Skip to content
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

[GPU] Update PagedAttention creation logic #28802

Merged
merged 1 commit into from
Feb 4, 2025
Merged

[GPU] Update PagedAttention creation logic #28802

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
12 changes: 9 additions & 3 deletions src/plugins/intel_gpu/src/plugin/ops/paged_attention.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,10 +25,16 @@ static void CreatePagedAttentionExtensionOp(ProgramBuilder& p, const std::shared
auto inputs = p.GetInputInfo(op);
auto prim = cldnn::paged_attention(layer_type_name_ID(op), inputs);

auto key_cache_ps = op->get_input_partial_shape(3);
const auto& rt_info = op->get_rt_info();
const auto k_head_size_id = "k_head_size";
const auto num_k_heads_id = "num_k_heads";
const auto has_rt_params = rt_info.find(k_head_size_id) != rt_info.end() &&
rt_info.find(num_k_heads_id) != rt_info.end();

auto query_ps = op->get_input_partial_shape(0);
auto head_size = key_cache_ps[2].get_length();
auto kv_heads_num = key_cache_ps[1].get_length();
auto key_cache_ps = op->get_input_partial_shape(3);
auto head_size = has_rt_params ? rt_info.at(k_head_size_id).as<int64_t>() : key_cache_ps[2].get_length();
auto kv_heads_num = has_rt_params ? rt_info.at(num_k_heads_id).as<int64_t>() : key_cache_ps[1].get_length();

// WA: in some cases, the query input may have a bounded dimension
// Use input shape of the input node in such cases
Expand Down
Loading