|
How to convert NV12 from nvargus to RGBA/RGB correctly using VIC or VPI?
|
|
3
|
12
|
March 11, 2026
|
|
Open-Source CLI Agent Framework for NVIDIA AI Endpoints - Seeking Feedback
|
|
2
|
22
|
March 10, 2026
|
|
Clear guide to install all the AI model training components
|
|
2
|
53
|
March 5, 2026
|
|
Verify ai performance by cutlass_profiler,but it was too slow,why?
|
|
1
|
18
|
March 4, 2026
|
|
Bypassing Python: Piping local LLM inference directly into a deterministic C++ compiler pipeline
|
|
2
|
25
|
March 1, 2026
|
|
Execution context creation fails with multiple optimization profiles
|
|
2
|
36
|
February 28, 2026
|
|
Results for ONNX inference vs TRT inference are huge using nvidia/segformer-b2-finetuned-ade-512-512
|
|
1
|
24
|
February 26, 2026
|
|
NVIDIA A2 16GB Ampere AI Graphics Card not working
|
|
0
|
31
|
February 19, 2026
|
|
Model outputting NaNs
|
|
2
|
90
|
February 18, 2026
|
|
Performance Inquiry: Optimizing Qwen3-VL 2B Inference for 2 QPS Target on Orin Nano Super
|
|
4
|
144
|
February 9, 2026
|
|
Suboptimal PyTorch Performance on Jetson Orin Nano Super
|
|
3
|
65
|
February 5, 2026
|
|
Why is NCCL not installed in the “nvcr.io/nvidia/cuda:13.1.1-cudnn-devel-ubuntu24.04” image?
|
|
0
|
57
|
February 4, 2026
|
|
TensorRT IAttention SDK issue
|
|
0
|
27
|
February 2, 2026
|
|
New NGC vLLM container image (vllm:26.01-py3)
|
|
4
|
727
|
January 31, 2026
|
|
Different Fusion Mechanism Causes Onnx --> Engine Failure
|
|
2
|
31
|
January 29, 2026
|
|
Nvfp4 Dynamic Quantizer Very Slow with Bias
|
|
3
|
67
|
January 29, 2026
|
|
Nvcr.io/nvidia/tensorrt:25.12-py3-igpu container is not running on Cuda 13
|
|
2
|
78
|
January 29, 2026
|
|
Consistent "CUDA error: an illegal memory access was encountered" Error
|
|
8
|
574
|
January 29, 2026
|
|
cudaErrorIllegalAddress Encountered: "CUDA error: an illegal memory access was encountered"
|
|
2
|
442
|
January 20, 2026
|
|
Architecture and library compatibility on aarch64
|
|
4
|
389
|
January 18, 2026
|
|
Effective PyTorch and CUDA
|
|
23
|
8854
|
January 12, 2026
|
|
Real-Time Poker Card Detection on Jetson Orin
|
|
0
|
84
|
January 9, 2026
|
|
NvRmMemInitNvmap failed / NVMAP permission denied when launching nvcr.io/nvidia/vllm:25.11-py3 container on Jetson Orin NX + JetPack 6.2 (L4T 36.4.3)
|
|
5
|
141
|
January 21, 2026
|
|
Optimising AI reasoning pipeline – Layer 2 + 3 merge for CPU efficiency
|
|
2
|
36
|
January 8, 2026
|
|
CUDNN failure 8: CUDNN_STATUS_EXECUTION_FAILED ; GPU=0 ; hostname=ubuntu
|
|
1
|
155
|
January 8, 2026
|
|
Nsys profile not showing any GPU data
|
|
2
|
103
|
January 5, 2026
|
|
cuDNN no longer included with CUDA Toolkit creates major friction for C++ ML toolchains
|
|
3
|
114
|
January 5, 2026
|
|
TensorRT RT-Detr model conversion precision loss
|
|
13
|
259
|
January 5, 2026
|
|
Verifying claimed TOPS performance on Jetson Thor – CUTLASS kernel for SM110 does not run, SM80 gives very low performance (~6.9 TFLOP/s)
|
|
22
|
613
|
January 21, 2026
|
|
Quantized GeMM using fp32 for Q/DQ layers
|
|
0
|
52
|
January 2, 2026
|