RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
☆903Aug 30, 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:
- ☆194Updated this week
- Docker images for LLM inference (SGLang + vLLM) on NVIDIA Blackwell GPUs (SM120, CUDA 13.2)☆69Updated this week
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆536Updated this week
- ☆37Apr 26, 2026Updated 4 months ago
- Messy repo filled with messy tests about hardware and LLMs. Built for me, public for you.☆49Aug 17, 2026Updated 2 weeks 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.
- llama.cpp fork with additional SOTA quants and improved performance☆3,148Updated 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…☆2,122Updated this week
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,816Updated this week
- llama-benchy - llama-bench style benchmarking tool for all backends☆682Jul 10, 2026Updated last month
- A high-throughput and memory-efficient inference and serving engine for LLMs☆41Aug 13, 2026Updated 2 weeks ago
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆58Apr 28, 2026Updated 4 months ago
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,201Updated this week
- NVIDIA Linux open GPU with P2P support☆459Aug 22, 2026Updated last week
- Docker configuration for running VLLM on dual DGX Sparks☆2,202Updated 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.
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆5,520Updated this week
- Everything I know about running LLMs locally☆1,811Jul 10, 2026Updated last month
- Python SDK for Agent Vector Protocol – transfer KV-cache between LLM agents instead of text☆26Apr 26, 2026Updated 4 months ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,745Updated 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
- Step-by-step guide: Qwen3.6 27B/35B on RTX PRO 6000 Blackwell — 120-200 tok/s with vLLM + MTP n=3☆21Aug 4, 2026Updated 3 weeks ago
- A harness optimized to smaller LLMs☆2,515Updated this week
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆318Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ChatGPT for Mac, living in your menubar.☆1,321Jun 26, 2026Updated 2 months ago
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,011Aug 18, 2026Updated last week
- LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features …☆451Updated this week
- Multi-vector latent space steering adapter module for language models☆20Nov 22, 2025Updated 9 months ago
- Linux hwmon driver for the NVIDIA DGX Spark (GB10 SoC) that exposes full system power telemetry via standard sensors / sysfs interfaces.☆32Mar 2, 2026Updated 5 months ago
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆490Apr 17, 2026Updated 4 months ago
- Using LLMs for iteratively exploring the solution search space at scale.☆743Aug 15, 2026Updated 2 weeks ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆32,926Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆90,491Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Local LLM stack with open-source components and documented the installation and configuration steps.☆37Jun 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 9 months ago
- ☆35Feb 6, 2026Updated 6 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆22Updated this week
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations☆19,329Updated this week
- NVIDIA DGX Spark Playbooks☆18Nov 26, 2025Updated 9 months ago
- A hands-on guide for AI builders: make your own RTX 4090D/5090 GPU server that’s fast and efficient.☆17Aug 19, 2025Updated last year