NVIDIA Linux open GPU with P2P support
☆354Jul 13, 2026Updated last week
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:
- Make FP4 on 5090 Great Again☆17Updated this week
- NVIDIA Linux open GPU with P2P support☆1,402Jun 6, 2025Updated last year
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currentl…☆1,777Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,063Updated this week
- Enable true multi gpu capability in Comfy UI using XDiT XFuser and FSDP managed by Ray☆368Jul 16, 2026Updated last week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆125Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆2,959Updated this week
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆76Jul 14, 2026Updated last week
- Low overhead tracing library and trace visualizer for pipelined CUDA kernels☆137Jul 17, 2026Updated last week
- Interactive Jacobian-Lens visualizer and live steerer for GGUF models on llama.cpp☆76Jul 12, 2026Updated last week
- Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving☆56Apr 28, 2026Updated 2 months ago
- vLLM fork for Tesla V100 (SM70) with AWQ 4-bit support, CUDA 12.8 build flow, and validated Qwen3.5 27B/35B deployment on multi-GPU V…☆544Updated this week
- ☆43Oct 9, 2025Updated 9 months ago
- vLLM fork for Tesla V100 (SM70) — extends 1CatAI's AWQ support and adds GGUF support☆19Jun 20, 2026Updated last month
- 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.
- ☆140Updated 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 …☆387Updated this week
- Fast LLM speculative inference server for consumer hardware.☆2,669Updated this week
- Core, junction, and VRAM temps for GDDR6, GDDR6X, GDDR7 NVIDIA GPUs in Linux☆88Updated this week
- Local LLM Inference Speed Test Tool☆118Jul 2, 2026Updated 3 weeks ago
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,284Updated this week
- RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink☆670Updated this week
- vLLM Docker Container for Qwen3.6 27b☆51Jun 15, 2026Updated last month
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆800Updated 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.
- 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
- ☆32Jul 2, 2025Updated last year
- Use the GPU's idle NVENC silicon to multiply the effective bandwidth of every PCIe wire on the board☆32May 16, 2026Updated 2 months ago
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆450Apr 17, 2026Updated 3 months ago
- Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)☆118Feb 10, 2026Updated 5 months ago
- ☆20Dec 24, 2024Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 11 months ago
- Fast LLM swapping with sleep/wake support, compatible with vllm, llama.cpp, etc. llama-swap fork.☆51Apr 5, 2026Updated 3 months ago
- A zero-allocation, header-only C++ BPE tokenizer for Qwen, built for maximum inference throughput.☆22Apr 3, 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.
- A collection of high quality huggingface datasets.☆29Apr 19, 2026Updated 3 months ago
- ☆58Oct 10, 2025Updated 9 months ago
- A comprehensive codebase for training and finetuning Image <> Latent models.☆50Mar 1, 2025Updated last year
- A daemon that automatically manages the performance states of NVIDIA GPUs.☆136Feb 24, 2026Updated 5 months ago
- Benchmark and deploy optimized LLM models on GPU servers with vLLM or SGLang. Chose from a list of optimized recipes for popular models o…☆66Updated this week
- ☆63Jul 10, 2025Updated last year
- A systematic empirical study of self-verification strategies in agentic coding harnesses☆29Mar 4, 2026Updated 4 months ago