DSpark-style speculative decoding draft head for Qwen3.6-27B AEON: training recipe, paired eval harness, vLLM patches. +11% serve tok/s vs DFlash (all domains, CI'd).
☆15Jul 2, 2026Updated 3 months ago
Alternatives and similar repositories for dspark-aeon-27b
Users that are interested in dspark-aeon-27b are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Uncensored Qwen3.8-27B Ultimate - BF16 master + NVFP4-MIXED deploy. QuickStarts for DGX Spark (one Dynamic DFlash lattice seat @ util 0.8…☆20Oct 6, 2026Updated 2 weeks ago
- Universal AI computer-control KVM (REST API + MCP) that drives any machine as plain USB hardware — nothing installed on the target. Built…☆20Oct 6, 2026Updated 2 weeks ago
- Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audi…☆25Oct 6, 2026Updated 2 weeks ago
- ☆16Jun 28, 2026Updated 3 months ago
- Run on TWO-DGX-Spark - vLLm-0.24.0 dual cache optimized DSV4F+DSpark+NVFP4 KV (Concurrency 12 with 1.5M context/3M KV token Pool) >0.58-0…☆21Aug 17, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Spec-first rails for agent-assisted repository workflows.☆23Oct 16, 2026Updated last week
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆24Aug 17, 2026Updated 2 months ago
- DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)☆31Aug 3, 2026Updated 2 months ago
- Hikari's curated English measured notes on local LLM systems (serving, specdec, training, steering).☆14Jul 29, 2026Updated 2 months ago
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆12Oct 13, 2026Updated last 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
- Self-hosted vLLM inference for Qwen3.6-35B-A3B-NVFP4☆32Jul 11, 2026Updated 3 months ago
- NVFP4 KV cache for vLLM on SM120 (RTX PRO 6000) via FlashInfer FA2 explicit-SF-stride patch — ~1.5x fp8 pool at ~95-104% speed☆20Jun 5, 2026Updated 4 months ago
- Experimental runtime reclamation of GB10 display-reserved memory into ordinary Linux RAM, with guarded driver, local signing, and reboot …☆11Sep 27, 2026Updated 3 weeks ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Security capability evaluation of locally served models. Method, corpus, and per-model results.☆18Updated this week
- A small Node.js script that polls a website and sends a notification when there's a change. Inspired by my attempts to get a close hotel …☆13Nov 10, 2022Updated 3 years ago
- Fermion Research fork of llama.cpp: FV5/FV5B five-value ternary types for Neutrino GGUF packs (CPU + CUDA)☆14Sep 29, 2026Updated 3 weeks ago
- World's first TurboQuant KV cache compression for llama.cpp on AMD ROCm (RX 9070 / gfx1201)☆21Apr 28, 2026Updated 5 months ago
- Notification integration for SimpleX messenger☆23Updated this week
- Herdr 软件全面调研、使用价值分析与上手教程 | An independent practical guide to Herdr☆26Aug 10, 2026Updated 2 months ago
- ☆13Aug 5, 2026Updated 2 months ago
- ☆23Aug 18, 2026Updated 2 months ago
- Three-DGX-Spark TP3 serving recipe for GLM-5.3 Flash☆19Oct 5, 2026Updated 2 weeks 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.
- DGX Spark EC fan speed override / rollback tool☆20Aug 23, 2026Updated 2 months ago
- 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 3 weeks ago
- Validated vLLM recipe: Qwen3.8-27B-NVFP4 at full 262,144-token context on a single RTX 5090, GPU-only (no CPU offload).☆16Aug 20, 2026Updated 2 months ago
- Build, load, and verify NCCL for switchless DGX Spark RoCE cycles☆18Sep 25, 2026Updated 3 weeks ago
- Tiny node module of utilities for working with waveforms in the browser. Depends on pcm.js and ffprobe.js.☆12Apr 22, 2013Updated 13 years ago
- AWS SAM Lambda and SQS demo☆11Jun 27, 2018Updated 8 years ago
- Give the DeepSeek Harness (dsh) eyes with any text model + any vision model: a vision proxy for chat image attachments and an analyze_ima…☆12Sep 28, 2026Updated 3 weeks ago
- Hermes Agent benchmark v0.1 — evaluate local models on the actual tool-calling patterns Hermes users hit. Reproducible, trace-capturing, …☆17Jun 24, 2026Updated 4 months ago
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆86Oct 6, 2026Updated 2 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆16Jul 21, 2026Updated 3 months ago
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆172Oct 13, 2026Updated last week
- Get file information based on file signature☆16Sep 11, 2015Updated 11 years ago
- LLM inference in C/C++☆24Updated this week
- Bigger local AI on the PC you already own. Find models, chat locally, and run supported sparse models across SSD, RAM and NVIDIA GPUs wit…☆21Updated this week
- Full GLM-5.3 (753B) served by TensorFold with tensor parallel 4 across four NVIDIA DGX Sparks: results, recipe, node settings, benches☆21Oct 13, 2026Updated last week
- React AWS S3 upload using Amplify and Material UI☆10Jan 5, 2023Updated 3 years ago