mlc-llm icon indicating copy to clipboard operation
mlc-llm copied to clipboard

Universal LLM Deployment Engine with ML Compilation

Results 578 mlc-llm issues
Sort by recently updated
recently updated
newest added

## 🐛 Bug Do not running Llama-3-8B-Instruct-q4f16_1-MLC ## To Reproduce Steps to reproduce the behavior: 1. conda create --name mlc-prebuilt python=3.11 2. conda activate mlc-prebuilt 3. conda install -c conda-forge...

bug

## 🐛 Bug ## To Reproduce Steps to reproduce the behavior: 1. Install latest mlc-llm and mlc-ai in conda with python 3.12, running on an Apple Silicon (M1 Pro) MacBook...

bug

## ❓ General Questions I'm trying to add a model I'm interested in running with MLC-LLM, however is there a method for testing the intermediate `nn.Modules` that are part of...

question

## ⚙️ Request New Models - Link to an existing implementation (e.g. Hugging Face/Github): ## Additional context

new-models

## ❓ General Questions When checking the Android demo app and Build Android App from Source, only 'arm64-v8a' is supported. I wonder if it is possible to build the 'mlc_llm...

question

This pr updates `use_qk_norm` option for Cohere series models like Command-R-Plus.

Hello, i does android demo app possible using with nnapi support?

question

## 🐛 Bug ## To Reproduce Steps to reproduce the behavior: 1.Do not set ``. Of course, my fine-tuned qwen2 model will output ``. But the problem is that it...

bug

## ❓ General Questions hello,great pr 我安装apk后,点击下载模型,进度一直到不了100%,还在下载,下载V版本的下载60个bin模型了, 请问哪里有问题么? 我想手动下载, 而且出现了模型重复下载的 情况,比如params_shard_0-1.bin 是重复下载吧

question

## 🐛 Bug I believe when the final token completes or is about to be completed in a request, the entire app crashes with `libc++abi: terminating due to uncaught exception...

bug