From 8058c91108a3611c48ef0b54448ce6b48c017f5d Mon Sep 17 00:00:00 2001 From: Pavani Majety Date: Mon, 9 Jun 2025 16:00:07 -0700 Subject: [PATCH] [HOT-FIX] Add `kv_sharing_target_layer_name` argument to cutlass_mla backend (#19374) Signed-off-by: Pavani Majety --- vllm/v1/attention/backends/mla/cutlass_mla.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/vllm/v1/attention/backends/mla/cutlass_mla.py b/vllm/v1/attention/backends/mla/cutlass_mla.py index 70aee058e296..c8ec571989c6 100644 --- a/vllm/v1/attention/backends/mla/cutlass_mla.py +++ b/vllm/v1/attention/backends/mla/cutlass_mla.py @@ -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