Re-patch TritonPlaceholder on main to make CI happy #753
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Yikun
force-pushed
the
triton-main
branch
2 times, most recently
from
ae88126 to
d427bcd
Compare
Signed-off-by: Yikun Jiang <[email protected]>
Yikun
commented
May 5, 2025
| from vllm_ascend.patch.worker import patch_0_8_5 # noqa: F401 | ||
| from vllm_ascend.patch.worker import patch_common # noqa: F401 | ||
| else: | ||
| from vllm_ascend.patch.worker import patch_main # noqa: F401 # isort:skip |
There was a problem hiding this comment.
Try move patch_main before patch_common to resolve:
https://github.com/vllm-project/vllm-ascend/actions/runs/14837426407/job/41651814910
ERROR 05-05 13:28:54 [registry.py:356] Traceback (most recent call last):
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm-empty/vllm/model_executor/models/registry.py", line 354, in _try_inspect_model_cls
ERROR 05-05 13:28:54 [registry.py:356] return model.inspect_model_cls()
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm-empty/vllm/model_executor/models/registry.py", line 325, in inspect_model_cls
ERROR 05-05 13:28:54 [registry.py:356] return _run_in_subprocess(
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm-empty/vllm/model_executor/models/registry.py", line 590, in _run_in_subprocess
ERROR 05-05 13:28:54 [registry.py:356] raise RuntimeError(f"Error raised in subprocess:\n"
ERROR 05-05 13:28:54 [registry.py:356] RuntimeError: Error raised in subprocess:
ERROR 05-05 13:28:54 [registry.py:356] /usr/local/python3.10/lib/python3.10/runpy.py:126: RuntimeWarning: 'vllm.model_executor.models.registry' found in sys.modules after import of package 'vllm.model_executor.models', but prior to execution of 'vllm.model_executor.models.registry'; this may result in unpredictable behaviour
ERROR 05-05 13:28:54 [registry.py:356] warn(RuntimeWarning(msg))
ERROR 05-05 13:28:54 [registry.py:356] Traceback (most recent call last):
ERROR 05-05 13:28:54 [registry.py:356] File "/usr/local/python3.10/lib/python3.10/runpy.py", line 196, in _run_module_as_main
ERROR 05-05 13:28:54 [registry.py:356] return _run_code(code, main_globals, None,
ERROR 05-05 13:28:54 [registry.py:356] File "/usr/local/python3.10/lib/python3.10/runpy.py", line 86, in _run_code
ERROR 05-05 13:28:54 [registry.py:356] exec(code, run_globals)
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm-empty/vllm/model_executor/models/registry.py", line 611, in <module>
ERROR 05-05 13:28:54 [registry.py:356] _run()
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm-empty/vllm/model_executor/models/registry.py", line 600, in _run
ERROR 05-05 13:28:54 [registry.py:356] load_general_plugins()
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm-empty/vllm/plugins/__init__.py", line 82, in load_general_plugins
ERROR 05-05 13:28:54 [registry.py:356] func()
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm_ascend/__init__.py", line 29, in register_model
ERROR 05-05 13:28:54 [registry.py:356] import vllm_ascend.patch.worker.patch_main.patch_tritonplaceholder # noqa
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm_ascend/patch/worker/__init__.py", line 25, in <module>
ERROR 05-05 13:28:54 [registry.py:356] from vllm_ascend.patch.worker import patch_common # noqa: F401
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm_ascend/patch/worker/patch_common/__init__.py", line 19, in <module>
ERROR 05-05 13:28:54 [registry.py:356] import vllm_ascend.patch.worker.patch_common.patch_minicpm # noqa
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm_ascend/patch/worker/patch_common/patch_minicpm.py", line 19, in <module>
ERROR 05-05 13:28:54 [registry.py:356] from vllm.model_executor.models.minicpm import MiniCPMAttention
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm-empty/vllm/model_executor/models/minicpm.py", line 39, in <module>
ERROR 05-05 13:28:54 [registry.py:356] from vllm.model_executor.layers.fused_moe import fused_moe
ERROR 05-05 13:28:54 [registry.py:356] File "/__w/vllm-ascend/vllm-ascend/vllm-empty/vllm/model_executor/layers/fused_moe/fused_moe.py", line 9, in <module>
ERROR 05-05 13:28:54 [registry.py:356] import triton
ERROR 05-05 13:28:54 [registry.py:356] ModuleNotFoundError: No module named 'triton'
ERROR 05-05 13:28:54 [registry.py:356]
wangxiyuan
approved these changes
May 5, 2025
|
LSTM, Thanks for this fix! |
|
@MengqingCao @wangxiyuan Thanks, merged to main |
Yikun
added a commit
to Yikun/vllm-ascend
that referenced
this pull request
May 6, 2025
…ject#753)" This reverts commit d7e1110. Signed-off-by: Yikun Jiang <[email protected]>
Yikun
added a commit
that referenced
this pull request
May 6, 2025
### What this PR does / why we need it? - Revert "Re-patch TritonPlaceholder on main to make CI happy (#753)" because upstream main CI already merged: vllm-project/vllm#17446 - Keep 0.8.5.post1 compatible ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? CI passed --------- Signed-off-by: Yikun Jiang <[email protected]>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
### What this PR does / why we need it? Re-patch TritonPlaceholder on main to make CI happy - Add triton patch back until vllm-project/vllm#17446 resolved - Move patch_main before patch_common to resolve minicpm triton import issue - Add `0.8.5` and `0.8.5.post1` to make patch work on 0.8.5 all versions Related: - vllm-project#704 - vllm-project#690 ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? All CI passed include main Signed-off-by: Yikun Jiang <[email protected]>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
…t#764) ### What this PR does / why we need it? - Revert "Re-patch TritonPlaceholder on main to make CI happy (vllm-project#753)" because upstream main CI already merged: vllm-project/vllm#17446 - Keep 0.8.5.post1 compatible ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? CI passed --------- Signed-off-by: Yikun Jiang <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it?
Re-patch TritonPlaceholder on main to make CI happy
0.8.5and0.8.5.post1to make patch work on 0.8.5 all versionsRelated:
Does this PR introduce any user-facing change?
No
How was this patch tested?
All CI passed include main