W4A4 full（VLLM_MOE_W4A4=2）+ （VLLM_B12X_SHARED_WRAPPER=1）+ FlashInfer 0.6.16 + threshold 4096 + util 0.78 + DSpark MTP n7 + CUMEM=0
☆16Aug 26, 2026Updated 2 months ago
Alternatives and similar repositories for LuZ0.3.1-DeepSeek-v4-Flash-DSpark-DGXspark-TP4-Ring
Users that are interested in LuZ0.3.1-DeepSeek-v4-Flash-DSpark-DGXspark-TP4-Ring are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepSeek V4 Flash DSpark DGX Spark TP4 Ring 生产调优与算子工程归档 (LuZ0.4.5)☆17Sep 11, 2026Updated last month
- DeepSeek-V4.1-Flash on 4x DGX Spark TP4 switchless RoCE ring - SGLang production recipe, 600K context, DSpark MTP, benchmark archive☆29Oct 1, 2026Updated 3 weeks ago
- GLM-5.3-Flash NVFP4 on 4x NVIDIA DGX Spark: vLLM TP4, DFlash2 adaptive draft, measured FP8 vs NVFP4 vs EXL3 vs SGLang☆39Sep 29, 2026Updated last month
- Tuned TP4 serving profile for DeepSeek-V4.1-Flash on 4x NVIDIA DGX Spark (SGLang, DSpark), built on the MiaAI-Lab recipe☆81Updated this week
- Full GLM-5.3 (753B, Int4-Int8Mix) on 4x NVIDIA DGX Spark, vLLM TP4☆22Oct 13, 2026Updated 2 weeks 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.
- glm53-flash recipe for tp=2 GB10☆10Oct 19, 2026Updated last week
- Low-latency collective transport and distributed LLM serving stack for switchless GB10 clusters.☆101Oct 19, 2026Updated last week
- keys-DGX-Sparkticus Utimate Power Pack Unleashed (Dual DGX-Sparks Needed)☆43Aug 23, 2026Updated 2 months ago
- First Int4-Int8Mix quantization of the full GLM-5.3 (743B), served on 4x NVIDIA DGX Spark (GB10) at TP4. Quantizer, verification gates, a…☆19Oct 6, 2026Updated 3 weeks ago
- Full GLM-5.3 (753B) served by TensorFold with tensor parallel 4 across four NVIDIA DGX Sparks: results, recipe, node settings, benches☆20Oct 13, 2026Updated 2 weeks ago
- GLM-5.3-Flash (FP8) + DFlash2 speculative decoding on 4x NVIDIA DGX Spark / ASUS GX10: vLLM TP4, 256K context, switchless ConnectX-7 ring…☆31Oct 1, 2026Updated 3 weeks ago
- DeepSeek-V4.1-Flash on 3-4x NVIDIA DGX Sparks☆276Oct 17, 2026Updated last week
- DeepSeek-V4.1-Flash EXL3 vLLM recipe for 2x DGX Spark (GB10)☆29Sep 27, 2026Updated last month
- Qwen-Image 2.1 on TensorFold's NVFP4 kernels: a drop-in ComfyUI loader, 4x faster than the GGUF path on one RTX 5070 Ti (native Windows).…☆12Oct 3, 2026Updated 3 weeks 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.
- LilyGo T-Dongle-S3☆22Jul 16, 2024Updated 2 years ago
- DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.☆125Sep 16, 2026Updated last month
- ☆21Aug 7, 2026Updated 2 months ago
- Alpha 因子挖掘系统 v3.0 — 模块化自动化因子挖掘平台 (表达式/遗传编程/深度学习三模式, A股+美股, CLI+Streamlit+Notebook)☆20Jun 25, 2026Updated 4 months ago
- ☆16May 2, 2026Updated 5 months ago
- NEW [🔥 updating...]LLM 驱动的股票量化因子挖掘与交易平台，现在支持MCP接入Codex、Claude Code。支持A股:多 Agent + 公式化挖掘、Qlib 回测、Web 门户、日频信号、Telegram/飞书 通知。☆30Updated this week
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,496Oct 4, 2026Updated 3 weeks ago
- ☆17Aug 16, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash on two NVIDIA DGX Sparks: EXL3 weights from the official checkpoint, upstream vLLM with our patches and decode kernel…☆45Oct 22, 2026Updated last 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.
- 行星摆线减速器☆16Jun 15, 2024Updated 2 years ago
- Image processing Projects in OpenCV☆11Nov 15, 2015Updated 10 years ago
- go zerocopy.Reader interface and implementation☆13Jun 15, 2014Updated 12 years ago
- NONMEM 7.4.3, 7.5.0, 7.6.0的Docker镜像，适合Windows, macOS, Linux☆15Jun 6, 2026Updated 4 months ago
- 根据代码自动生成文档和教程的AI☆15Apr 30, 2023Updated 3 years ago
- protobuf二进制协议映射到消息处理接口的一种实现方式☆13Feb 11, 2017Updated 9 years ago
- GLM-5.3-Flash (320B MoE) at TP4 across four DGX Sparks, same day as the model drop: 36 tok/s, 1.26M-token FP8 KV pool, 262K context, MTP …☆57Oct 10, 2026Updated 2 weeks ago
- 使用腾讯云通讯IM实现的小程序直播间demo☆12May 16, 2018Updated 8 years ago
- Preview release of a unified serving engine, built for the fastest FastH3 serving.☆28Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Serving 4-bit Qwen3.8-27B on a single DGX Spark (GB10): 75 tok/s single-stream, 246 tok/s aggregate at 8-way concurrency. NVFP4 vs MixedI…☆51Sep 29, 2026Updated 3 weeks ago
- Reproducible LLM inference on four NVIDIA DGX Spark (GB10) nodes wired as a direct switchless ConnectX ring — serving profiles, ring laun…☆20Oct 2, 2026Updated 3 weeks ago
- 基于Yii2.0框架模仿打造京东电商平台☆11Mar 12, 2017Updated 9 years ago
- 油猴脚本~还你一个更好用的知乎☆16Feb 22, 2023Updated 3 years ago
- [TPAMI'22] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving, [CVPR'21] Multi-Modal Fusion Transformer fo…☆15Sep 14, 2022Updated 4 years ago
- 一个让你更方便刷题的工具 Leetcode Assistant☆15May 4, 2024Updated 2 years ago
- LLM fine-tuning with LoRA + NVFP4/MXFP8 on NVIDIA DGX Spark (Blackwell GB10)☆22Dec 22, 2025Updated 10 months ago