RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
☆809Aug 10, 2026Updated this week
Alternatives and similar repositories for rtx6kpro
Users that are interested in rtx6kpro are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆164Updated this week
- Docker images for LLM inference (SGLang + vLLM) on NVIDIA Blackwell GPUs (SM120, CUDA 13.2)☆61Updated this week
- LLM inference decode throughput benchmark with Rich TUI dashboard. Measures token generation speed across concurrency levels and context …☆67Jul 11, 2026Updated last month
- Optimized vLLM setup for Qwen3.6-27B-FP8 on dual RTX PRO 6000 Blackwell (192 GB GDDR7, no NVLink) ; config, benchmark sweep results, and …☆19May 10, 2026Updated 3 months ago
- Educational reference: NVIDIA Blackwell SM100 vs SM120, NVFP4, tcgen05, MoE inference on consumer Blackwell☆21Apr 28, 2026Updated 3 months 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.
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆511Updated this week
- ☆35Apr 26, 2026Updated 3 months ago
- Messy repo filled with messy tests about hardware and LLMs. Built for me, public for you.☆46Aug 2, 2026Updated last week
- llama.cpp fork with additional SOTA quants and improved performance☆3,024Updated this week
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currentl…☆1,921Updated this week
- LLM speculative inference server for consumer hardware & heterogeneous computing☆2,728Updated this week
- llama-benchy - llama-bench style benchmarking tool for all backends☆624Jul 10, 2026Updated last month
- A high-throughput and memory-efficient inference and serving engine for LLMs☆37Updated this week
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆56Apr 28, 2026Updated 3 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.
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,127Updated this week
- NVIDIA Linux open GPU with P2P support☆392Jul 13, 2026Updated 3 weeks ago
- Docker configuration for running VLLM on dual DGX Sparks☆2,008Updated this week
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆5,312Updated this week
- Everything I know about running LLMs locally☆1,752Jul 10, 2026Updated last month
- Python SDK for Agent Vector Protocol – transfer KV-cache between LLM agents instead of text☆25Apr 26, 2026Updated 3 months ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,638Updated this week
- Benchmarking tool for vLLM inference performance with GPU monitoring☆52Jun 7, 2026Updated 2 months ago
- These are performance benchmarks we did to prepare for our own privacy-preserving and NDA-compliant in-house AI coding assistant. If by a…☆32Apr 2, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Step-by-step guide: Qwen3.6 27B/35B on RTX PRO 6000 Blackwell — 120-200 tok/s with vLLM + MTP n=3☆18Aug 4, 2026Updated last week
- A harness optimized to smaller LLMs☆2,343Jul 31, 2026Updated last week
- Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a sep…☆48Jul 7, 2026Updated last month
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆285Updated this week
- NVIDIA Fan Control Service tested on Ubuntu providing more aggressive fan curves for RTX Pro 6000 GPUs☆16Jan 17, 2026Updated 6 months ago
- VellumForge2 is a Golang CLI for generating high-quality Direct Preference Optimization datasets via a hierarchical prompt pipeline with …☆21Feb 15, 2026Updated 5 months ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,579May 10, 2026Updated 3 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 …☆431Updated this week
- Multi-vector latent space steering adapter module for language models☆20Nov 22, 2025Updated 8 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.
- Linux hwmon driver for the NVIDIA DGX Spark (GB10 SoC) that exposes full system power telemetry via standard sensors / sysfs interfaces.☆30Mar 2, 2026Updated 5 months ago
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆474Apr 17, 2026Updated 3 months ago
- Using LLMs for iteratively exploring the solution search space at scale.☆742Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,578Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆88,592Updated this week
- Local LLM stack with open-source components and documented the installation and configuration steps.☆35Jun 2, 2026Updated 2 months ago
- A simple streamlit app to play with qwen3-2b-VL to perform OCR. Dockerized set up, tested with 3060 12 GB.☆32Nov 23, 2025Updated 8 months ago