Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
change
sglang
Commits
ea34350d
Unverified
Commit
ea34350d
authored
Nov 25, 2024
by
Lianmin Zheng
Committed by
GitHub
Nov 25, 2024
Browse files
Rename double sparsity config file (#2188)
parent
1605ae12
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
5 additions
and
3 deletions
+5
-3
.github/workflows/pr-test.yml
.github/workflows/pr-test.yml
+2
-2
test/srt/double-sparsity-config-Llama-3.1-8B-Instruct.json
test/srt/double-sparsity-config-Llama-3.1-8B-Instruct.json
+0
-0
test/srt/test_double_sparsity.py
test/srt/test_double_sparsity.py
+3
-1
No files found.
.github/workflows/pr-test.yml
View file @
ea34350d
...
...
@@ -84,7 +84,7 @@ jobs:
timeout-minutes
:
25
run
:
|
cd test/srt
python3 run_suite.py --suite minimal --range-begin 14 --range-end 2
1
python3 run_suite.py --suite minimal --range-begin 14 --range-end 2
3
unit-test-backend-part-4
:
if
:
github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
...
...
@@ -101,7 +101,7 @@ jobs:
timeout-minutes
:
25
run
:
|
cd test/srt
python3 run_suite.py --suite minimal --range-begin 2
1
python3 run_suite.py --suite minimal --range-begin 2
3
unit-test-backend-2-gpu-part-1
:
if
:
github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
...
...
test/srt/Llama-3.1-8B-Instruct.json
→
test/srt/
double-sparsity-config-
Llama-3.1-8B-Instruct.json
View file @
ea34350d
File moved
test/srt/test_double_sparsity.py
View file @
ea34350d
...
...
@@ -18,7 +18,9 @@ class TestDoubleSparsity(unittest.TestCase):
cls
.
model
=
DEFAULT_MODEL_NAME_FOR_TEST
cls
.
base_url
=
DEFAULT_URL_FOR_TEST
dirpath
=
os
.
path
.
dirname
(
__file__
)
config_file
=
os
.
path
.
join
(
dirpath
,
"Llama-3.1-8B-Instruct.json"
)
config_file
=
os
.
path
.
join
(
dirpath
,
"double-sparsity-config-Llama-3.1-8B-Instruct.json"
)
# NOTE: Generate the config file by running https://github.com/andy-yang-1/DoubleSparse/blob/main/evaluation/group_channel_config.py
cls
.
process
=
popen_launch_server
(
cls
.
model
,
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment