|
TensorRT 10.14 silently produces wrong detection scores for D-FINE (DETR-style) models on RTX 5090 / sm_120 — default build drops 12 detections to 0,
|
|
1
|
28
|
August 21, 2026
|
|
[Blackwell] cuDNN fused FP16 SDPA decode kernel (q_len=1) hangs under MPS multi-tenancy
|
|
0
|
11
|
August 21, 2026
|
|
Request for Access: Riva TTS Magpie
|
|
4
|
213
|
August 20, 2026
|
|
TrafficCamNet Transformer Lite: Fine-tuning from 4 to 9 classes — RT-DETR weights or ResNet-50 backbone weights?
|
|
2
|
33
|
August 19, 2026
|
|
What are good practices for building reliable AI workflows that interact with external APIs?
|
|
2
|
52
|
August 18, 2026
|
|
Yin Yan appled to code
|
|
0
|
10
|
August 18, 2026
|
|
Is 32× A100 40 GB with 1 GPU per node a reasonable distributed-training testbed?
|
|
1
|
18
|
August 18, 2026
|
|
Qwen3.8-27B at 256K on a 24 GB Blackwell target GPU: iMatrix NVFP4 + MTP, 55.4 tok/s
|
|
0
|
137
|
August 18, 2026
|
|
TensorRT inferior scalability on A10, L4 possibly due to locking issues
|
|
8
|
228
|
August 17, 2026
|
|
Where is Qwen 3.8 NVFP4?
|
|
0
|
150
|
August 17, 2026
|
|
What Matters Most for Long-Form AI Writing: Context Window, Memory, or Prompt Structure?
|
|
0
|
47
|
August 17, 2026
|
|
DeepSeek-Coder-V2-Lite 16B on RTX 2050 laptop — seeking inference feedback
|
|
3
|
63
|
August 16, 2026
|
|
Work whit agent
|
|
0
|
24
|
August 16, 2026
|
|
Individual developer access to Windows AR SDK Core
|
|
0
|
17
|
August 16, 2026
|
|
SIPA-OS AI PIPELINE
|
|
0
|
32
|
August 14, 2026
|
|
Aliased I/O TensorRT plugin bug
|
|
0
|
21
|
August 13, 2026
|
|
No artifact → no claim → exit 1. No hash → no trust. No zip → no history. System records existence, not truth
|
|
0
|
28
|
August 13, 2026
|
|
Meta Muse Glimmer 30B unslot
|
|
0
|
43
|
August 12, 2026
|
|
How to Scale from 2 to 10+ DGX Spark Systems for a ChatGPT-Like AI Platform?
|
|
2
|
92
|
August 10, 2026
|
|
Infer vs generate for Triton ensemble models
|
|
0
|
19
|
August 9, 2026
|
|
PyTorch Conditionals that run on GPU / TensorRT
|
|
1
|
36
|
August 8, 2026
|
|
AOT tensorrt.plugin reloads plugin PTX via cuModuleLoadData on every enqueue in dynamic-shape engines
|
|
2
|
86
|
August 6, 2026
|
|
Techniques to Imporve TensorRT Model Inference Speed
|
|
3
|
178
|
August 5, 2026
|
|
100m Person Detection & Tracking at 35+ FPS on Jetson Orin Nano (8GB)
|
|
3
|
518
|
August 5, 2026
|
|
TensorRT Engine Creation Fails with “tensor volume exceeds 2147483648” on MobileNet SSD v2 in DeepStream 7.1 (Jetson Orin Nano)
|
|
2
|
112
|
August 4, 2026
|
|
FinC2E — Governance-First AI for AML/KYC & Audit-Ready Decision Support (Human-in-the-Loop)
|
|
3
|
139
|
August 4, 2026
|
|
Nemotron-asr-streaming NIM OOMs on 16 GB GeForce RTX (Blackwell) — only profile is batch-1024, no bs= or diarizer=disabled selector
|
|
2
|
127
|
August 4, 2026
|
|
Compute bottleneck evaluating multiple trajectories through a 7B VLM (VLA Architecture Design)
|
|
4
|
120
|
August 4, 2026
|
|
Bright AI runs DeepSeek-Coder-V2-Lite 16B locally on an RTX 2050 laptop
|
|
0
|
40
|
August 3, 2026
|
|
Open catalog comparing NVIDIA Riva with 168 TTS and 106 STT systems
|
|
0
|
14
|
August 3, 2026
|