Low-latency collective transport and distributed LLM serving stack for switchless GB10 clusters.
☆94Oct 16, 2026Updated this week
Alternatives and similar repositories for sparkring
Users that are interested in sparkring 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) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe☆106Updated this week
- vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2☆67Sep 30, 2026Updated 2 weeks ago
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆410Sep 29, 2026Updated 2 weeks ago
- Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quan…☆135Updated this week
- Optimized inference for the DGX Spark and spark clusters☆120Updated this week
- 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.
- Convert and Run Exl3 format LLM quant on Apple Silicon.☆58Aug 24, 2026Updated last month
- 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
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆90Oct 4, 2026Updated last week
- Best-of-N coding agents with LLM-as-a-Verifier selection for Oh My Pi: isolated git worktrees, verifier-ranked trajectories, winner-only …☆73Oct 1, 2026Updated 2 weeks ago
- Metal Cuda Direct Memory Access☆196Updated this week
- Serve EXL3 (ExLlamaV3 trellis) quantized models on vLLM fork runtimes — any architecture, mixed per-layer bitrates, composable with sourc…☆26Updated this week
- A declarative synchronization tool for managing cloud DNS records.☆11Sep 3, 2018Updated 8 years ago
- A utility to verify rpm and yum databases.☆11Jun 21, 2018Updated 8 years ago
- ☆10Apr 16, 2020Updated 6 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,463Oct 4, 2026Updated last week
- Conformance and capability test suite for LLM inference engines — surface coverage, spec conformance, model capability, and an MTP/perfor…☆49Oct 5, 2026Updated last week
- DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.☆126Sep 16, 2026Updated last month
- Dart boltz client☆11Sep 9, 2026Updated last month
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆166Sep 3, 2026Updated last month
- Go project template for Foreign Data Wrappers for PostgreSQL☆18Jan 7, 2019Updated 7 years ago
- Capping GPU clocks on NVIDIA GB10: -12C peak temp, -36% GPU power, ~1.6% throughput cost. Measurement harness, raw data, and the systemd …☆77Jul 31, 2026Updated 2 months ago
- Find your memory Timings of a Ryzen Zen2+ cpu under linux!☆13Sep 26, 2026Updated 3 weeks ago
- Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE☆151Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The Ecosystem of Monero☆14Mar 7, 2025Updated last year
- work in progress - funded by FlipStarter and BCH☆11Dec 3, 2024Updated last year
- ☆12Feb 1, 2021Updated 5 years ago
- A web animation library built for Go.☆31Dec 19, 2016Updated 9 years ago
- Runtime-agnostic container library for Rust on macOS and Linux☆66Updated this week
- Lightning node (service) for mercury wallet☆10Jun 16, 2023Updated 3 years ago
- Humane Teams at Home and Around the World☆12Nov 3, 2017Updated 8 years ago
- A Bip352 silent payment wallet which runs as daemon. Written in GO.☆18Aug 14, 2025Updated last year
- GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold☆450Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Ansible project to create and maintain public Monero nodes on virtual private servers.☆10May 1, 2021Updated 5 years ago
- ☆15Sep 30, 2026Updated 2 weeks ago
- Shared test infrastructure for the AWS cloud provider repositories☆19Oct 7, 2026Updated last week
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆703Updated this week
- PigeonEye is a fast, native Kubernetes GUI + CLI Tool☆60Oct 6, 2026Updated last week
- A lightweight, in-process sandbox for safely executing the tool calls an AI agent requests☆44Sep 10, 2026Updated last month
- Standalone rendezvous server: https://github.com/libp2p/specs/blob/master/rendezvous/README.md☆17Mar 13, 2023Updated 3 years ago