-
Notifications
You must be signed in to change notification settings - Fork 205
88 lines (78 loc) · 5.32 KB
/
more-tests.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
80
81
82
83
84
85
86
87
88
name: Run parallel prefill
on:
pull_request:
push:
branches:
- main
workflow_dispatch:
jobs:
test-cuda:
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
runner: linux.g5.4xlarge.nvidia.gpu
gpu-arch-type: cuda
gpu-arch-version: "12.1"
timeout: 60
script: |
echo "::group::Print machine info"
uname -a
echo "::endgroup::"
echo "::group::Install newer objcopy that supports --set-section-alignment"
yum install -y devtoolset-10-binutils
export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH
echo "::endgroup::"
echo "::group::Download checkpoints"
# Install requirements
./install/install_requirements.sh cuda
pip3 list
python3 -c 'import torch;print(f"torch: {torch.__version__, torch.version.git_version}")'
echo "::endgroup::"
echo "::group::Download checkpoints"
mkdir -p checkpoints/stories15M
pushd checkpoints/stories15M
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories15M.pt
wget https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
popd
echo "::endgroup::"
echo "::group::Run inference"
export MODEL_PATH=checkpoints/stories15M/stories15M.pt
export MODEL_NAME=stories15M
export MODEL_DIR=/tmp
for DTYPE in bfloat16 float16 float32; do
###################################################################
# group with different temperatures
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 0
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 0.9
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 1.0
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 100
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 200
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 500
###################################################################
# group with different temperatures and prefill, and compile
# and prefill compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 0 --compile --compile-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 0.9 --compile --compile-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 1.0 --compile --compile-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 100 --compile --compile-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 200 --compile --compile-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 500 --compile --compile-prefill
###################################################################
# group with different temperatures and sequential prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 0 --sequential-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 0.9 --sequential-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 1.0 --sequential-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 100 --sequential-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 200 --sequential-prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 500 --sequential-prefill
###################################################################
# group with different temperatures and prefill, and compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 0 --sequential-prefill --compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 0.9 --sequential-prefill --compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 1.0 --sequential-prefill --compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 100 --sequential-prefill --compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 200 --sequential-prefill --compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --top-k 500 --sequential-prefill --compile
done
echo "tests complete"
echo "******************************************"
echo "::endgroup::"