Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE
☆151Oct 16, 2026Updated last month
Alternatives and similar repositories for pd-bridge
Users that are interested in pd-bridge are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Metal Cuda Direct Memory Access☆213Nov 1, 2026Updated 2 weeks ago
- Wrap commands that might cause out-of-memory errors, and stop them before they freeze your machine☆15Sep 22, 2026Updated last month
- Serve LibertAIDAI/GLM-5.3-Flash-NVFP4 on 2x NVIDIA DGX Spark (GB10) with patched vLLM TP=2, 262k context, MTP-4.☆21Nov 2, 2026Updated 2 weeks 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 3 months ago
- GLM-5.3 Flash EXL3 for 2-4x DGX Sparks☆762Nov 4, 2026Updated 2 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Recover usable memory on DGX Spark with a 64 KiB kernel: an opt-in NVIDIA UVM page-table packing patch, build tools, and measured validat…☆40Oct 16, 2026Updated last month
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆99Nov 12, 2026Updated last week
- GLM-5.2 QuantTrio TP=4+DCP2 on 4x NVIDIA DGX Spark (GB10) — tuned and measured under a real agent workload. Adaptive MTP, the indexer law…☆20Aug 24, 2026Updated 2 months ago
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,519Oct 4, 2026Updated last month
- 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 …☆58Oct 10, 2026Updated last month
- GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆126Oct 30, 2026Updated 2 weeks ago
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆905Updated this week
- Model-agnostic LLM benchmarking + tuning in one command. A model is a 15-key profile file. Built in production on a 4x NVIDIA DGX Spark c…☆10Sep 16, 2026Updated 2 months ago
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆78Oct 26, 2026Updated 3 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe☆112Oct 25, 2026Updated 3 weeks ago
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆641Oct 4, 2026Updated last month
- LLM Engine for DGX Spark☆27Updated this week
- LLM Inference Engine for Metal, CUDA and Vulkan.☆2,322Updated this week
- DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks☆284Sep 19, 2026Updated last month
- Local image generation and editing for NVIDIA DGX Spark, powered by Qwen-Image-2.1 and Gradio.☆34Sep 21, 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☆99Updated this week
- Give DeepSeek V4 Flash eyes. OpenAI-compatible shim + tiny local VLM. Point any harness at one URL and your text-only model accepts image…☆30Aug 9, 2026Updated 3 months ago
- GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold☆535Nov 4, 2026Updated 2 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.
- ☆820Updated this week
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆167Sep 3, 2026Updated 2 months ago
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆108Aug 20, 2026Updated 2 months ago
- Agent-ready two-node DGX Spark recipe for DeepSeek V4 Flash plus an optional Qwen Vision sidecar, with generic OpenAI-compatible, Hermes,…☆23Aug 10, 2026Updated 3 months ago
- qwen38-flash-next recipe for tp=2 GB10☆135Oct 29, 2026Updated 2 weeks ago
- Qwen3.8 27B on SGLang for DGX Spark☆484Sep 12, 2026Updated 2 months ago
- Claude Code ZeroClaw Pro 2026: AI Multitool & CLI Router for Claude SDK Subagents☆52Updated this week
- Eight-system DGX Spark engineering: fabric repair, NCCL tuning, rack recabling, custom 3D-printed PSU supports, and thermal validation.☆11Aug 3, 2026Updated 3 months ago
- Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Spe…☆56Sep 29, 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.
- 3D models for DGX cases☆55Aug 14, 2026Updated 3 months ago
- Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.☆70Sep 2, 2026Updated 2 months ago
- GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spe…☆65Nov 4, 2026Updated 2 weeks ago
- Cap the GPU clock on NVIDIA DGX Sparks across all your machines, persistently☆111Nov 9, 2026Updated last week
- Honeycomb Lab — hex map + OpenAI gateway control plane for a home AI fleet☆17Oct 26, 2026Updated 3 weeks ago
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆419Sep 29, 2026Updated last month
- Local model hosting with 2x DGX Sparks☆12Aug 29, 2026Updated 2 months ago
Are these results useful?