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

Jump to bottom

【Hackathon 6th Fundable Projects 2 No.19】cppcoreguidelines-no-malloc-final #63752

Merged
merged 17 commits into from
May 22, 2024
Merged

【Hackathon 6th Fundable Projects 2 No.19】cppcoreguidelines-no-malloc-final #63752

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
bffd5d2
no-malloc fix
walkalone20 Apr 22, 2024
bd174f1
minor changes
walkalone20 Apr 22, 2024
814df22
minor changes
walkalone20 Apr 22, 2024
f605d06
minor changes
walkalone20 Apr 22, 2024
5c13ccd
minor changes
walkalone20 Apr 23, 2024
3bdec0b
interface value update
walkalone20 Apr 23, 2024
05bb976
minor changes
walkalone20 Apr 23, 2024
2cc3f5c
linter
walkalone20 Apr 23, 2024
375c415
capi fix
walkalone20 Apr 23, 2024
9844a3b
restore
walkalone20 Apr 23, 2024
54bb40d
minor changes
walkalone20 May 1, 2024
2908bc4
format
walkalone20 May 1, 2024
9745f02
minor changes
walkalone20 May 1, 2024
7ad02ee
Update interface_value.h
walkalone20 May 1, 2024
ae6e00e
Update interface_value.h
walkalone20 May 1, 2024
acd4b53
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into…
walkalone20 May 21, 2024
e60385c
Merge branch 'PaddlePaddle:develop' into no-malloc
walkalone20 May 21, 2024
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
11 changes: 4 additions & 7 deletions paddle/fluid/inference/tensorrt/convert/cross_multihead_matmul_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -234,16 +234,13 @@ class CrossMultiheadMatMulOpConverter : public OpConverter {
auto creator = GetPluginRegistry()->getPluginCreator("fMHCA", "1");
assert(creator != nullptr);
std::vector<nvinfer1::PluginField> fields{};
nvinfer1::PluginFieldCollection* plugin_collection =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_collection) +
fields.size() *
sizeof(nvinfer1::PluginField))); // remember to free
walkalone20 marked this conversation as resolved.
Show resolved Hide resolved
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_collection(
new nvinfer1::PluginFieldCollection);

plugin_collection->nbFields = static_cast<int>(fields.size());
plugin_collection->fields = fields.data();
auto plugin = creator->createPlugin("fMHA_V2", plugin_collection);
free(plugin_collection);
auto plugin = creator->createPlugin("fMHA_V2", plugin_collection.get());
plugin_collection.reset();
std::vector<nvinfer1::ITensor*> plugin_inputs;
plugin_inputs.emplace_back(reshape_after_fc_q_layer->getOutput(0));
plugin_inputs.emplace_back(reshape_after_fc_layer->getOutput(0));
Expand Down
22 changes: 9 additions & 13 deletions paddle/fluid/inference/tensorrt/convert/emb_eltwise_layernorm.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,10 +119,8 @@ class EmbEltwiseLayerNormOpConverter : public OpConverter {
static_cast<int32_t>(emb_sizes[i]));
}

nvinfer1::PluginFieldCollection* plugin_ptr =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_ptr) +
fields.size() * sizeof(nvinfer1::PluginField)));
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_ptr(
new nvinfer1::PluginFieldCollection);
plugin_ptr->nbFields = static_cast<int>(fields.size());
plugin_ptr->fields = fields.data();

Expand All @@ -132,15 +130,15 @@ class EmbEltwiseLayerNormOpConverter : public OpConverter {
auto creator = GetPluginRegistry()->getPluginCreator(
"ManyEmbLayerNormVarlenPluginDynamic", "1");
auto plugin_obj = creator->createPlugin(
"ManyEmbLayerNormVarlenPluginDynamic", plugin_ptr);
"ManyEmbLayerNormVarlenPluginDynamic", plugin_ptr.get());

auto plugin_layer = engine_->network()->addPluginV2(
plugin_inputs.data(), plugin_inputs.size(), *plugin_obj);

plugin_layer->setName(("ManyEmbLayerNormVarlenPluginDynamicV1(Output: " +
op_desc.Output("Out")[0] + ")")
.c_str());
free(plugin_ptr);
plugin_ptr.reset();
if (enable_int8) {
float out_scale =
PADDLE_GET_CONST(float, op_desc.GetAttr("out_threshold"));
Expand Down Expand Up @@ -218,27 +216,25 @@ class EmbEltwiseLayerNormOpConverter : public OpConverter {
static_cast<int32_t>(emb_sizes[i]));
}

nvinfer1::PluginFieldCollection* plugin_ptr =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_ptr) +
fields.size() * sizeof(nvinfer1::PluginField)));
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_ptr(
new nvinfer1::PluginFieldCollection);
plugin_ptr->nbFields = static_cast<int>(fields.size());
plugin_ptr->fields = fields.data();

std::vector<nvinfer1::ITensor*> plugin_inputs = input_ids;

auto creator = GetPluginRegistry()->getPluginCreator(
"ManyEmbLayerNormPluginDynamic", "1");
auto plugin_obj =
creator->createPlugin("ManyEmbLayerNormPluginDynamic", plugin_ptr);
auto plugin_obj = creator->createPlugin("ManyEmbLayerNormPluginDynamic",
plugin_ptr.get());

auto plugin_layer = engine_->network()->addPluginV2(
plugin_inputs.data(), plugin_inputs.size(), *plugin_obj);

plugin_layer->setName(("ManyEmbLayerNormPluginDynamicV1(Output: " +
op_desc.Output("Out")[0] + ")")
.c_str());
free(plugin_ptr);
plugin_ptr.reset();
if (enable_int8) {
float out_scale =
PADDLE_GET_CONST(float, op_desc.GetAttr("out_threshold"));
Expand Down
12 changes: 4 additions & 8 deletions paddle/fluid/inference/tensorrt/convert/flash_multihead_matmul_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,16 +210,12 @@ class FlashMultiheadMatMulOpConverter : public OpConverter {
auto creator = GetPluginRegistry()->getPluginCreator("fMHA_V2", "1");
assert("fmha_v2 plugin creater must not be null" && creator != nullptr);
std::vector<nvinfer1::PluginField> fields{};
nvinfer1::PluginFieldCollection* plugin_collection =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_collection) +
fields.size() *
sizeof(nvinfer1::PluginField))); // remember to free

std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_collection(
new nvinfer1::PluginFieldCollection);
plugin_collection->nbFields = static_cast<int>(fields.size());
plugin_collection->fields = fields.data();
auto plugin = creator->createPlugin("fMHA_V2", plugin_collection);
free(plugin_collection);
auto plugin = creator->createPlugin("fMHA_V2", plugin_collection.get());
plugin_collection.reset();
std::vector<nvinfer1::ITensor*> plugin_inputs;
plugin_inputs.emplace_back(reshape_before_mha_layer->getOutput(0));
auto plugin_layer = engine_->network()->addPluginV2(
Expand Down
12 changes: 5 additions & 7 deletions paddle/fluid/inference/tensorrt/convert/multiclass_nms3_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,10 +102,8 @@ class MultiClassNMS3OpConverter : public OpConverter {
{"clipBoxes", &clip_boxes, nvinfer1::PluginFieldType::kINT32, 1},
};

nvinfer1::PluginFieldCollection* plugin_collections =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_collections) +
fields.size() * sizeof(nvinfer1::PluginField)));
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_collections(
new nvinfer1::PluginFieldCollection);
plugin_collections->nbFields = static_cast<int>(fields.size());
plugin_collections->fields = fields.data();
std::string nms_plugin_name = "BatchedNMS_TRT";
Expand All @@ -114,9 +112,9 @@ class MultiClassNMS3OpConverter : public OpConverter {
}
auto creator =
GetPluginRegistry()->getPluginCreator(nms_plugin_name.c_str(), "1");
auto batch_nms_plugin =
creator->createPlugin(nms_plugin_name.c_str(), plugin_collections);
free(plugin_collections);
auto batch_nms_plugin = creator->createPlugin(nms_plugin_name.c_str(),
plugin_collections.get());
plugin_collections.reset();

auto batch_nms_layer = engine_->network()->addPluginV2(
batch_nms_inputs.data(), batch_nms_inputs.size(), *batch_nms_plugin);
Expand Down
12 changes: 5 additions & 7 deletions paddle/fluid/inference/tensorrt/convert/multiclass_nms_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,10 +100,8 @@ class MultiClassNMSOpConverter : public OpConverter {
{"clipBoxes", &clip_boxes, nvinfer1::PluginFieldType::kINT32, 1},
};

nvinfer1::PluginFieldCollection* plugin_collections =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_collections) +
fields.size() * sizeof(nvinfer1::PluginField)));
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_collections(
new nvinfer1::PluginFieldCollection);
plugin_collections->nbFields = static_cast<int>(fields.size());
plugin_collections->fields = fields.data();

Expand All @@ -113,9 +111,9 @@ class MultiClassNMSOpConverter : public OpConverter {
}
auto creator =
GetPluginRegistry()->getPluginCreator(nms_plugin_name.c_str(), "1");
auto batch_nms_plugin =
creator->createPlugin(nms_plugin_name.c_str(), plugin_collections);
free(plugin_collections);
auto batch_nms_plugin = creator->createPlugin(nms_plugin_name.c_str(),
plugin_collections.get());
plugin_collections.reset();

auto batch_nms_layer = engine_->network()->addPluginV2(
batch_nms_inputs.data(), batch_nms_inputs.size(), *batch_nms_plugin);
Expand Down
33 changes: 12 additions & 21 deletions paddle/fluid/inference/tensorrt/convert/multihead_matmul_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -234,17 +234,14 @@ class MultiheadMatMulOpConverter : public OpConverter {
nvinfer1::PluginFieldType::kFLOAT32,
1});
}
nvinfer1::PluginFieldCollection* plugin_collection =
static_cast<nvinfer1::PluginFieldCollection*>(malloc(
sizeof(*plugin_collection) +
fields.size() *
sizeof(nvinfer1::PluginField))); // remember to free
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_collection(
new nvinfer1::PluginFieldCollection);
plugin_collection->nbFields = static_cast<int>(fields.size());
plugin_collection->fields = fields.data();

auto plugin = creator->createPlugin("CustomQKVToContextPluginDynamic",
plugin_collection);
free(plugin_collection);
plugin_collection.get());
plugin_collection.reset();

std::vector<nvinfer1::ITensor*> plugin_inputs;
plugin_inputs.emplace_back(fc_layer->getOutput(0));
Expand Down Expand Up @@ -429,17 +426,14 @@ class MultiheadMatMulOpConverter : public OpConverter {
nvinfer1::PluginFieldType::kFLOAT32,
1});
}
nvinfer1::PluginFieldCollection* plugin_collection =
static_cast<nvinfer1::PluginFieldCollection*>(malloc(
sizeof(*plugin_collection) +
fields.size() *
sizeof(nvinfer1::PluginField))); // remember to free
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_collection(
new nvinfer1::PluginFieldCollection);
plugin_collection->nbFields = static_cast<int>(fields.size());
plugin_collection->fields = fields.data();

auto plugin = creator->createPlugin("CustomQKVToContextPluginDynamic",
plugin_collection);
free(plugin_collection);
plugin_collection.get());
plugin_collection.reset();

std::vector<nvinfer1::ITensor*> plugin_inputs;
plugin_inputs.emplace_back(
Expand Down Expand Up @@ -661,16 +655,13 @@ class MultiheadMatMulOpConverter : public OpConverter {
&var_seqlen,
nvinfer1::PluginFieldType::kINT32,
1}};
nvinfer1::PluginFieldCollection* plugin_collection =
static_cast<nvinfer1::PluginFieldCollection*>(malloc(
sizeof(*plugin_collection) +
fields.size() *
sizeof(nvinfer1::PluginField))); // remember to free
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_collection(
new nvinfer1::PluginFieldCollection);
plugin_collection->nbFields = static_cast<int>(fields.size());
plugin_collection->fields = fields.data();
auto plugin = creator->createPlugin("CustomQKVToContextPluginDynamic",
plugin_collection);
free(plugin_collection);
plugin_collection.get());
plugin_collection.reset();
// set inputs
std::vector<nvinfer1::ITensor*> plugin_inputs;
// input_0 for plugin
Expand Down
10 changes: 4 additions & 6 deletions paddle/fluid/inference/tensorrt/convert/preln_emb_eltwise_layernorm.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,10 +173,8 @@ class PrelnEmbEltwiseLayerNormOpConverter : public OpConverter {
static_cast<int32_t>(emb_sizes[i]));
}

nvinfer1::PluginFieldCollection* plugin_ptr =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_ptr) +
fields.size() * sizeof(nvinfer1::PluginField)));
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_ptr(
new nvinfer1::PluginFieldCollection);
plugin_ptr->nbFields = static_cast<int>(fields.size());
plugin_ptr->fields = fields.data();

Expand All @@ -188,15 +186,15 @@ class PrelnEmbEltwiseLayerNormOpConverter : public OpConverter {
"ManyEmbLayerNormVarlenPluginDynamic", "2");

auto plugin_obj = creator->createPlugin(
"ManyEmbLayerNormVarlenPluginDynamic", plugin_ptr);
"ManyEmbLayerNormVarlenPluginDynamic", plugin_ptr.get());

auto plugin_layer = engine_->network()->addPluginV2(
plugin_inputs.data(), plugin_inputs.size(), *plugin_obj);

plugin_layer->setName(("ManyEmbLayerNormPluginDynamic_V3(Output: " +
op_desc.Output("Out")[0] + ")")
.c_str());
free(plugin_ptr);
plugin_ptr.reset();
float out_0_scale =
PADDLE_GET_CONST(float, op_desc.GetAttr("out_0_threshold"));
float out_1_scale =
Expand Down
10 changes: 4 additions & 6 deletions paddle/fluid/inference/tensorrt/convert/prompt_tuning_emb_eltwise_layernorm.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,10 +118,8 @@ class PromptTuningEmbEltwiseLayerNormOpConverter : public OpConverter {
static_cast<int32_t>(emb_sizes[i]));
}

nvinfer1::PluginFieldCollection* plugin_ptr =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_ptr) +
fields.size() * sizeof(nvinfer1::PluginField)));
std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_ptr(
new nvinfer1::PluginFieldCollection);
plugin_ptr->nbFields = static_cast<int>(fields.size());
plugin_ptr->fields = fields.data();

Expand All @@ -134,7 +132,7 @@ class PromptTuningEmbEltwiseLayerNormOpConverter : public OpConverter {
auto creator = GetPluginRegistry()->getPluginCreator(
"PromptTuningEmbLayerNormVarlenPluginDynamic", "1");
auto plugin_obj = creator->createPlugin(
"PromptTuningEmbLayerNormVarlenPluginDynamic", plugin_ptr);
"PromptTuningEmbLayerNormVarlenPluginDynamic", plugin_ptr.get());

auto plugin_layer = engine_->network()->addPluginV2(
plugin_inputs.data(), plugin_inputs.size(), *plugin_obj);
Expand All @@ -143,7 +141,7 @@ class PromptTuningEmbEltwiseLayerNormOpConverter : public OpConverter {
("PromptTuningEmbLayerNormVarlenPluginDynamicV1(Output: " +
op_desc.Output("Out")[0] + ")")
.c_str());
free(plugin_ptr);
plugin_ptr.reset();
if (enable_int8) {
float out_scale =
PADDLE_GET_CONST(float, op_desc.GetAttr("out_threshold"));
Expand Down
12 changes: 4 additions & 8 deletions paddle/fluid/inference/tensorrt/convert/qk_multihead_matmul_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,16 +258,12 @@ class QkMultiheadMatMulOpConverter : public OpConverter {
auto creator = GetPluginRegistry()->getPluginCreator("fMHA_V2", "1");
assert(creator != nullptr);
std::vector<nvinfer1::PluginField> fields{};
nvinfer1::PluginFieldCollection* plugin_collection =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(*plugin_collection) +
fields.size() *
sizeof(nvinfer1::PluginField))); // remember to free

std::unique_ptr<nvinfer1::PluginFieldCollection> plugin_collection(
new nvinfer1::PluginFieldCollection);
plugin_collection->nbFields = static_cast<int>(fields.size());
plugin_collection->fields = fields.data();
auto plugin = creator->createPlugin("fMHA_V2", plugin_collection);
free(plugin_collection);
auto plugin = creator->createPlugin("fMHA_V2", plugin_collection.get());
plugin_collection.reset();
std::vector<nvinfer1::ITensor*> plugin_inputs;
plugin_inputs.emplace_back(mha_input_tensor);
auto plugin_layer = engine_->network()->addPluginV2(
Expand Down
34 changes: 13 additions & 21 deletions paddle/fluid/inference/tensorrt/convert/skip_layernorm.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,17 +149,15 @@ class SkipLayerNormOpConverter : public OpConverter {
scale_weight.values,
GetPluginFieldType(scale_weight.type),
static_cast<int32_t>(scale_weight.count)}};
nvinfer1::PluginFieldCollection* pluginPtr =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(nvinfer1::PluginFieldCollection) +
fields.size() * sizeof(nvinfer1::PluginField)));
std::unique_ptr<nvinfer1::PluginFieldCollection> pluginPtr(
new nvinfer1::PluginFieldCollection);
pluginPtr->nbFields = static_cast<int32_t>(fields.size());
pluginPtr->fields = fields.data();

auto pluginObj =
creator->createPlugin("CustomSkipLayerNormPluginDynamic", pluginPtr);
auto pluginObj = creator->createPlugin("CustomSkipLayerNormPluginDynamic",
pluginPtr.get());

free(pluginPtr);
pluginPtr.reset();

auto plugin_layer = engine_->network()->addPluginV2(
inputs.data(), inputs.size(), *pluginObj);
Expand Down Expand Up @@ -213,18 +211,15 @@ class SkipLayerNormOpConverter : public OpConverter {
smooth_scale.data(),
nvinfer1::PluginFieldType::kFLOAT32,
static_cast<int32_t>(smooth_scale.size())});
nvinfer1::PluginFieldCollection* pluginPtr =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(nvinfer1::PluginFieldCollection) +
fields.size() *
sizeof(nvinfer1::PluginField))); // remember to free
std::unique_ptr<nvinfer1::PluginFieldCollection> pluginPtr(
new nvinfer1::PluginFieldCollection);
pluginPtr->nbFields = static_cast<int32_t>(fields.size());
pluginPtr->fields = fields.data();

auto pluginObj = creator->createPlugin(
"CustomSkipLayerNormPluginDynamicWithSmooth", pluginPtr);
"CustomSkipLayerNormPluginDynamicWithSmooth", pluginPtr.get());

free(pluginPtr);
pluginPtr.reset();

auto plugin_layer = engine_->network()->addPluginV2(
inputs.data(), inputs.size(), *pluginObj);
Expand All @@ -237,18 +232,15 @@ class SkipLayerNormOpConverter : public OpConverter {
"layer"));
layer = plugin_layer;
} else {
nvinfer1::PluginFieldCollection* pluginPtr =
static_cast<nvinfer1::PluginFieldCollection*>(
malloc(sizeof(nvinfer1::PluginFieldCollection) +
fields.size() *
sizeof(nvinfer1::PluginField))); // remember to free
std::unique_ptr<nvinfer1::PluginFieldCollection> pluginPtr(
new nvinfer1::PluginFieldCollection);
pluginPtr->nbFields = static_cast<int32_t>(fields.size());
pluginPtr->fields = fields.data();

auto pluginObj = creator->createPlugin(
"CustomSkipLayerNormPluginDynamic", pluginPtr);
"CustomSkipLayerNormPluginDynamic", pluginPtr.get());

free(pluginPtr);
pluginPtr.reset();

auto plugin_layer = engine_->network()->addPluginV2(
inputs.data(), inputs.size(), *pluginObj);
Expand Down
Loading