-
## Description
INT8 quantization fails with error in title on Jetson AGX Orin in latest JetPack 6.0 container. I also tried this previously on JetPack 5.1.2 and it failed with the same issue so I t…
-
Hello, I am trying to add support for models with GQA eg. Tiny llama
The indicator for grouped query attention is when num_key_value_heads < num_attention_heads in config.json file
For TinyLlama m…
-
**问题描述**
yolov3_ darknet53_ 270e_ VOC 训练出来的模型
image_shape:[3,608,608]
Paddle2onnx conversion yolov3_ darknet53_ 270e_ VOC model
[WARNING] Due to the operator:multiclass_nms3, the converted…
-
### Component
Forge
### Have you ensured that all of these are up to date?
- [X] Foundry
- [ ] Foundryup
### What version of Foundry are you on?
forge 0.2.0 (0ae39ea 2023-12-11T00:27:32.487222000…
-
Referring to the discussion in #2176 it looks like there is a major speed regression from 0.28.1 to 0.29.0. The example function below and similar tight loops, doing merely more than nan checks, addit…
-
# Error: Stack too deep.
I have a web3j project and I'm trying to import an already existing contract for interaction, but the compilation fails with the error:
```
Error: Stack too deep. Try compi…
-
Hi,
I'm trying to migrate Numba to LLVM's new pass manager APIs introduced in [1046](https://github.com/numba/llvmlite/pull/1046) and I think I might have encountered a bug.
Some of the tests (eg…
-
I have met a issue when run realsense D455.
When I run the ros Mono node, it can detetced the ORB feature and local the map.
How ever, when I run ros Mono-inertial node, I found that it can not loca…
-
# 复现步骤
## 环境
- Ubuntu 22.04
- Python 3.11.7
- torch: 2.2.2+cu121
- pnnx: 通过 pip install 安装， 版本 20240410
## 最小复现代码
x.py
```python
import torch
import torch.nn.functional as F
cla…
-
**Description**
Triton is unable to load models with Tensorflow saved model format with OpenVINO backend.
**Triton Information**
What version of Triton are you using?
23.10,23.11,23.12,24.03,24.…