A10G-24G-Accuracy:
uses: ./.github/workflows/nm-lm-eval-accuracy.yml
with:
label: aws-avx2-32G-a10g-24G
timeout: 60
gitref: '${{ github.ref }}'
Gi_per_thread: 12
python: "3.10.12"
secrets: inherit