Skip to content

Use UNIFORM QueryLen MLA for MTP #773

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

Open
wants to merge 1 commit into
base: ganyi/rocm_fp8_mla_and_persistent_kernel
Choose a base branch
from
Open

Use UNIFORM QueryLen MLA for MTP #773

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
2 changes: 1 addition & 1 deletion vllm/v1/attention/backends/mla/rocm_aiter_mla.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ class AiterMLAMetadataBuilder(MLACommonMetadataBuilder[AiterMLAMetadata]):
# TODO(luka, lucas): audit this as part of:
# https://github.com/vllm-project/vllm/issues/22945
cudagraph_support: ClassVar[AttentionCGSupport] = AttentionCGSupport.UNIFORM_BATCH
query_len_support: ClassVar[QueryLenSupport] = QueryLenSupport.VARLEN
query_len_support: ClassVar[QueryLenSupport] = QueryLenSupport.UNIFORM

def __init__(
self,
Expand Down