|
Easy-vllm — Let a code agent build & serve any model on vLLM for your DGX Sparks
|
|
1
|
133
|
July 11, 2026
|
|
Managing Multiple vLLM Models on DGX Spark with LiteLLM
|
|
9
|
334
|
July 11, 2026
|
|
GGUF Quantizer Independently Fingerprints the Universal Depth Layout
|
|
0
|
19
|
July 10, 2026
|
|
vLLM FP8 models unusable on AGX Thor (SM 11.0): kernels compiled for sm100f only — This kernel only supports sm100f. → CUBLAS_STATUS_INTERNAL_ERROR
|
|
2
|
31
|
July 8, 2026
|
|
Serving Qwen3.5-397B-A17B at 1M Tokens on 2× DGX Spark — MiniMax M3 Is Next
|
|
5
|
1057
|
July 3, 2026
|
|
DeepSeek v4 Flash (IQ2XXS) on a single GB10!
|
|
13
|
4498
|
July 2, 2026
|
|
Compute bottleneck evaluating multiple trajectories through a 7B VLM (VLA Architecture Design)
|
|
3
|
58
|
June 30, 2026
|
|
SCBKR: A local responsibility-chain workbench for LLMs with human-confirmed generation, storage, replay, and retrieval gates
|
|
1
|
51
|
June 30, 2026
|
|
Three times ( VoiceClone | VoiceDesign | CustomVoice ) - Faster-Qwen3-TTS for NVIDIA DGX Spark (GB10)
|
|
55
|
2220
|
June 30, 2026
|
|
2 node spark vs 3 or 4 node spark
|
|
18
|
1272
|
June 29, 2026
|
|
Ollama installation script for Jetson Jetpack 7
|
|
5
|
182
|
June 29, 2026
|
|
Hybrid Edge-Cloud modular VLA(Vision Language Action) Pipeline using NVIDIA NIM for Autonomous Driving
|
|
0
|
46
|
June 28, 2026
|
|
Qwen3.5-122B-A10B on single Spark: up to 51 tok/s (v2.1 — patches + quick-start + benchmark)
|
|
434
|
23702
|
June 24, 2026
|
|
Running vllm as a service on Thor JP7.2
|
|
6
|
138
|
June 24, 2026
|
|
EXCEPTION_ACCESS_VIOLATION while testing the Unreal ACE LLM plugin
|
|
0
|
23
|
June 22, 2026
|
|
You Can Only Keep ONE: DGX Spark, RTX 5090 Workstation, or Mac Studio Ultra - Which One Survives on Your Desk in 2026?
|
|
0
|
967
|
June 21, 2026
|
|
From Governance Runtime Assurance to Human-Directed Intelligence
|
|
7
|
58
|
June 19, 2026
|
|
Pushing GB10 to the Limit: Qwen3 235B MoE + Concurrent Best-of-4 + Persistent Agent Layer. Architecture check & Optimization tips?
|
|
0
|
217
|
June 12, 2026
|
|
Llama.cpp MTP Lifted LLM Performance of Jetson Orin
|
|
1
|
155
|
June 8, 2026
|
|
Ollama ERROR in docker
|
|
2
|
154
|
June 8, 2026
|
|
Jetson AGX Thor r38.4: BPMP thermal path stalls after large CUDA/vLLM unified-memory workload; nvfancontrol and thermal kworkers stuck in D state
|
|
11
|
243
|
June 5, 2026
|
|
vLLM Qwen3.6-27B Extended Latency on Jetson Thor 128GB with Large Prompts
|
|
7
|
348
|
June 4, 2026
|
|
Problem running Qwen Models via vllm on Jetson Orin
|
|
5
|
473
|
June 4, 2026
|
|
Nemotron-3-Nano on Jetson Thor vLLM : ITL degrades 4.7x with concurrency, MTP rejected
|
|
6
|
250
|
June 4, 2026
|
|
Nemotron-3-Super-120B-A12B-NVFP4 on single DGX Spark: 23.45 tok/s (spark-arena.com/ benhmarks)
|
|
6
|
1061
|
May 26, 2026
|
|
Deterministic gpt-oss-120b using vLLM on a DGX Spark
|
|
8
|
717
|
May 26, 2026
|
|
Request for Brev.dev Credits for Human Rights & Cognitive Disability Support Project (Non-Profit Watchdog)
|
|
0
|
56
|
May 23, 2026
|
|
Request to enable Public API Endpoints for my personal organization
|
|
0
|
37
|
May 22, 2026
|
|
Nemotron Nano Omni on Thor?
|
|
11
|
303
|
May 21, 2026
|
|
Jetson Thor reboots under AI workloads and when connecting 2.5" HDD
|
|
14
|
195
|
May 21, 2026
|