Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell 96 GB GPU (SM120): 524K context, HiCache and NIXL.
☆165Oct 17, 2026Updated this week
Alternatives and similar repositories for sglang-rtxpro6000
Users that are interested in sglang-rtxpro6000 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 V4.1 Flash on 4x RTX PRO 6000 Blackwell: native weights, DSpark, vision, NVMe or locked RAM Engram offload.☆67Updated this week
- thinkingbox is a framework for defining tool as MCP servers, running LLM agents against them, and evaluating agent behavior — for offline…☆103Updated this week
- 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
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆87Updated this week
- LLM inference in C/C++☆56Aug 8, 2026Updated 2 months 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.
- C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer☆121Updated this week
- Mayonnaise: a macOS like UI library for Linux, alternative to Qt and GTK. Written with pure C++ and OpenGL/Vulkan.☆50Updated this week
- Self-improving Codex loop: DeepSeek runs the task, Luna grades it, Sol rewrites the prompt until it is done☆47Sep 16, 2026Updated last month
- An open source MCP proxy.☆18Jan 3, 2025Updated last year
- Faster inference backend for Open-Jev-27B: fused CUDA kernels, prefix tree, CUDA Graphs (B300, bf16)☆91Sep 28, 2026Updated 2 weeks ago
- Your agent swarm as a live DAG: an orchestration graph with attempts, review gates, and evidence, in a herdr split pane.☆107Aug 23, 2026Updated last month
- Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith …☆187Updated this week
- One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, pa…☆363Sep 26, 2026Updated 3 weeks ago
- Step-by-step guide: Qwen3.6 27B/35B on RTX PRO 6000 Blackwell — 120-200 tok/s with vLLM + MTP n=3☆23Aug 4, 2026Updated 2 months 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.
- KiCad 10 plugin that simulates the S-parameters of an RF structure directly in the PCB editor, with the openEMS FDTD solver.☆104Updated this week
- upmd - Run tasks and workflows from Markdown.☆279Updated this week
- Serverless peer-to-peer voice and text chat for your terminal. No accounts or central server. Peers connect directly over encrypted QUIC.☆212Oct 10, 2026Updated last week
- A high level pool for maintaining pools of *sql.DB databases (e.g: thousands of SQLite files)☆10Oct 29, 2016Updated 9 years ago
- ☆21Updated this week
- Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.☆212Updated this week
- ☆24Dec 29, 2025Updated 9 months ago
- Adds size optimizations to any Perseus app automatically.☆10Apr 20, 2022Updated 4 years ago
- People and organisations pool their own machines over Yggdrasil to keep files, websites, email for their own domains and messaging for al…☆40Updated this 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.
- filesharing for the meatspace era☆212Updated this week
- ☆27Updated this week
- Lokal Webpack Plugin, works with NextJS and all webpack-based dev server.☆15Aug 12, 2024Updated 2 years ago
- Claude Code, Codex and Pi write down everything you do. bough draws it and prices it: a day, the work inside it, every prompt, and what e…☆124Updated this week
- Run a command once, reuse its output for a while.☆179Oct 8, 2026Updated last week
- A Terminal Markdown editor that stays rendered while you edit☆57Updated this week
- ☆12Feb 4, 2023Updated 3 years ago
- SubmitQueue is a high-performance speculative merge queue that keeps your trunk consistently green at scale.☆237Updated this week
- ☆70Updated this week
- 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.
- Define complex workflows with the saga pattern on top of graphile-worker☆12Feb 28, 2024Updated 2 years ago
- ☆11Jan 7, 2026Updated 9 months ago
- Nimic allows using pure Python as a systems language with AOT compilation. It provides systems-level functionality directly within CPytho…☆42Updated this week
- Add geo functionality extension to datafusion query engine.☆12Apr 26, 2024Updated 2 years ago
- DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe☆220Sep 24, 2026Updated 3 weeks ago
- DX Kit which blurs the line between the code editor and the project.☆11Aug 20, 2016Updated 10 years ago
- Streaming and async template rendering for node.js using template strings☆13Sep 25, 2023Updated 3 years ago