The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 200+ tok/s single-request decode with support of FP8 weight ( Join Discord //discord.gg/VFqVVySdMS )
☆1,173Oct 1, 2026Updated 3 weeks ago
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:
- Single-request LLM serving recipes, patches, and benchmarks for modified RTX 2080 Ti 22GB / SM75 systems☆93Jun 10, 2026Updated 4 months ago
- ☆59Sep 26, 2026Updated 3 weeks ago
- 这是一套 MiniMax H3 本地部署与性能优化整理：在 4 张 22 GB RTX 2080 Ti 上，通过 Raylight FSDP/USP、双组NVLink、多卡 Qwen 文本编码节点、SM75 SageAttention 和通信流水，让MiniMax H3 的…☆23Aug 12, 2026Updated 2 months ago
- 一个Turing专用vLLM分支，通过整合FlashInfer 0.6.18（PR #3526）与SM75后端门槛补丁（PR #47949），持续同步vLLM主线最新版本☆34Oct 11, 2026Updated last week
- Local LLM Inference Speed Test Tool☆244Updated this 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.
- V100 / SM70-focused vLLM engineering fork for modern LLM inference.☆1,380Updated this week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,142Updated this week
- LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features …☆471Sep 22, 2026Updated last month
- KVMem virtualizes KV memory across inference backends to make ultra-long-context local AI accessible on limited hardware.☆1,136Updated this week
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆31,018Updated this week
- Run MoE models beyond VRAM on AMD, NVIDIA & Intel GPUs. Vulkan-powered, portable Windows app with automatic setup. | 让游戏显卡跑起超显存大模型，支持 AMD…☆327Updated 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…☆5,116Updated this week
- Qwen3.8-27B INT8 + DFlash2 on a rented CMP 170HX — failure analysis (private GHCR image prevented benchmark)☆17Aug 30, 2026Updated last month
- 双 SM80 / CMP 170HX 的 Qwen3.8-Flash-Next 社区 vLLM：NVIDIA NVFP4、GDS、TEP2、MTP6，支持 1～10 并发，词表与 PCIe 通信优化。中英文部署与可构建源码。☆28Oct 15, 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.
- ☆151Jun 13, 2026Updated 4 months ago
- Sage attention for turning.☆84Dec 29, 2025Updated 9 months ago
- Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parall…☆157Updated this week
- Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop ker…☆33Aug 29, 2026Updated last month
- Superseded by github.com/poisonxa16/pxa — PXA, the set-and-forget engine for Pascal and Volta☆24Sep 8, 2026Updated last month
- SGLang for cool dudes using V100☆80Oct 5, 2026Updated 2 weeks ago
- ML software (llama.cpp, ComfyUI, Strata, Maya, ...) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆357Updated this week
- Flash Attention 2 implementation for Turing GPUs☆130Sep 14, 2026Updated last month
- Inference engine for large language models on consumer GPUs, with deep optimization for older hardware☆55Updated this week
- 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.
- The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; bench…☆88Updated this week
- 解锁自有 NVIDIA CMP 170HX / 90HX 的算力限制。Linux x86-64，需要 root。☆57Aug 6, 2026Updated 2 months ago
- High-performance Duo-V100-GPU inference for selected model checkpoints and GPUs.☆31Oct 14, 2026Updated last week
- NInfer-4090: NInfer inference engine ported to RTX 4090 (sm_89) with YaRN support for Qwen3.8-27B☆29Oct 2, 2026Updated 3 weeks ago
- Run MiniMax H3 at native fp16 on pre-bf16 GPUs (V100/Volta) — exact-math fix for the black-frame overflows, ~11× faster than the fp32 fal…☆55Aug 8, 2026Updated 2 months ago
- A tool to unlobotomize your NVIDIA card!☆782Oct 8, 2026Updated 2 weeks ago
- MiniMax H3 video generation on 2080Ti 22G (Turing sm_75) - field-tested handbook, workflows & FAQ☆19Updated this week
- NVIDIA Linux open GPU with P2P support☆37Oct 12, 2026Updated last week
- High-performance Triton backend for NVIDIA Turing (SM75) GPUs.☆50Sep 27, 2026Updated 3 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.
- FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.☆14,721Updated this week
- Unlocking NVIDIA CMP 90HX (GA102): kernel 6.12☆38Aug 22, 2026Updated 2 months ago
- DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallel…☆118Aug 13, 2026Updated 2 months ago
- A fork of jasl/vllm (codex/ds4-sm120-min-enable) with CPU-GPU hybrid inference support for DeepSeek-V4 on SM120+.☆31Sep 10, 2026Updated last month
- An extension utility for llama.cpp, used with 3090*2 + Strix Halo. llama.cpp的拓展小工具，自用于3090*2 + Strix Halo。☆409Sep 7, 2026Updated last month
- Lynn GitHub 镜像仓 · Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· 主仓 https://github.com/MerkyorLynn/Lynn · 下载 htt…☆35Updated this week
- ☆457Updated this week