Skip to content

Commit e7efc7e

Browse files
authored
[BugFix] Remove not using patch_eagle.py for CI. (#1385)
### What this PR does / why we need it? This PR aims to address a long-standing **CI bug** and remove unused code. The specific changes include: 1. **Fixing CI Bug**: Resolves the root cause of CI test failures or instability. This often stems from incorrect environment configurations, dependency version conflicts, or flawed test script logic. This fix ensures the reliability and consistency of the CI pipeline. 2. **Removing `patch_eagle.py`**: Deletes the `patch_eagle.py` file, which is no longer utilized by the project. This file was likely legacy code, experimental code, or its functionality has since been replaced by other modules. Its removal helps reduce codebase complexity, improves maintainability, and prevents potential confusion. ### Does this PR introduce _any_ user-facing change? No, this PR primarily focuses on internal CI stability maintenance and code cleanup. It does not introduce any user-visible changes to APIs, interfaces, or other behaviors. ### How was this patch tested? CI passed. Specifically: 1. **Existing CI Pipelines Passed**: After fixing the CI bug, all existing CI tests and pipelines were verified to run correctly and pass successfully. 2. **Code Cleanup Verified**: Following the removal of `patch_eagle.py`, it was ensured that any related functional modules (if applicable) continue to work as expected, without introducing new regressions. This was typically verified by running the project's main test suite. Signed-off-by: yuancaoyaoHW <a2749322671@gmail.com>
1 parent 941269a commit e7efc7e

File tree

3 files changed

+1
-86
lines changed

3 files changed

+1
-86
lines changed

vllm_ascend/patch/__init__.py

Lines changed: 1 addition & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -105,20 +105,6 @@
105105
# Future Plan:
106106
# Revert it when the related pr is merged in vllm and vllm-ascend.
107107
#
108-
# ** File: worker/patch_common/patch_eagle.py **
109-
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
110-
# 1. `vllm.v1.spec_decode.eagle.prepare_inputs`
111-
# Why:
112-
# We need to use the patched `prepare_input_kernel` in `eagle.prepare_inputs`.
113-
# The mainly reason to overwrite `prepare_input_kernel` is this is a triton
114-
# kernel, ascend is now not support triton kernel.
115-
# How:
116-
# Re-implementation the `prepare_input_kernel` triton kernel by pytorch
117-
# Related PR (if no, explain why):
118-
# - Ascend doesn't support triton
119-
# Future Plan:
120-
# Revert it when the ascend support triton kernel.
121-
#
122108
# ** File: worker/patch_common/patch_sampler.py **
123109
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
124110
# 1. `vllm.v1.sample.sampler.Sampler.apply_top_k_top_p`
@@ -168,4 +154,4 @@
168154
# Related PR (if no, explain why):
169155
# This is the problem in vllm-ascend
170156
# Future Plan:
171-
# Remove this patch once pytorch 2.7.0 is supported for vllm ascend.
157+
# Remove this patch once pytorch 2.7.0 is supported for vllm ascend.

vllm_ascend/patch/worker/patch_common/__init__.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,6 @@
1919
# patch files.
2020
import vllm_ascend.patch.worker.patch_common.patch_utils # noqa isort:skip
2121
import vllm_ascend.patch.worker.patch_common.patch_distributed # noqa
22-
import vllm_ascend.patch.worker.patch_common.patch_eagle # noqa
2322
import vllm_ascend.patch.worker.patch_common.patch_minicpm # noqa
2423
import vllm_ascend.patch.worker.patch_common.patch_multi_step_worker # noqa
2524
import vllm_ascend.patch.worker.patch_common.patch_sampler # noqa

vllm_ascend/patch/worker/patch_common/patch_eagle.py

Lines changed: 0 additions & 70 deletions
This file was deleted.

0 commit comments

Comments
 (0)