# tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark > A serving stack for DeepSeek-V4.1-Flash (552B MoE) on four NVIDIA DGX Sparks via vLLM with tensor parallelism, including patches, launch scripts, and measured throughput numbers. - Magnitude: 0.3 out of 10 — Steady - Stars: 86 total · +0 stars on 2026-09-27 (UTC), ≈ 0 by evening - Star trust: star growth looks organic - Category: Language models · Language: Python · License: MIT · Created: 2026-09-10 · Last push: 2026-09-19 - GitHub: https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark · Page: https://gitnova.dev/en/r/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark ## Useful for - Deploy DeepSeek-V4.1-Flash across multiple DGX Sparks with vLLM - Compare throughput and KV pool size between TP3 and TP4 configurations - Verify vision and tool calling with the provided demo script ## Why it’s here - The repository is 17 days old and already has 86 stars. - Recent forks include notable developers: @yunwei37 (1,315 followers). ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 15 - Issues and pull requests: 12 - Watchers: 4 - Average over the last week: 0 per day - Usual pace: 4 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-09-30 … 2026-10-29: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 09-14 1.3, 09-15 1.8, 09-16 1.0, 09-17 1.0, 09-18 0.9, 09-19 0.9, 09-20 1.5, 09-21 1.4, 09-22 0.7, 09-23 0.7, 09-24 1.0, 09-25 0.7, 09-26 0.3, 09-27 0.3 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-27 00:15 UTC, updated every 30 minutes.