Docker compose serving stack for DeepSeek v4 Flash DSpark for NVIDIA Spark GB10 system using Aidendle94 image
☆33Aug 30, 2026Updated last month
Alternatives and similar repositories for DeepSeek-v4-DSpark-Aidendle94-GB10-ServingStack
Users that are interested in DeepSeek-v4-DSpark-Aidendle94-GB10-ServingStack are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- GLM-5.3-Flash NVFP4 (lab quant) on 2x DGX Spark — TP=2 over RoCE, one .env, compose head/worker, download/start/stop/status/tail-log☆11Sep 8, 2026Updated last month
- GLM-5.3-Flash (EXL3 4bpw + DFlash2) on 2x NVIDIA DGX Spark: one-shot installer, 33-74 tok/s c1, 1.3M+ context, vision☆43Sep 2, 2026Updated last month
- ☆17Sep 6, 2026Updated last month
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆493Sep 10, 2026Updated last month
- Headless / multi-user serving-mode for the DGX Spark: free unified memory for vLLM by paring back the desktop. Companion to qwen3.5-122B-…☆20Jun 29, 2026Updated 4 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- DGX Spark / GB10 vLLM Docker stack for large-model serving, presets, patches, and validation notes.☆12Jun 29, 2026Updated 4 months ago
- Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors e…☆105Updated this week
- DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw on 2x NVIDIA DGX Spark (GB10) with TensorFold: 2.1-2.3x the vLLM kit's decode speed.☆71Updated this week
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆106Aug 20, 2026Updated 2 months ago
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆404Updated this week
- Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.☆71Updated this week
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,497Oct 4, 2026Updated 3 weeks ago
- This is an experimental fork of Salvatore Sanfilippo's `antirez/ds4` project: ```text https://github.com/antirez/ds4 ``` This checkout …☆28Sep 23, 2026Updated last month
- DGX Spark real-time system monitoring dashboard (SvelteKit + SSE)☆22Mar 11, 2026Updated 7 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆17Jan 15, 2026Updated 9 months ago
- GLM-5.3-Flash on two NVIDIA GB10 nodes: versioned ARM64 images, one terminal launcher, native TP2 and image input☆15Oct 18, 2026Updated last week
- vLLM Tune consolidates MoE and FP8 dense GEMM kernel tuning into a single command☆32May 24, 2026Updated 5 months ago
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆18Jun 5, 2026Updated 4 months ago
- Two-node DGX Spark/ASUS GX10 DeepSeek V4 Flash DSpark NVFP4 port for vLLM 0.25, with live dashboard and reproducible deployment.☆82Updated this week
- Official Spark Arena Recipe Registry☆66Oct 17, 2026Updated last week
- BertholomusAI recipe: DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark (GB10), our own TensorFold TP2 engine. Weights: Mia-AiLab EXL3 2.9bpw (M…☆43Updated this week
- A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively☆128Feb 22, 2026Updated 8 months ago
- Real-time terminal UI dashboard for monitoring vLLM☆33Jul 13, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- A monitor of resources for DGX Spark☆25Feb 13, 2026Updated 8 months ago
- GLM-5.2 (744B/40B MoE) on a 4× DGX Spark / GB10 (sm_121) cluster: portable Triton sparse-MLA kernels, a data-free expert prune, MTP draft…☆37Aug 20, 2026Updated 2 months ago
- Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpar…☆411Aug 27, 2026Updated 2 months ago
- Per-session analytics for Hermes Desktop: tokens, cache, cost, failures, files — plus Ask AI analysis☆16Sep 27, 2026Updated last month
- Validate the usable size of your local LLM cache under pressure☆13Sep 26, 2026Updated last month
- ☆13Apr 28, 2025Updated last year
- DGX Spark inference dashboard — vLLM, SGLang, llama.cpp, WebGPU & sparkrun with agent-powered Auto-Fix and speed optimization☆69Updated this week
- Stable, high-throughput inference server for multi-GPU NVIDIA V100 (SM70): Qwen3.8 Flash-Next with AWQ / NVFP4, multimodal input, CPU/dis…☆17Updated this week
- Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)☆316Aug 23, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ⏳Time, but only when it matters. A Hermes plugin for tacit temporal awareness.☆22Aug 16, 2026Updated 2 months ago
- Qwen3.6 27B × DFlash — 30-35 tok/s on NVIDIA DGX Spark (GB10) - LLama.Cpp☆17May 2, 2026Updated 5 months ago
- 【Hermes 桌面端插件 v3.7.7】外观整合浮窗——双栏面板、悬停即见简介、主题自动跟随官方(含 Ink & Paper 灰阶与 Binshao 暖纸)、纸纹模拟、霞鹜文楷、界面缩放与聊天文字大小、窗口透明(玻璃)、开场标识、消息气泡、对话行为五件套，状态栏一键设置，…☆16Oct 23, 2026Updated last week
- MiMo-V2.6-Flash-RL on 2x NVIDIA DGX Spark (GB10): vLLM TP2 + DFlash + vision/audio, fp8 KV 300K, four fixes for the stock image, measured…☆47Oct 4, 2026Updated 3 weeks ago
- a fast and lightweight distributed background task processing framework with seamless scheduling.☆15Mar 30, 2026Updated 6 months ago
- DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM ki…☆93Updated this week
- Raw speed benchmark traces: Qwen3.8-27B on 4x RTX 3090. llama.cpp GGUF sweeps + 288-point vLLM vs SGLang, NVFP4 vs FP8 matrix.☆13Sep 28, 2026Updated last month