Skip to content

Add generate test #4181

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lvhan028 merged 18 commits into from
Dec 16, 2025
Merged

Add generate test #4181

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
fe427f2
TEST: add generate test
littlegy Nov 28, 2025
9d8368c
update test_input_ids_mode
littlegy Dec 4, 2025
de55eac
fix lint
littlegy Dec 4, 2025
ecf380a
update rl test
littlegy Dec 11, 2025
4faf231
Merge branch 'InternLM:main' into generate_test
littlegy Dec 12, 2025
936ca2a
fix mm processor args
CUHKSZzxy Dec 10, 2025
99be3c0
comment
CUHKSZzxy Dec 10, 2025
e63e462
optimize
CUHKSZzxy Dec 11, 2025
5bbff7f
add test case
CUHKSZzxy Dec 11, 2025
e401e5e
add comments
CUHKSZzxy Dec 11, 2025
571ca77
fix typo
CUHKSZzxy Dec 11, 2025
d36844b
fix generate
CUHKSZzxy Dec 11, 2025
e46e5ec
warning
CUHKSZzxy Dec 12, 2025
191dc4e
remove
CUHKSZzxy Dec 12, 2025
f8c73bd
check parameters for /generate endpoint
lvhan028 Dec 12, 2025
9d90730
update generate test
littlegy Dec 15, 2025
7113aec
Merge branch 'InternLM:main' into generate_test
littlegy Dec 15, 2025
75e4fca
update toolkit
littlegy Dec 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions autotest/evaluate/test_api_evaluate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,9 +171,9 @@ def get_turbomind_model_list(tp_num):
new_model_list = []
for model in model_list:
if 'Qwen3-235B-A22B-Thinking-2507' in model['model']:
model['extra'] = '--session-len 65536 --cache-max-entry-count 0.9 --max-batch-size 1024 '
model['extra'] += '--session-len 65536 --cache-max-entry-count 0.9 --max-batch-size 1024 '
else:
model['extra'] = '--session-len 65536 --cache-max-entry-count 0.9 '
model['extra'] += '--session-len 65536 --cache-max-entry-count 0.9 '
model['cuda_prefix'] = None
new_model_list.append(model)
return new_model_list
Expand All @@ -184,9 +184,9 @@ def get_pytorch_model_list(tp_num):
new_model_list = []
for model in model_list:
if 'Qwen3-235B-A22B-Thinking-2507' in model['model']:
model['extra'] = '--session-len 65536 --cache-max-entry-count 0.9 --max-batch-size 1024 '
model['extra'] += '--session-len 65536 --cache-max-entry-count 0.9 --max-batch-size 1024 '
else:
model['extra'] = '--session-len 65536 --cache-max-entry-count 0.9 '
model['extra'] += '--session-len 65536 --cache-max-entry-count 0.9 '
model['cuda_prefix'] = None
new_model_list.append(model)
return new_model_list
Expand Down
Loading