Skip to content

[Nightly][BugFix][v0.13.0] Remove kv_cache nz test case for test_mla_preprocess_nq.py #6506

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

Closed
whx-sjtu wants to merge 1 commit into from
Closed

[Nightly][BugFix][v0.13.0] Remove kv_cache nz test case for test_mla_preprocess_nq.py #6506

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 2 additions & 4 deletions tests/e2e/nightly/single_node/ops/singlecard_ops/test_mla_preprocess_nq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
import gc

import pytest
import torch
import torch_npu

Expand All @@ -9,9 +8,8 @@
enable_custom_op()


@pytest.mark.parametrize("cache_mode", ["krope_ctkv", "nzcache"])
@torch.inference_mode()
def test_mla_preprocess_kernel(cache_mode: str):
def test_mla_preprocess_kernel():
token_num = 1
head_num = 2
N_7168 = 7168
Expand Down Expand Up @@ -84,7 +82,7 @@ def test_mla_preprocess_kernel(cache_mode: str):
None,
None,
None,
cache_mode=cache_mode,
cache_mode="krope_ctkv",
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Feb 3, 2026

Choose a reason for hiding this comment

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

high

This should use the cache_mode parameter from the test function to work with the pytest.mark.parametrize decorator suggested above.

Suggested change
cache_mode="krope_ctkv",
cache_mode=cache_mode,

quant_mode="no_quant",
enable_inner_out=False,
q_out0=q_nope_out,
Expand Down