Shakhizat Nurgaliyev

ValueError: axes don't match array

2

### Search before asking - [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no similar questions. ### Question Hi yolov5 community, Has anyone experienced the below problem,...

Nvidia Jetson device Support

25

Dear Nvidia Team, I would like to request support for running TensorRT-LLM on the Nvidia AGX Orin development kit. Thank you! Best regards, Shakhizat

Can not make –allow-privileged=true for kubelet on worker nodes

1

Hello, I was trying to setup dynamically provisioned volumes using Exascaler CSI Driver(https://github.com/DDNStorage/exa-csi-driver) for Kubernetes cluster. However, the Persistent Volume Claim always shows a pending status. I have a question...

Hello, During the finetuning of LLM on the NVIDIA Jetson AGX Orin Developer Kit, I have encountered an issue. When I use the parameter settings **paged_adamw_8bit** or **paged_adamw_32bit**, the process...

### ❓ The question Dear all, Could you please suggest what parameter(s) increase or change when conducting multi-node training of OLMo, so that we can observe the difference between single-node...

Greeting to all, I was trying to enable the GPU on my NVIDIA Jetson AGX Orin when I ran the command "microk8s enable gpu." However, it appears that Kubernetes is...

## ❓ General Questions Hello everyone, I am running inference using two dual AMD Radeon RX 7900 XTX GPUs with the following command: `mlc_llm chat HF://mlc-ai/Llama-3.1-70B-Instruct-q4f16_1-MLC --overrides "tensor_parallel_shards=2;prefill_chunk_size=128"` During inference,...

### Problem Description Hello, when I run command to build from the source : `./install.sh -idc --legacy_hipblas_direct` It shows below output after a while : ` 40 | #include |...

Feature 'f16 arithemetic and compare instructions' requires .target sm_53 or higher

3

### Your current environment Collecting environment information... PyTorch version: 2.3.0 Is debug build: False CUDA used to build PyTorch: 12.2 ROCM used to build PyTorch: N/A OS: Ubuntu 22.04.4 LTS...

error: creating server: Internal - s3:// file-system not supported. To enable, build with -DTRITON_ENABLE_S3=ON.

2

Hello, When I pass S3 path, I receive the following error: `error: creating server: Internal - s3:// file-system not supported. To enable, build with -DTRITON_ENABLE_S3=ON` The pod is based on...