xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 06:35:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

[HOT-FIX] Add kv_sharing_target_layer_name argument to cutlass_mla backend (#19374)

Browse Source 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
This commit is contained in:
Pavani Majety 2025-06-09 16:00:07 -07:00 committed by GitHub
parent 7d44c469fe
commit 8058c91108
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/v1/attention/backends/mla/cutlass_mla.py
View File

@ -40,12 +40,13 @@ class CutlassMLAImpl(MLACommonImpl[MLACommonMetadata]):
blocksparse_params: Optional[dict[str, Any]],
logits_soft_cap: Optional[float],
attn_type: str,
kv_sharing_target_layer_name: Optional[str],
# MLA Specific Arguments
**mla_args) -> None:
super().__init__(num_heads, head_size, scale, num_kv_heads,
alibi_slopes, sliding_window, kv_cache_dtype,
blocksparse_params, logits_soft_cap, attn_type,
**mla_args)
kv_sharing_target_layer_name, **mla_args)
unsupported_features = [
alibi_slopes, sliding_window, blocksparse_params, logits_soft_cap