Skip to content

fix: prevent apps from crashing when LLMs are loaded #1063

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

Open
chmjkb wants to merge 4 commits into
base: main
Choose a base branch
from
+7 −3
Open

fix: prevent apps from crashing when LLMs are loaded #1063

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4de1a86
wip
chmjkb Apr 7, 2026
1aac7aa
fix: update memoryLowerBound for llm
chmjkb Apr 8, 2026
aeac249
chore: remove unused header
chmjkb Apr 8, 2026
e76e2cc
Update packages/react-native-executorch/common/rnexecutorch/models/ll…
chmjkb Apr 8, 2026
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
10 changes: 7 additions & 3 deletions packages/react-native-executorch/common/rnexecutorch/models/llm/LLM.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ using executorch::runtime::Error;
LLM::LLM(const std::string &modelSource, const std::string &tokenizerSource,
std::vector<std::string> capabilities,
std::shared_ptr<react::CallInvoker> callInvoker)
: BaseModel(modelSource, callInvoker, Module::LoadMode::File) {
: BaseModel(modelSource, callInvoker, Module::LoadMode::Mmap) {

if (capabilities.empty()) {
runner_ =
Expand All @@ -42,8 +42,12 @@ LLM::LLM(const std::string &modelSource, const std::string &tokenizerSource,
throw RnExecutorchError(loadResult, "Failed to load LLM runner");
}

memorySizeLowerBound = fs::file_size(fs::path(modelSource)) +
fs::file_size(fs::path(tokenizerSource));
// I am purposefully not adding file size of the model here. The reason is
// that Hermes would crash the app if we try to alloc too much memory here.
// Also, given we're using mmap, the true memory consumption of a model is not
// really equal to the size of the model. The size of the tokenizer file is a
// hint to the GC that this object might be worth getting rid of.
memorySizeLowerBound = fs::file_size(fs::path(tokenizerSource));
}

std::string LLM::generate(std::string input,
Expand Down
Loading