@ericlewis777 Huge thanks! This is so much fun, very helpful and informative! Do you have any further plan to experiment similar to what the exo-lab’s post(link) combining Mac and the spark? Or I mean putting the heavy computation on a saparate server/PC or Mac and the rest on the Spark clusters?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Performance characteristics going from 1->2 sparks | 38 | 1370 | August 30, 2026 | |
| Qwen3.5-397B-A17B-int4-AutoRound - 4 x db10 node - updated results 37 - 94 tok/s | 26 | 2452 | April 28, 2026 | |
| Install and Use vLLM for Inference on two Sparks does not work | 159 | 7299 | December 9, 2025 | |
| Should we as a community gofundme one Spark for Eugr's nightly builds? | 51 | 2429 | April 1, 2026 | |
| Two-Spark cluster with vLLM using tensor-parallel-size 2 causes one node to drop while the other's GPU goes 100% forever | 36 | 2876 | February 13, 2026 | |
| Kimi 2.6 and Qwen 3.5-397B -FP8 on 8xGB10 cluster | 28 | 2577 | May 29, 2026 | |
| DGX Spark performance | 49 | 8205 | February 13, 2026 | |
| Three node Spark clusters (without a switch) are now supported in spark-vllm-docker and sparkrun! | 15 | 3677 | July 19, 2026 | |
| DGX Spark + Qwen3-Next-80B: Proven Performance, But Missing Clear Path to NIM, TensorRT-LLM & Web UIs | 16 | 6179 | March 6, 2026 | |
| Help: Running NVFP4 model on 2x DGX Spark with vLLM + Ray (multi-node) | 18 | 3210 | December 25, 2025 |