☆120Aug 6, 2026Updated 2 months ago
Alternatives and similar repositories for nccl-mesh-plugin
Users that are interested in nccl-mesh-plugin are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- First Int4-Int8Mix quantization of the full GLM-5.3 (743B), served on 4x NVIDIA DGX Spark (GB10) at TP4. Quantizer, verification gates, a…☆20Oct 6, 2026Updated 3 weeks ago
- A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively☆128Feb 22, 2026Updated 8 months ago
- English guide + one-command patcher for the vLLM spin-wait bug that overheats NVIDIA DGX Spark / GB10. Credit: nacyot. CPU cores spin at …☆24Aug 17, 2026Updated 2 months ago
- method of training mamba for reasoning☆11Updated this week
- ☆11May 29, 2026Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A proof of concept model based on Llama 3.1-8B, featuring reasoning capabilities in Bulgarian.☆12Feb 9, 2025Updated last year
- antirez/ds4-style hybrid quant DeepSeek V4 Flash on a single DGX Spark via vLLM☆17May 11, 2026Updated 5 months ago
- Experimental runtime reclamation of GB10 display-reserved memory into ordinary Linux RAM, with guarded driver, local signing, and reboot …☆12Oct 23, 2026Updated last week
- Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors e…☆105Updated this week
- A self-hosted control plane for a DGX Spark GPU cluster: provision nodes over SSH or a join token, deploy and serve inference behind one …☆13Oct 23, 2026Updated last week
- Local-first RAG application for technical documentation and research papers☆28Updated this week
- Terminal system monitor (TUI) that builds its layout from the hardware it actually finds — hybrid CPU clusters, GPUs, RDMA/RoCE NICs, PCI…☆17Aug 1, 2026Updated 3 months ago
- Docker configuration for running VLLM on dual DGX Sparks☆2,468Updated this week
- Two-node DGX Spark/ASUS GX10 DeepSeek V4 Flash DSpark NVFP4 port for vLLM 0.25, with live dashboard and reproducible deployment.☆83Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Zoof is a high-efficiency Small Language Model (SLM) engineered from scratch. It demonstrates how modern architectural choices and high-q…☆48Jan 13, 2026Updated 9 months ago
- ☆19Oct 25, 2025Updated last year
- Full GLM-5.3 (753B, Int4-Int8Mix) on 4x NVIDIA DGX Spark, vLLM TP4☆23Oct 13, 2026Updated 2 weeks ago
- Walls of Excellence (woe) is a mono repository for my home infrastructure and Kubernetes cluster which adheres to Infrastructure as Code …☆14Updated this week
- A PyTorch implementation of gradient-free optimization for directly optimizing NDCG (Normalized Discounted Cumulative Gain) in neural inf…☆19Dec 21, 2025Updated 10 months ago
- Software for miniVNA☆10Apr 17, 2016Updated 10 years ago
- ☆75Feb 27, 2026Updated 8 months ago
- Docker compose serving stack for DeepSeek v4 Flash DSpark for NVIDIA Spark GB10 system using Aidendle94 image☆33Aug 30, 2026Updated 2 months ago
- ☆18Jul 1, 2025Updated last year
- 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.
- SrvDB: open-source embedded vector database for Python & Rust. Local semantic search, RAG and AI memory with no server. Crash-safe, offli…☆15Oct 26, 2026Updated last week
- A local, multimodal embedding server and vector database using NVIDIA's Omni-Embed-Nemotron-3B. This project allows you to generate embed…☆11Nov 27, 2025Updated 11 months ago
- (trying to) train llama2 7B fast☆10Oct 14, 2025Updated last year
- Working recipe: MiniMax-M3 NVFP4 at tensor-parallel 3 across 3x DGX Spark (GB10/sm_121) with clean tool-calling. Includes the head-node O…☆16Jul 13, 2026Updated 3 months ago
- ☆35Feb 6, 2026Updated 8 months ago
- GRAVE is a professional-grade volatile retention format for data you have chosen to let go.☆17Jul 30, 2026Updated 3 months ago
- The Python Implementation of CRISP: Clustering Multi-Vector Representations for Denoising and Pruning☆27Jul 27, 2025Updated last year
- A curated list of tools, guides, playbooks, and resources for the NVIDIA DGX Spark (GB10 Grace Blackwell personal AI supercomputer).☆95Oct 22, 2026Updated last week
- "Pacha" TUI (Text User Interface) is a JavaScript application that utilizes the "blessed" library. It serves as a frontend for llama.cpp …☆37Aug 3, 2023Updated 3 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆14Dec 6, 2023Updated 2 years ago
- ☆11Sep 18, 2023Updated 3 years ago
- llama-benchy - llama-bench style benchmarking tool for all backends☆767Jul 10, 2026Updated 3 months ago
- Bridge your Antigravity IDE usage/quota to Cursor IDE and other OpenAI-compatible tools. A local proxy server that converts Antigravity C…☆14Jan 4, 2026Updated 9 months ago
- ☆12May 30, 2025Updated last year
- Boot straight into AI. UEFI application — no OS required.☆17Updated this week
- Research MIL-to-HWX compiler for the M4 Apple Neural Engine☆17Sep 3, 2026Updated last month