Tencent Hy3 295B MoE (NVFP4) on 2x NVIDIA DGX Spark — TP2 over 200GbE, 256K context, 26 tok/s end-to-end. Tuned, benchmarked, agent-ready.
☆14Jul 7, 2026Updated 3 months ago
Alternatives and similar repositories for Hy3-295B-NVFP4-2x-DGX-Spark
Users that are interested in Hy3-295B-NVFP4-2x-DGX-Spark are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config…☆34Jul 12, 2026Updated 3 months ago
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Sep 4, 2026Updated last month
- Serve the official Ling-3.0-flash INT4 on one NVIDIA DGX Spark, 38.7 tok/s, faster than the community GGUF. Recipe, watchdog, benchmarks.☆26Aug 29, 2026Updated last month
- NVFP4 Gemma-4 26B-A4B MoE for DGX Spark — optimal recipe: DFlash n=10 (flex) on AEON vLLM Ultimate. 144 tok/s single / 1,724 peak (Coding…☆45Oct 6, 2026Updated 2 weeks ago
- GLM-5.2 NVFP4+AQLM on 3× DGX Spark — 380k context MTP serve stack☆72Aug 2, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆20Sep 2, 2023Updated 3 years ago
- 在DSH中与AI下五子棋，也可以让AI对局，看哪个AI棋力更强☆32Oct 3, 2026Updated 2 weeks ago
- ☆57Oct 4, 2026Updated 2 weeks ago
- Deploy Listmonk on Railway. Send e-mail campaigns from a powerful dashboard.☆10Apr 18, 2024Updated 2 years ago
- Tools used to convert counterstrike 2 demofiles to videos + annotations☆26Jun 25, 2026Updated 3 months ago
- Examples for using the SiLLM framework for training and running Large Language Models (LLMs) on Apple Silicon☆16May 8, 2025Updated last year
- DGX Spark (GB10/sm_121) port: DeepSeek-V4-Flash 159B on one Spark, GLM-5.2 753B across two. Prepacked 2-bit planes + unified-memory fixes…☆19Jul 20, 2026Updated 3 months ago
- TTS integration for Claude Code with audio ducking. Fork of https://git.sr.ht/~cg/claude-code-tts☆19Feb 2, 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
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Head-to-head comparison of local LLMs for agentic workflows (Hermes Agent, tool-eval-bench)☆36Oct 4, 2026Updated 2 weeks ago
- Starter template for an SPA-like MVC web app w/ Svelte, Tailwind, Inertia.js, Ruby on Rails☆11Mar 18, 2025Updated last year
- ☆41Jul 28, 2026Updated 2 months ago
- A web based RSS Aggregator☆23Feb 8, 2019Updated 7 years ago
- AWS Lambda Wrapper for v8-profiler☆12Feb 8, 2018Updated 8 years ago
- Command line interface and interactive chat for OpenAI API compatible endpoints☆30Updated this week
- Manage "engagement" on Twitter by moving retweets and algorithmic tweets to their own lists☆15Jun 4, 2021Updated 5 years ago
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆140Oct 15, 2026Updated last week
- ☆10Mar 17, 2024Updated 2 years 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.
- A DeepSeek Harness plugin for reasoning-effort defaults and protocol-aware gateway compatibility settings for llm-pi-ai models.☆54Updated this week
- Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, option…☆48Oct 13, 2026Updated last week
- Redwood.js serverfull hosting with PM2☆10Oct 20, 2021Updated 5 years ago
- Qwen3.8 27B on SGLang for DGX Spark☆473Sep 12, 2026Updated last month
- Incremental game using Angular JS☆11Apr 27, 2017Updated 9 years ago
- ☆16Jun 28, 2026Updated 3 months ago
- DSH（DeepSeek Harness）远程 Web 启动 + 用户名/密码认证插件。 | DeepSeek Harness Remote‑Web‑Launch Plugin with Username/Password Auth☆62Updated this week
- playing with protobuf and udp in golang☆12Apr 17, 2016Updated 10 years ago
- A set of PSScriptAnalyzer rules that help make it Good Enough!☆11Aug 26, 2026Updated last month
- 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.
- Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch,…☆27Jul 23, 2026Updated 2 months ago
- A simple dashboard for the DGX Spark.☆43Aug 8, 2026Updated 2 months ago
- Concurrency Patch to enable on DSpark - DeepSeek V4 Flash/Pro C=16 can be modified for more☆12Jun 29, 2026Updated 3 months ago
- Enterprise-ready CI/CD reference for Microsoft Foundry AI agents, with parallel GitHub Actions and Azure DevOps pipelines, evaluation-dri…☆25May 22, 2026Updated 5 months ago
- GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K context, DeepSeek Sparse Atte…☆155Jun 19, 2026Updated 4 months ago
- Run oversized sparse MoE GGUF models with bounded NVMe-to-RAM-to-VRAM caching, native multi-GPU planning, and a Linux desktop Studio.☆20Oct 12, 2026Updated last week
- Simple scripts to update Microsoft Apps via Intune for Autopilot Deployments☆13Jul 17, 2024Updated 2 years ago