The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 100+ tok/s single-request decode with support of FP8 weight ( Join Discord //discord.gg/VFqVVySdMS )
☆814Sep 4, 2026Updated this week
Alternatives and similar repositories for vLLM-2080Ti-Definitive
Users that are interested in vLLM-2080Ti-Definitive are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆154Jun 13, 2026Updated 2 months ago
- LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features …☆452Sep 1, 2026Updated last week
- Flash Attention 2 implementation for Turing GPUs☆125Mar 23, 2026Updated 5 months ago
- Lightweight multi-agent orchestration engine☆14Jul 1, 2026Updated 2 months ago
- ML software (llama.cpp, ComfyUI, vLLM) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆335Aug 30, 2026Updated last week
- 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.
- Sage attention for turning.☆80Dec 29, 2025Updated 8 months ago
- Patched native-Windows build of vLLM. Three Windows-specific fixes (CPU-relay for Gloo, Qwen3 reasoning parser, wildcard model name) on t…☆27May 8, 2026Updated 3 months ago
- 大语言模型工具集☆28Aug 1, 2025Updated last year
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations☆19,478Updated this week
- vLLM for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆434Feb 20, 2026Updated 6 months ago
- NVIDIA Linux open GPU with P2P support☆500Updated this week
- fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tp…☆4,972Updated this week
- 加载使用TileStache（谷歌瓦片规则）切割出的矢量瓦片实例☆12Sep 18, 2019Updated 6 years ago
- forked from vllm-project/flash-attention☆64May 9, 2026Updated 3 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.
- One-KVM，结合廉价硬件和PiKVM，实现低成本远控方案。☆10Sep 6, 2024Updated 2 years ago
- onecloud's u-boot, build by yourself.☆19Jan 8, 2025Updated last year
- vllm混合推理扩展插件，支持多NUMA混合推理，单卡推理Qwen3-Next模型可达1000+ prefill☆34Nov 7, 2025Updated 10 months ago
- 生成中文文字识别（OCR）的训练数据☆12Mar 2, 2020Updated 6 years ago
- MT5 factor mining, backtest, and web training UI☆577Updated this week
- Fork of turbo quant tom-tom and TurboQuant KV cache from domwox☆31Jul 7, 2026Updated 2 months ago
- ☆12Mar 21, 2024Updated 2 years ago
- 零依赖体感：用户安装一个桌面包即可，不需要先手动装一堆 CLI 和环境。 离线友好：安装包内置 OpenClaw 离线载荷，弱网/无外网场景也能 完成初始化。 跨平台交付：统一产出 macOS / Windows / Linux 安装包。☆86May 6, 2026Updated 4 months ago
- 基于vercel Serverless Functions搭建的无服务xss平台☆22Oct 29, 2024Updated last year
- 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.
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆80Jul 14, 2026Updated last month
- yolov7-pose end2end TRT实现☆27Sep 8, 2022Updated 3 years ago
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆131Updated this week
- 自动化控制、可视化操作、自动连点器、流程自动化、RPA☆70Aug 10, 2026Updated 3 weeks ago
- 使用Python线上打包Android项目apk☆12Jun 30, 2017Updated 9 years ago
- rtmp/rtsp Qt Media☆21Jul 14, 2026Updated last month
- Unofficial DomoAI API☆27Jul 1, 2024Updated 2 years ago
- LLM inference in C/C++☆2,356Updated this week
- On cloud or premise, the AutoML controller for DeepCamera☆13Sep 1, 2022Updated 4 years 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.
- 基于janus-gateway实现的流媒体服务器。☆11May 15, 2024Updated 2 years ago
- 设备注册中心redis实现☆11Oct 18, 2019Updated 6 years ago
- 使用Python脚本实现360加固后一键V2签名和Walle打出渠道包☆18Dec 11, 2017Updated 8 years ago
- Pytorch implementation of an Hourglass network for corner detection of a wrinkled towel.☆15Nov 30, 2020Updated 5 years ago
- web在线答题☆11Aug 14, 2018Updated 8 years ago
- Cloud Optimized GeoTiff utility tools (create validate)☆11Sep 20, 2019Updated 6 years ago
- LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key …☆36,770Jan 9, 2026Updated 7 months ago