|
Introducing Tool Eval Bench CLI
|
|
230
|
12819
|
November 19, 2026
|
|
Mjolnir — a Community Open Project for LLM serving on Jetson Thor: 1.21× decode kernel, fp6 KV, MTP=6, +68% decode
|
|
4
|
106
|
November 18, 2026
|
|
Co-Designing Sparse Attention for Efficient Long-Context Inference
|
|
0
|
29
|
November 17, 2026
|
|
Can One NVIDIA DGX Spark Support 4 Developers Running Independent AI Coding Agents for Unity Game Development?
|
|
8
|
882
|
November 17, 2026
|
|
Let's optimize ... DGX Spark
|
|
18
|
2621
|
November 16, 2026
|
|
NVIDIA Vera Rubin NVL72 Leads Agentic Inference Performance on MLPerf Endpoints v1.0
|
|
0
|
26
|
November 16, 2026
|
|
Post-Training NVIDIA Nemotron to Increase Accuracy in Your Scientific Domain
|
|
0
|
25
|
November 16, 2026
|
|
NeMo Helix 0.9.1 on a clean Ubuntu 24.04 machine: five install problems and their workarounds
|
|
0
|
20
|
November 15, 2026
|
|
Request for NVIDIA Build API Rate Limit Increase (40 → 200 RPM) — OpenCode Agentic Development
|
|
0
|
44
|
November 13, 2026
|
|
Request for NVIDIA NIM API Rate Limit Increase (40 RPM to 200 RPM) – Agentic Workflow Development
|
|
0
|
54
|
November 12, 2026
|
|
Pragmatic Software Factories?
|
|
7
|
729
|
November 11, 2026
|
|
DGX Spark Evaluation / Sponsorship Request – Local AI Coding Agents
|
|
3
|
286
|
November 10, 2026
|
|
Qwen3.8-27B at 34–38 tok/s on DGX Spark — open-source one-command setup (SGLang + NVFP4 + DSpark)
|
|
118
|
24031
|
November 10, 2026
|
|
Request for NVIDIA Build API Rate Limit Increase (40 → 200 RPM)
|
|
0
|
80
|
November 9, 2026
|
|
[NEWS] NVIDIA at CoRL 2026: Advancing Robot Learning
|
|
0
|
237
|
November 9, 2026
|
|
Request for NVIDIA Build API Rate Limit Increase (40 → 200 RPM) — OpenCode Agentic Development
|
|
0
|
79
|
November 9, 2026
|
|
Decision models (d1, JEV, Perplexity Flash, d3-mini, Kev) measured on Jetson – answer accuracy, latency, memory per request
|
|
1
|
154
|
November 9, 2026
|
|
Why Context Window Expansion Fails in Agentic AI: The AST-Driven Pruning Solution
|
|
0
|
34
|
November 8, 2026
|
|
TZeroAlgorithm: AST-Driven Context Pruning Engine & MCP Server for LLM VRAM Optimization
|
|
0
|
82
|
November 8, 2026
|
|
[News] NVIDIA at CoRL 2026: Advancing Robot Learning
|
|
0
|
125
|
November 7, 2026
|
|
Nsight Systems 2026.6.1 Desktop-Server (x86-64 | Arm SBSA | Arm64 native and x64 emulation) Release Announcement
|
|
0
|
83
|
November 5, 2026
|
|
Request for NVIDIA NIM API Credit and Rate-Limit Increase
|
|
0
|
51
|
November 5, 2026
|
|
Unable to receive SMS verification code for NVIDIA Build API key
|
|
0
|
65
|
November 5, 2026
|
|
It makes no sense to me anymore to run my Sparks above a 1400–1700 MHz GPU clock
|
|
17
|
2618
|
November 4, 2026
|
|
Unable to receive SMS verification code for NVIDIA Build API key
|
|
1
|
100
|
November 4, 2026
|
|
NVIDIA Nemotron-3.5-Bolt-74B-A9B-24GB and Nemotron-3.5-Super-VL-120B-A12B published - NVIDIAs new general purpose models especially for GB10
|
|
19
|
2297
|
November 1, 2026
|
|
Anyone open to showing me a demo?
|
|
18
|
911
|
November 1, 2026
|
|
Request to Credit & Rate-Limit Increase from (1,000 → 5,000 credits, 40 → 200 RPM)
|
|
3
|
530
|
November 1, 2026
|
|
Six weeks optimizing Qwen3.8-Flash-Next on one DGX Spark: 67.5 tok/s median decode, ~80 on structured work — reproducible recipe with raw data
|
|
21
|
5100
|
October 31, 2026
|
|
[Livestream] Develop a Robot Policy with Agent Skills and NVIDIA Cosmos 3 Edge on Viam
|
|
0
|
126
|
October 31, 2026
|