Skip to content

[3/N][CI/UT] add spec decode e2e UT && [BUGFIX] fix init_logger bug #487

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.

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
merged 1 commit into from
Apr 18, 2025

Conversation

mengwei805
Copy link
Collaborator

@mengwei805 mengwei805 commented Apr 9, 2025

What this PR does / why we need it?

add spec decode e2e UT:

  1. add test_eagle_correctness.py;
  2. add test_mtp_correctness.py; use bf16 model weights;

fix init_logger bug:

  1. slove OOM probelm in camem.py;
  2. replace from vllm.logger import init_logger to from vllm.logger import logger overall situation

Does this PR introduce any user-facing change?

None

How was this patch tested?

Local verification passed

@mengwei805 mengwei805 force-pushed the v0.7.3-sd-ut-part3 branch 8 times, most recently from 7c03c68 to 21b49d7 Compare April 11, 2025 08:24
@MengqingCao MengqingCao self-assigned this Apr 11, 2025
@@ -148,7 +148,7 @@ jobs:
- name: Run vllm-project/vllm-ascend key feature test
if: steps.filter.outputs.speculative_tests_changed
run: |
pytest -sv tests/spec_decode
pytest -sv tests/spec_decode/e2e/test_eagle_correctness.py::test_llama2_eagle_e2e_greedy_correctness
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

todo: Revert this when successfully download llama model

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK, the modification here is just for debugging. I will restore it after debugging is successful.

@mengwei805 mengwei805 force-pushed the v0.7.3-sd-ut-part3 branch 3 times, most recently from b612b09 to 2a40cef Compare April 16, 2025 08:57
@mengwei805 mengwei805 force-pushed the v0.7.3-sd-ut-part3 branch 2 times, most recently from 5be0942 to fbbff4e Compare April 16, 2025 09:31
@mengwei805 mengwei805 changed the title [3/N][CI/UT] add spec decode e2e UT [3/N][CI/UT] add spec decode e2e UT && [BUGFIX] fix init_logger bug Apr 16, 2025
@mengwei805 mengwei805 force-pushed the v0.7.3-sd-ut-part3 branch 10 times, most recently from 3b5a721 to cc17c3c Compare April 17, 2025 08:25
@mengwei805 mengwei805 force-pushed the v0.7.3-sd-ut-part3 branch 6 times, most recently from 97a7955 to d791a9b Compare April 17, 2025 14:14
@wangxiyuan wangxiyuan merged commit d922fb9 into vllm-project:v0.7.3-dev Apr 18, 2025
14 checks passed
@MengqingCao MengqingCao mentioned this pull request Apr 22, 2025
43 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants