We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 1161b12 commit 55b75d8Copy full SHA for 55b75d8
csrc/batch_mla_run.cu
@@ -68,7 +68,6 @@ void BatchMLAPagedAttentionRun(at::Tensor float_workspace_buffer, at::Tensor int
68
params.q_pe = static_cast<DTypeQ*>(q_pe.data_ptr());
69
params.ckv = static_cast<DTypeKV*>(ckv_cache.data_ptr());
70
params.kpe = static_cast<DTypeKV*>(kpe_cache.data_ptr());
71
- params.kv_indices = static_cast<IdType*>(kv_indices.data_ptr());
72
73
params.q_indptr = GetPtrFromBaseOffset<IdType>(int_buffer_ptr, plan_info.q_indptr_offset);
74
params.kv_indptr = GetPtrFromBaseOffset<IdType>(int_buffer_ptr, plan_info.kv_indptr_offset);
0 commit comments