-
**Describe the bug**
I am trying to run the non-persistent example given for mistralai/Mistral-7B-Instruct-v0.3 on a RTX A6000 GPU (on a server) so compute capability is met, ubuntu is 22.04, CUDA to…
-
### Describe the issue
### Urgency
_No response_
### Target platform
w11
### Build script
…
-
### Description
Sometimes the cuda version detection in linux is not correct.
### Reproduction Steps
1. pull and run the docker `nvidia/cuda:11.7.1-devel-ubuntu22.04`.
2. Run the LLamaSharp exampl…
-
### Checklist
- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 2. The bug has not been fixed in the latest version.
- [X] 3. Please note that if the bug-related issue y…
-
Yolov5-in-Deepstream-5.0-master/Deepstream 5.0/nvdsinfer_custom_impl_Yolo$ make
g++ -c -o yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I../includes -I/usr/local/cuda-11.3…
-
报错信息如下：Processing /data/yhl/mamba/Mamba-YOLO-main/selective_scan
Preparing metadata (setup.py) ... done
Requirement already satisfied: torch in /root/miniconda3/envs/mambayolo/lib/python3.10/site-…
-
## 🐛 Usability Bug
Consider the following scenario:
Helper Code:
```
def is_tpu_available():
devices = xm.xla_real_devices()
if len(devices) > 0:
return 'TPU' in devices[0]
…
-
### Your current environment
```text
Collecting environment information...
PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A…
-
```
task_space = TaskSpace("T")
a=[None] * num_gpu
for i in range(num_gpu):
@spawn(task_space[i], placement=[gpu(i)], vcus=0.0)
def t1():
with cp.cuda.Dev…
-
### 🐛 Describe the bug
Pytorch2.4 uses a new version of triton that adds the `cuTensorMapEncodeTiled` API (https://github.com/triton-lang/triton/commit/7289a23b4b78e4f4a8075c855f6e0754427f1ca6#diff-0…