Oliver Xu

You should compile onnx2tnn first !!!

4

**1. 使用环境（environment）** - OS: Mac - OS Version: Monterey 12.4 **2. Github版本** - branch：origin/master - commit(optional): commit a690339 **3. 详细描述bug 情况 (Describe the bug)** A clear and concise description of...

Fix torch listconstruct errors when dependent on inputs flexible shapes

2

## Recommodation for merge: No. There're some unit tests still needs to be added. ## What it fixes This PR is trying to fix #1921, along with other bugs that...

Conversion for Padding related to dynamic input shape failed

4

## 🐞Describing the bug If model contained a Padding, whose pad value is related to dynamic input shape, the conversion failed. ## Stack Trace ``` scikit-learn version 1.2.2 is not...

CoreML Calculation error for some parameter setup case of torch.nn.AvgPool2d

8

## 🐞Describing the bug Upon converting `torch.nn.AvgPool2d`, CoreML predict (both on host Mac using `libcoremlpython` or on device iPhone 13 Pro) gives erroneous output on parameter setup "kernel size 7,...

Possible 'pad' issue when used in chain ?

2

# Problems I met: I padded some assets (or expenses) to an asset account spendable, and then pad this asset account spendable to another asset account. `bean-check` gives me an...

第二次使用，只要勾选了“有午休”，进度就不会跑

4

如题用于记录。争取能提PR

Is there python binding support ?

1

There's no python binding related code in repository. Since ppl.nn.llm is ppl.nn, how can I integrate ppl.nn.llm with ppl.nn python binding ? Is it possible to use python to build...

Qwen Chat CUDA OutOfMemory

2

RTX 4090 24G, Qwen-7B-Chat loads OK: ``` model_config = ModelConfig(lora_infos={ "lora_1": conf['lora_1'], "lora_2": conf['lora_2'], }) model = ModelFactory.from_huggingface(conf['base_model_dir'], model_config=model_config) pipeline = Pipeline(model, model.tokenizer) ``` But the following causes OutOfMemoryError ```...