-
### Description
Getting the following error when trying to run code on a A100 80GB Google Cloud Debian Deep Learning image ([c0-deeplearning-common-cu113-v20230501-debian-10](https://console.cloud.…
-
os: Ubuntu 22.04
pytorch: 2.1.0 nightly with cuda 12.1
miniconda-3.10 (latest)
When using ```pip install -e . ``` as documented to compile/install triton 2.1.0-dev[head]. @triton.jit does't get b…
-
Platforms: inductor
This test was disabled because it is failing in CI. See [recent examples](https://hud.pytorch.org/flakytest?name=test_comprehensive_nn_functional_batch_norm_cuda_float64&suite=Tes…
-
### Describe the Feature
- Being able to rename collections
- Making translation things easier by adding a button like "skip to next untranslated item" so that you don't have to navigate in menus li…
-
My setup is:
1. jetson orin 32GB
2. JetPack 6.0
3. Triton 2.40 (NGC Container 23.11)
4. Cuda 12.2, TensorRT 8.6.2
5. Python Backend API 1.16
**`input_0: try to use CUDA copy while GPU is no…
-
Dear Alex.
Thanks for this great repo. The flash attention community really needs this feature.
I'm trying to integrate this repo in my own project, but encounter two issues:
- torch.bfloat16 is n…
-
I would like to deploy qwen-vl using Triton. Do you have any example repositories that are compatible with qwen-vl?
-
### Description
```shell
Host: linux amd64
GPU: RTX 3060
container version:22.12
GPT model converted from megatron (model files and configs are from gpt guide)
dockerfile:
----
ARG TRITON_SE…
-
Hello, thank you for your open source. When I train on my own dataset, an error message will be reported at the end of 1 epoch training. The error message is as follows:
2024-10-18 20:47:35,180 D…
-
**Description**
I encounter a crash when I am using big model with ONNX backend on CPU. The problem seems to be related to this closed ticket: https://github.com/triton-inference-server/server/issu…