Skip to content

[Sampler] Add missing sync in gpu verifier #2262

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

Merged
tqchen merged 1 commit into from
May 1, 2024
Merged

[Sampler] Add missing sync in gpu verifier #2262

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion cpp/serve/function_table.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,7 +135,7 @@ void FunctionTable::Init(String reload_lib_path, Device device, picojson::object
static_cast<int>(tvm::runtime::memory::AllocatorType::kPooled), static_cast<int>(kDLCPU), 0,
static_cast<int>(tvm::runtime::memory::AllocatorType::kPooled));
this->mod_get_func = [this](const std::string& name) -> PackedFunc {
return this->local_vm->GetFunction(name, false);
return this->local_vm->GetFunction(name, true);
};
this->get_global_func = [](const std::string& name) -> PackedFunc {
const auto* f = tvm::runtime::Registry::Get(name);
Expand Down
1 change: 1 addition & 0 deletions cpp/serve/sampler/gpu_sampler.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,6 +244,7 @@ class GPUSampler : public SamplerObj {
token_tree_first_child_device, token_tree_next_sibling_device,
uniform_samples_device, token_tree_parent_ptr_device);

DeviceAPI::Get(device_)->SyncStreamFromTo(device_, compute_stream_, copy_stream_);
CopyArray(token_tree_parent_ptr_device, token_tree_parent_ptr_host, copy_stream_);

std::vector<SampleResult> additional_sample_result;
Expand Down