-
This code works as expected.
```cuda
auto lookup_cache_or_build_graph(int n, int c, int h, int w, int k, int r, int s,
int padding, int stride, int dilation)
{
static cache_type_fwd user_main…
-
Hello,
Thank you for maintaining this repository and the effort you've put into it. While working with the model, I encountered an issue related to the softmax function in the `_coordinate_selectio…
-
[//]: # "SPDX-FileCopyrightText: Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved."
[//]: # "SPDX-License-Identifier: Apache-2.0"
[//]: # ""
[//]: # "Licensed under the …
-
## 1. 背景
> Python 用户在进行数值计算、数据科学、机器学习和深度学习时，拥有广泛的库和框架可供选择。每年都会出现推动这些领域发展的新框架。这些活动和创造力意外地导致了多维数组（或称张量）库的碎片化，而多维数组库正是这些领域中的基础数据结构。选择包括 NumPy、Tensorflow、PyTorch、Dask、JAX、CuPy、MXNet、Xarray 等。
> 这些库的 API 大…
-
I am experiencing a significant discrepancy in the logits and probabilities output when running the same TensorFlow.js model on Android and iOS. The model, a self-trained MobileNetV3 (large) from PyTo…
-
## 🐛 Bug
## To Reproduce
Using this model [Phi-3-vision-128k-instruct](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct)
I got some bugs, need your help !!!
For phi3-v problem, w…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Problem summary
Hi, thank you for your work!
I got a problem and hope you can help. My model has 2 input im…
-
[ocr.zip](https://github.com/user-attachments/files/17430720/ocr.zip)
in package,
onnx_run_mod.py is start point
2.3\ppocr\en_number_mobile_v2.0_rec_infer.onnx is src onnx
2.3\ppocr\en_number_…
-
### Proposal to improve performance
Propose synchronizing the broadcast of tensor_dict at the beginning of each decoding step or block the process after broadcast.
### Report of performance regr…
-
ValueError: Attempted to assign 6 x 256 = 1536 image tokens to 466 placeholders
Command is shown as follows:CUDA_VISIBLE_DEVICES=0,1 swift infer --ckpt_dir ./output/internvl2-8b/v0-20241022-191411/ch…