Qwen3.8-Flash-Next 180B NVFP4 @ 231 tok/s on one RTX PRO 6000 Blackwell (sm120) - sglang patches, launchers, full optimization analysis
☆30Aug 31, 2026Updated 2 months ago
Alternatives and similar repositories for sglang-flashnext-sm120
Users that are interested in sglang-flashnext-sm120 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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 …☆195Updated this week
- Personal fork of Kacper’s vLLM-Moet for DeepSeek V4 Flash on a single RTX PRO 6000. Shared for others to use; support is best-effort as t…☆18Aug 19, 2026Updated 2 months ago
- Qwen3.8-Flash-Next optimized for 1x RTX Pro 6000☆20Sep 17, 2026Updated last month
- Pi extension for Cursor models via OAuth and local gRPC proxy☆14Sep 6, 2026Updated 2 months ago
- Multi-dataset evaluation of Anthropic's J-Space on Qwen3-4B. Demonstrates that internal 'workspace noise' can reliably route high-confide…☆12Jul 13, 2026Updated 3 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- high-performance linear attention kernel library built on TileLang☆15Jun 8, 2026Updated 5 months ago
- Context Window Analyzer CLI - Understand what fills your LLM context window☆14Feb 3, 2026Updated 9 months ago
- Huggingface but for inference engines.☆14Oct 31, 2026Updated last week
- RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink☆1,197Updated this week
- Local-first, LLM-guided, coverage-driven fuzzer for network protocols and binary formats. Single Rust binary. Zero signup.☆15Jul 14, 2026Updated 3 months ago
- A lightweight, self-hosted PLM and inventory management system running on Raspberry Pi, featuring FreeCAD integration and web-based 3D vi…☆13Jul 4, 2026Updated 4 months ago
- Build AI teams that work alongside yours -- accessible from your phone.☆19Jun 20, 2026Updated 4 months ago
- Automatically adds color-code folders, tags, and your Graph View with premium palettes, and auto-assign smart icons to visualize your str…☆13Updated this week
- "Complete setup guide for multi-GPU vLLM inference on NVIDIA Blackwell RTX Pro 6000 cards with Ubuntu 24.04, CUDA 12.8, and NCCL optimiza…☆12Aug 24, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆40Aug 13, 2026Updated 2 months ago
- This repo helps to transform text into a better form for lora training☆12Apr 9, 2023Updated 3 years ago
- ☆31Aug 28, 2026Updated 2 months ago
- Speculative Decoding Implementations: MTP, EAGLE-3, Medusa-1, PARD, Draft Models, N-gram and Suffix Decoding from scratch☆15May 2, 2026Updated 6 months ago
- Generate and execute fuzzing campaign commands for AFL++ based on the recommended multi-core secondary fuzzer options.☆11Jan 12, 2024Updated 2 years ago
- Generates kid-friendly weather forecasts suitable for display on a large monitor. Uses OpenWeatherMap and a local or hosted LLM.☆17Feb 28, 2026Updated 8 months ago
- A self-hosted control plane for a DGX Spark GPU cluster: provision nodes over SSH or a join token, deploy and serve inference behind one …☆13Oct 23, 2026Updated 2 weeks ago
- A web frontend for managing an EmpyrionServer (similar to the EAH), as a MOD so that it can also be used seemless in game hosting.☆24Aug 3, 2026Updated 3 months ago
- Qwen3.8-Flash-Next (176B MoE) on a single RTX PRO 6000 Blackwell 96GB — NVMe-streamed PLE table, CUDA graphs with NEXTN speculation, meas…☆10Aug 28, 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.
- An independent Android client for Hermes Agent servers☆18Oct 29, 2026Updated last week
- Terminal system monitor (TUI) that builds its layout from the hardware it actually finds — hybrid CPU clusters, GPUs, RDMA/RoCE NICs, PCI…☆17Updated this week
- A bare minimum deployment of guardrails as a service.☆12Aug 13, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash (764B) on 4×CMP 170HX: PP4 + shadow KV + EXL3 2bpw + DSpark + 512k ctx + native vision — patches, recipes, acceptance…☆15Sep 29, 2026Updated last month
- Output high level Pcode (PcodeAST) in Ghidra☆18Apr 7, 2023Updated 3 years ago
- ☆12Aug 31, 2026Updated 2 months ago
- Fuzzing Infrastructure with k8s & cephfs☆12Jul 23, 2020Updated 6 years ago
- Node-based visual programming environment☆15Nov 12, 2024Updated last year
- ☆11Dec 9, 2022Updated 3 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.
- ☆22Jul 2, 2026Updated 4 months ago
- Production-ready academic PDF processor that extracts metadata and structured JSON from research papers. Designed as a plug-and-play modu…☆23Updated this week
- Harn is a programming language and runtime for building AI agents.☆29Updated this week
- Files related to the SKR Mini E3 v2.0☆10Jun 16, 2020Updated 6 years ago
- 3D printer laser adapter☆10Dec 22, 2023Updated 2 years ago
- Docker that queries Starlinks Dishy and serves you the response on it's own web server☆12Nov 6, 2021Updated 5 years ago
- keys-DGX-Sparkticus Utimate Power Pack Unleashed (Dual DGX-Sparks Needed)☆43Aug 23, 2026Updated 2 months ago
Are these results useful?