Skip to content

【main】【bugfix】fix: restrict default MLAPO activation to Decode nodes only #6451

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
wangxiyuan merged 4 commits into from
Jan 31, 2026
+8 −4
Merged

【main】【bugfix】fix: restrict default MLAPO activation to Decode nodes only #6451

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
29f45e1
fix deepseek run failed in PD mixed
fems14 Jan 31, 2026
a1ddbd9
fix deepseek run failed in PD mixed
fems14 Jan 31, 2026
ea73842
fix deepseek run failed in PD mixed
fems14 Jan 31, 2026
4c1e1ff
Merge branch 'vllm-project:main' into main
fems14 Jan 31, 2026
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
4 changes: 2 additions & 2 deletions vllm_ascend/attention/mla_v1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
AscendCommonAttentionMetadata,
ascend_chunked_prefill_workspace_size,
enable_cp,
enabling_malpo,
enabling_mlapo,
maybe_save_kv_layer_to_connector,
split_decodes_and_prefills,
trans_rope_weight,
Expand Down Expand Up @@ -710,7 +710,7 @@ def __init__(
self.ring_mla_mask_size = 512

self.speculative_config = self.vllm_config.speculative_config
self.enable_mlapo = enabling_malpo(self.vllm_config)
self.enable_mlapo = enabling_mlapo(self.vllm_config)

self.is_kv_producer = (
self.vllm_config.kv_transfer_config is not None and self.vllm_config.kv_transfer_config.is_kv_producer
Expand Down
8 changes: 6 additions & 2 deletions vllm_ascend/attention/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -305,6 +305,10 @@ def transdata(nd_mat, block_size: tuple = (16, 16)):
return nz_mat


def enabling_malpo(vllm_config: VllmConfig) -> bool:
is_decode_instance = vllm_config.kv_transfer_config is not None and vllm_config.kv_transfer_config.is_kv_consumer
def enabling_mlapo(vllm_config: VllmConfig) -> bool:
is_decode_instance = (
vllm_config.kv_transfer_config is not None
and vllm_config.kv_transfer_config.is_kv_consumer
and not vllm_config.kv_transfer_config.is_kv_producer
)
return bool(envs.VLLM_ASCEND_ENABLE_MLAPO and is_decode_instance)
Loading