Unlock P2P comms between consumer NVIDIA GPUs
☆572Sep 16, 2026Updated last month
Alternatives and similar repositories for open-gpu-kernel-modules
Users that are interested in open-gpu-kernel-modules are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- NVIDIA Linux open GPU with P2P support☆1,434Jun 6, 2025Updated last year
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,416Updated this week
- Practical local LLM recipes and benchmarks for RTX 5060 Ti setups☆186Oct 8, 2026Updated last week
- Make FP4 on 5090 Great Again☆24Jul 20, 2026Updated 3 months ago
- Qwen3.8-Flash-Next (MoE, NVFP4) and Qwen3.8-27B on two 16 GB consumer GPUs: two-GPU tensor parallel, experts offloaded to CPU. Formerly n…☆43Updated this week
- 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.
- Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,86…☆119Updated this week
- Enable true multi gpu capability in Comfy UI using XDiT XFuser and FSDP managed by Ray☆476Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,713Updated this week
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆133Sep 30, 2026Updated 2 weeks ago
- NVIDIA Linux open GPU with P2P support☆34Oct 12, 2026Updated last week
- llama.cpp fork with additional SOTA quants and improved performance☆3,314Updated this week
- LLM inference in C/C++☆56Aug 8, 2026Updated 2 months ago
- Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants…☆178Updated this week
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆464Updated 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.
- Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parall…☆152Updated this week
- Unlocks full compute, PCIe Gen2 and ReBar support for CMP 50HX mining cards. Same performance as RTX 2080 Ti achieved. One click install.☆89Oct 10, 2026Updated last week
- V100 / SM70-focused vLLM engineering fork for modern LLM inference.☆1,365Updated this week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,087Updated this week
- CLI port of BenchLocal quality bench packs — runs LLM behavioral evals against any OpenAI-compatible endpoint. Companion to club-3090.☆18Updated this week
- Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when …☆2,132Updated this week
- RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink☆1,148Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,166Updated this week
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆82Sep 19, 2026Updated last month
- 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.
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆58Apr 28, 2026Updated 5 months ago
- Unlock tool for the NVIDIA CMP 170HX (GA100) mining card. Restores full A100 compute throughput by exploiting the Falcon BootROM .fwsigna…☆57Jul 30, 2026Updated 2 months ago
- Core, junction, and VRAM temps for GDDR6, GDDR6X, GDDR7 NVIDIA GPUs in Linux☆100Sep 24, 2026Updated 3 weeks ago
- Unified tracing profiler and visualizer, one timeline from CPU to GPU/HES to in-kernel zones☆149Sep 21, 2026Updated last month
- ☆24Dec 29, 2025Updated 9 months ago
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆545Updated this week
- Single-file installer for a club-3090 webserver providing an admin control panel, a reverse proxy that automatically routes requests to t…☆28Jul 8, 2026Updated 3 months ago
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,483Updated this week
- vLLM Docker Container for the latest Qwen 27b☆52Sep 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.
- Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and in…☆18Nov 11, 2024Updated last year
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,934Updated this week
- LLM inference decode throughput benchmark with Rich TUI dashboard. Measures token generation speed across concurrency levels and context …☆120Oct 13, 2026Updated last week
- Interactive Jacobian-Lens visualizer and live steerer for GGUF models on llama.cpp☆90Jul 12, 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 …☆470Sep 22, 2026Updated 3 weeks ago
- Project Maya - run GLM-5.3-Flash (321B MoE) and DeepSeek-V4.1-Flash-1017 (748B MoE) privately on your own GPU(s), from one card to 16, NV…☆1,212Updated this week
- vLLM fork for Tesla V100 (SM70) — extends 1CatAI's AWQ support and adds GGUF support☆25Jun 20, 2026Updated 4 months ago