Qwen 3.8 125B-A6B CUDA inference speedup benchmark: ds4 engine, overlay, and submission harness
☆15Oct 10, 2026Updated last week
Alternatives and similar repositories for cudafast-qwen38-125b-a6b-engine
Users that are interested in cudafast-qwen38-125b-a6b-engine are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fan Shroud for the Spark platform, for improved cooling performance on long workloads. Full STL/STEP files + electronics schematics☆39Sep 22, 2026Updated 3 weeks ago
- Pinned stock Qwen3.8-27B NVFP4 + DFlash2 recipe and measured evidence for one NVIDIA DGX Spark☆21Sep 10, 2026Updated last month
- Qwen3.8-27B on one DGX Spark: SGLang + DFlash2 recipe, engine image, benchmarks, data and charts. By @redp314☆37Sep 6, 2026Updated last month
- Pinned, checksum-verified GLM-5.3-Flash EXL3 K2 recipe for one NVIDIA GB10.☆38Updated this week
- Open Source Legal AI assistant for MS Word as Plugin - contract review, playbooks, drafting, and legal research task-pane add-in.☆77Oct 1, 2026Updated 2 weeks 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.
- A pure Rust implementation of Google's DiffusionGemma model☆37Sep 18, 2026Updated last month
- qwen38-flash-next recipe for solo GB10☆150Updated this week
- Java library to enable AfterBurn with OpenFaaS☆11Mar 31, 2018Updated 8 years ago
- Zero-Copy Context Bridging Gateway for Multi-Agent GPU Inference. Bypasses the expensive prefill phase by dynamically stitching KV Caches…☆22Jul 25, 2026Updated 2 months ago
- Files you own. Memory your agents can trust. Also: your AI won't gaslight you about what's in your own notes anymore.☆19Aug 26, 2026Updated last month
- 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.☆44Updated this week
- ☆15Sep 5, 2026Updated last month
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆90Oct 4, 2026Updated 2 weeks 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
- 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.
- 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
- 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
- Fay is an open-source digital human framework integrating language models and digital characters. It offers retail, assistant, and agent …☆26Apr 16, 2024Updated 2 years ago
- ☆12Jul 24, 2019Updated 7 years ago
- ☆14Nov 27, 2025Updated 10 months ago
- A HACS repo to enable Equation Integration into Home Assistant☆11Jan 7, 2025Updated last year
- CUDA Craftax-Classic: 7x faster RL training than JAX☆80Sep 10, 2026Updated last month
- Unofficial DeepSeek Harness plugin: mobile-friendly UI, Web Push notifications, and Linux Tailscale setup guide☆34Sep 29, 2026Updated 3 weeks ago
- Qwen3.8 Flash Next on one DGX Spark (TensorFold)☆285Updated this week
- 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.
- Gradio UI to load crewAI configuration from excel xls and generate the python code. The source of the crews is in the xls. It allows for …☆10Oct 17, 2025Updated last year
- DGX Spark (GB10) random hard power-off: how to diagnose the log-less crash signature and stop it with a GPU clock cap. Field-tested fix +…☆25Aug 16, 2026Updated 2 months ago
- Qwen3.8-27B on one DGX Spark (TensorFold)☆34Oct 1, 2026Updated 2 weeks ago
- AI-powered skills for financial professionals. Comprehensive collection of finance, accounting, audit, and compliance skills for AI agent…☆38Oct 1, 2026Updated 2 weeks ago
- DeepSeek v4 Flash EXL3 on one DGX Spark☆349Aug 24, 2026Updated last month
- Qwen3.8-27B ADay777-Ablit · NVFP4 · A4Q · NVFP4-KV (4M+ pool) · MTP-3 — single DGX Spark (GB10/sm121), eugr vLLM 0.27. 1M ctx @ c=4.☆24Aug 17, 2026Updated 2 months ago
- Archived standalone Browser and historical releases. Active Desktop + Browser project: ManoloRemiddi/augmentor-agent.☆29Sep 23, 2026Updated 3 weeks ago
- An open source deep research clone. AI Agent (Local LLM or Gemini) that reasons large amounts of web data extracted with SwiftSoup.☆14Feb 10, 2025Updated last year
- ☆11Feb 4, 2020Updated 6 years ago
- 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.
- E-paper waveshare 2.13 V2 Golang driver☆12Dec 24, 2020Updated 5 years ago
- Redmine's plugin to allow to assign an SLA by issue priority and project☆11Nov 28, 2019Updated 6 years ago
- Open source time-tracking application, dockerized.☆15Mar 23, 2024Updated 2 years ago
- 2x DGX Spark (GB10) running DeepSeek-V4-Flash: dual-node FP8 TP=2 (~41 tok/s single / ~350 agg), single-node ds4, a 10-model GGUF benchma…☆30Jun 16, 2026Updated 4 months ago
- Independent peer review of terrafying/ai-torture-chamber: reasoning, reproducibility, and activation steering experiments with bodily con…☆38Oct 1, 2026Updated 2 weeks ago
- A set of tools to modify and read VMU files and filetypes☆15Aug 19, 2022Updated 4 years ago
- Run MoE models bigger than your RAM, without the speed cliff☆16Updated this week