ChaoQin

[Model Request] OpenELM

1

## ⚙️ Request New Models - Link to an existing implementation (e.g. Hugging Face/Github): https://huggingface.co/apple/OpenELM-3B-Instruct - Is this model architecture supported by MLC-LLM? (the list of [supported models](https://llm.mlc.ai/docs/prebuilt_models.html)) No ##...

[Bug] gemma-2b for Android. OpenCL Error Code=-54: CL_INVALID_WORK_GROUP_SIZE

7

## 🐛 Bug Compile Gemma-2b for Android in q4f16_0. Load model successful, but chat get error: OpenCL Error Code=-54: CL_INVALID_WORK_GROUP_SIZE Stack trace: File "/home/chaoqin/mlcllm/3rdpaty/tvm/scr/runtime/opencl/opencl_module.cc", line 90 ## To Reproduce Steps...

## 🐛 Bug Long respone from llama-2-7b lead to Android APP no response. When I ask "what is qualcomm", Llama-2 will respone a very long content. After that, when I...