|
Compute bottleneck evaluating multiple trajectories through a 7B VLM (VLA Architecture Design)
|
|
3
|
57
|
June 30, 2026
|
|
Dynamic shapes not dynamic at all
|
|
1
|
34
|
June 30, 2026
|
|
Jetson AGX Orin (JetPack 6.2.1): silent GPU hang - host1x interrupt servicing stalls under sustained compute, reproduces on two distinct Orin systems
|
|
19
|
337
|
June 30, 2026
|
|
Can we fix the number of GPU Cores used during a TensorRT inference execution? & is (Multi-instance GPU) MIG Available on Jetson AGX Thor
|
|
4
|
59
|
June 29, 2026
|
|
FP4 (NVFP4) support on Jetson Orin Nano — is it planned or architecturally excluded?
|
|
2
|
58
|
June 26, 2026
|
|
SENTINEL — AI surveillance on Orin Nano Super: YOLOv8 + LFM2-VL + llama.cpp unified memory fix
|
|
5
|
107
|
June 24, 2026
|
|
DeepStream 8.0 / 7.1 compatibility issue on Jetson Orin Nano Super with JetPack 7.2 / Jetson Linux R39.2
|
|
7
|
201
|
June 23, 2026
|
|
You Can Only Keep ONE: DGX Spark, RTX 5090 Workstation, or Mac Studio Ultra - Which One Survives on Your Desk in 2026?
|
|
0
|
951
|
June 21, 2026
|
|
Triton Inference Server Support Matrix lists incorrect PyTorch version for release 26.05
|
|
0
|
39
|
June 20, 2026
|
|
High YOLOv8-s inference latency on TensorRTNode, but `trtexec` is fast
|
|
6
|
70
|
June 16, 2026
|
|
Pushing GB10 to the Limit: Qwen3 235B MoE + Concurrent Best-of-4 + Persistent Agent Layer. Architecture check & Optimization tips?
|
|
0
|
215
|
June 12, 2026
|
|
2:4 sparsity doesnot improve inference performance on RTX 3090
|
|
15
|
3755
|
June 4, 2026
|
|
Production Inference Path for Fine-Tuned Canary-v2 (TensorRT or RIVA Support)
|
|
4
|
164
|
June 2, 2026
|
|
Qwen3.6-27B-FP8 export failed in fuse_gdn_input_projections: Float8_e4m3fn and Half torch.cat promotion unsupported
|
|
1
|
72
|
May 30, 2026
|
|
Strange changes in file size when deployed with tensorrt
|
|
9
|
1003
|
May 30, 2026
|
|
Fail to Build the TRT Engine of a multi-GatherND ONNX Model for large input volume
|
|
1
|
64
|
May 30, 2026
|
|
I need Tensorrt 10.3 C++ API Documentation
|
|
2
|
63
|
May 21, 2026
|
|
Question Regarding INT8 Accuracy Degradation on Turing GPUs with TensorRT 10.11
|
|
2
|
135
|
May 20, 2026
|
|
Questions about the CUDA Runtime
|
|
22
|
251
|
May 20, 2026
|
|
Adaptive Governance Runtime Engineering
|
|
0
|
48
|
May 19, 2026
|
|
Runtime Optimization vs Governance Runtime Engineering — Parallel Acceleration Above the Model Layer
|
|
0
|
45
|
May 16, 2026
|
|
Runtime Optimization vs Governance Orchestration — A New AI Acceleration Layer Emerging Above the Model
|
|
0
|
68
|
May 11, 2026
|
|
Issues with long term execution of computer vision project using Jetson Orin
|
|
5
|
102
|
May 7, 2026
|
|
TensorRT engine produces distorted outputs on Jetson Orin NX (JetPack 6.2 / Ampere) but matches ONNX on DGX Spark (JetPack 7.0 / Grace Blackwell)
|
|
10
|
206
|
May 6, 2026
|
|
The versions of deep learning tools such as CUDA and TensorRT for Jetson
|
|
5
|
120
|
May 4, 2026
|
|
[Issue] Qwen3-Next-80B NVFP4 and FP8 Cannot Be Served via trtllm-serve on DGX Spark GB10 (TRT-LLM 1.3.0rc7)
|
|
2
|
299
|
May 1, 2026
|
|
Error Code: 9: Skipping tactic 0x001526e231ae2e51 due to exception Cask convolution execution
|
|
3
|
393
|
April 30, 2026
|
|
Issues with Using TensorRT on Jetson Orin Nano
|
|
3
|
236
|
April 30, 2026
|
|
Jetson Orin Nano run TensorRT's sample failed
|
|
8
|
108
|
April 27, 2026
|
|
Model outputting NaNs
|
|
3
|
242
|
April 20, 2026
|