Segmentation fault when run GEMMA-2B model

[mvhsin]

Have I written custom code (as opposed to using a stock example script provided in MediaPipe)

None

OS Platform and Distribution

Android 12

Mobile device if the issue happens on mobile device

Orange Pi 5

Browser and version if the issue happens on browser

No response

Programming Language and version

C++

MediaPipe version

No response

Bazel version

6.5

Solution

llm_inference_engine_cpu_main

Android Studio, NDK, SDK versions (if issue is related to building in Android environment)

No response

Xcode & Tulsi version (if issue is related to building for iOS)

No response

Describe the actual behavior

build llm_inference_engine_cpu_main and run by ./llm_inference_engine_cpu_main --model_path <path_to_gemma-2b-it-cpu-int4.bin>, then I got seg fault

Describe the expected behaviour

Able to run llm_inference_engine_cpu_main and load GEMMA bin file without error

Standalone code/steps you may have used to try to get what you need

The root cause is that the condition and function call mismatch here: https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/cc/genai/inference/c/llm_inference_engine_cpu.cc#L507 Please help fix it. Thanks!

Other info / Complete Logs

No response

[kuaashish]

Hi @mvhsin,

Could you please provide the complete steps you are following from our documentation, or share the command you are using along with the full error log? This will help us better understand the issue and reproduce it on our end.

Thank you!!

[github-actions]

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.