Gordon Wong

According to the source: https://github.com/Sunhat/react-native-extra-dimensions-android/blob/0d449d2668a61d9900498ca894aec9691cc7a1a7/android/src/main/java/ca/jaysoo/extradimensions/ExtraDimensionsModule.java#L87 currently, all of the simulator's SoftMenuBarHeight will be 0, since the simulator's soft menu bar is controlled by `qemu.hw.mainkeys` instead of `config_showNavigationBar ` And I...

Did you enable SR-IOV in BIOS settings? https://zhuanlan.zhihu.com/p/561002399

I'm having this issue too, any update on this issue? This is a really great project BTW.

> @gongdao123 are you on ios 18 beta? No, I'm uploaded via Chrome. And view it using Chrome as well.

Sure thing. @alextran1502 [DSC04673.HIF.zip](https://github.com/user-attachments/files/15903689/DSC04673.HIF.zip)

Me too. The image with this issue is shot with ILCE-7CM2. Any update on this issue? @alextran1502

Yes, I have the same issue here. And here are Engine Args: python -m vllm.entrypoints.openai.api_server --model Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4 --disable-log-requests --quantization gptq - -max-model-len 11260 --gpu-memory-utilization 0.95 --served-model-name Qwen/Qwen2.5-32B --max-num-seqs 32 --tensor-parallel-size...

My case was using vLLM, if I set gpu_memory_utilization above 0.95. Will very easily trigger GPU hang when doing inferencing

Can we have this patch merged? It has been a few days since the approval. @SolitaryThinker