@@ -120,6 +120,8 @@ std::string registry_key(const std::string& target) {
120120 target.starts_with (kPrefix ) ? target.substr (kPrefix .size ()) : target;
121121 if (key == " aten.relu_.default" ) {
122122 key = " aten.relu.default" ;
123+ } else if (key == " llama.update_cache.default" ) {
124+ key = " update_cache.default" ;
123125 }
124126 return key;
125127}
@@ -133,11 +135,16 @@ bool is_functional_in_place(const std::string& target) {
133135// Ops whose ET-VK implementations require width-packed operands. This list
134136// seeds layout assignment; propagation below determines the final layouts.
135137bool is_width_packed_op (std::string_view key) {
136- constexpr std::array<std::string_view, 4 > kOps {
138+ constexpr std::array<std::string_view, 9 > kOps {
137139 " aten.linear.default" ,
138140 " aten.addmm.default" ,
139141 " aten.mm.default" ,
140- " aten.bmm.default" };
142+ " aten.bmm.default" ,
143+ " et_vk.linear_dq8ca_q4gsw.default" ,
144+ " et_vk.rms_norm.default" ,
145+ " llama.custom_sdpa.default" ,
146+ " update_cache.default" ,
147+ " torchao.choose_qparams_affine.default" };
141148 return std::ranges::find (kOps , key) != kOps .end ();
142149}
143150
@@ -898,19 +905,17 @@ class VulkanEngineExecutable final : public EngineExecutable {
898905 throw std::runtime_error (" vulkan: unhandled argument kind" );
899906 }
900907
901- // Insert a same-shape view_copy that repacks a channels -packed activation
902- // into a fresh width-packed tensor, and return the width-packed ref .
903- VkRef repack_to_width (VkRef src, const Value& v) {
908+ // Insert a same-shape clone into a fresh width -packed tensor when an
909+ // activation's current layout or storage cannot satisfy its consumer .
910+ VkRef repack_to_width (VkRef src, const Value& v, utils::StorageType storage ) {
904911 const std::vector<int64_t >& sizes = v.tensor_meta ().sizes ;
905912 const VkRef dst = graph_->add_tensor (
906913 sizes,
907914 to_vk_dtype (device_dtype (v.tensor_meta ().dtype )),
908- utils:: kTexture3D ,
915+ storage ,
909916 utils::kWidthPacked );
910- const VkRef size_list =
911- graph_->add_scalar_list (std::vector<int64_t >(sizes));
912- std::vector<VkRef> args = {src, size_list, dst};
913- VK_GET_OP_FN (" aten.view_copy.default" )(*graph_, args);
917+ std::vector<VkRef> args = {src, none_ref_, dst};
918+ VK_GET_OP_FN (" aten.clone.default" )(*graph_, args);
914919 return dst;
915920 }
916921
@@ -1022,6 +1027,17 @@ class VulkanEngineExecutable final : public EngineExecutable {
10221027 " vulkan: unsupported op '" + key + " ' (target " + n.target + " )" );
10231028 }
10241029 const bool width = is_width_packed_op (key);
1030+ std::optional<utils::StorageType> activation_storage;
1031+ if (key == " et_vk.linear_dq8ca_q4gsw.default" ) {
1032+ const auto output =
1033+ std::ranges::find_if (n.outputs , [this ](const Output& candidate) {
1034+ return valid (candidate.value_id ) &&
1035+ g ().value (candidate.value_id ).is_tensor ();
1036+ });
1037+ if (output != n.outputs .end ()) {
1038+ activation_storage = storage_at (output->value_id );
1039+ }
1040+ }
10251041
10261042 std::vector<VkRef> args;
10271043 args.reserve (n.inputs .size () + 1 );
@@ -1038,8 +1054,13 @@ class VulkanEngineExecutable final : public EngineExecutable {
10381054 const Value& v = g ().value (value_id);
10391055 const bool activation = v.role == ValueRole::Intermediate ||
10401056 v.role == ValueRole::UserInput;
1041- if (activation && layout_at (value_id) != utils::kWidthPacked ) {
1042- a = repack_to_width (a, v);
1057+ const bool storage_mismatch = activation_storage.has_value () &&
1058+ na.name == " input" && storage_at (value_id) != *activation_storage;
1059+ if (activation &&
1060+ (layout_at (value_id) != utils::kWidthPacked ||
1061+ storage_mismatch)) {
1062+ a = repack_to_width (
1063+ a, v, activation_storage.value_or (storage_at (value_id)));
10431064 }
10441065 }
10451066 }
0 commit comments