R_REDDYX.XYZ
AIShell★ 95⑂ 8 forksMIT

0xSero/DeepSeek-V4.1-Flash-Two-Sparks

DeepSeek V4.1 on DGX Sparks

Runs DeepSeek-V4.1-Flash across two NVIDIA DGX Spark systems, featuring EXL3 routed experts, 262k token context, 2M‑token KV cache, vision, tool use, MTP, and Pi bundling.

// KEY FEATURES

  • Runs DeepSeek-V4.1-Flash model inference on dual DGX Spark nodes for AI workloads.
  • Provides 262k‑token context length and 2M‑token KV cache via EXL3 routed expert routing.
  • Integrates vision, tool use, MTP capabilities and bundles with Pi for edge deployment.
#deepseek#dgx-spark#exl3#vllm
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

Trading Agents for A-Shares★ 95WorkMesh AI Employment Platform★ 95Telegram AI Expense Logger★ 95Free Roblox Studio AI Agent★ 95AI Search in CLI★ 94Local Memory for LLM★ 96

← FULL CATALOG

0xSero/DeepSeek-V4.1-Flash-Two-Sparks — DeepSeek V4.1 on DGX…