-
### Your current environment
```text
The output of `python collect_env.py`
```
Collecting environment information...
WARNING 07-08 14:14:25 _custom_ops.py:14] Failed to import from vllm._C with M…
-
### 🐛 Describe the bug
```python
import pygame
import torch
from torch import nn
screen = pygame.display.set_mode((9, 9))
class BearBrain(nn.Module):
def __init__(self):
super().…
-
I tried to run the image_demo as below
python demo/image_demo.py --config configs/mamba2_yolo_world_s.py --checkpoint MambaYOLOWorld_s_pretrain_O365GoldG.pth --image my_image.jpg --text food
an…
-
### Description
```shell
main branch, V100
Deployed docker pods crashs and restarts every few minutes. It seems stable when qps is low.
Below is error log before pods crashs which I get using com…
-
Hi guys, i tried to train the lora but i got a lot of error and idk how to fix(i tried).
thanks if anyone could help me
here's the error:
Traceback (most recent call last):
File "D:\kohya_ss\ven…
-
Hi, is there any guide how to implement Yolo v4 TAO model into Triton inference server? I have trained Yolo v4 custom data model via TAO toolkit and looking for an guide how to implement this model wi…
-
I'm opening this issue to track the progress on enabling project development within conda environment based on the conda-forge channel without external dependencies.
Current working solution:
1. C…
-
`triton ssh` looks up the image to see if it should use the ubuntu user for ssh instead of root. If the image has been disabled, or otherwise can't be looked up, `triton ssh` fails outright.
Instea…
-
### System Info
- CPU architecture: x86_64
- Host memory: 256GB
- GPU
+ Name: NVIDIA A30
+ Memory: 24GB
- Libraries
+ TensorRT-LLM: v0.11.0
+ TensorRT: 10.1.0
+ CUDA: 12.6
+ NVID…
-
Hi， all.
I used triton and cuda to implement the gauss5x5 operator. The performance difference between triton and cuda is very large. What is the reason?
cuda: **0.55ms**
tirton: **17.03ms**
…