LLM speculative inference server for consumer & heterogeneous hardware
☆2,784Aug 23, 2026Updated this week
Alternatives and similar repositories for lucebox
Users that are interested in lucebox are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currentl…☆2,068Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,898Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆906Updated this week
- Experimental llama.cpp fork for inference research and development☆779Updated this week
- llama.cpp fork with additional SOTA quants and improved performance☆3,077Aug 15, 2026Updated last week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- LLM inference in C/C++☆2,309Updated this week
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,043Apr 23, 2026Updated 4 months ago
- ☆395Apr 16, 2026Updated 4 months ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,735Updated this week
- ☆119Apr 28, 2026Updated 3 months ago
- RDNA-native LLM inference engine in Rust.☆546Updated this week
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆231Updated this week
- Pure Rust Inference Engine☆659Updated this week
- Structured Chain-of-Thought☆220May 16, 2026Updated 3 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm☆21,674Updated this week
- A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support…☆1,582Updated this week
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆451Jul 3, 2026Updated last month
- Test LLMs on real tasks. Compare models side-by-side.☆413Aug 10, 2026Updated last week
- TokenSpeed is a speed-of-light LLM inference engine.☆1,952Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,159Updated this week
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆5,449Updated this week
- A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official …☆527Updated this week
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆769Updated 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.
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆447Aug 17, 2026Updated last week
- ☆7,005Jul 20, 2026Updated last month
- llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.☆264Updated 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…☆132Updated this week
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆357Aug 6, 2026Updated 2 weeks ago
- Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.☆74,496Updated this week
- NEW ROCmfp4 format for llama.cpp☆148Jun 13, 2026Updated 2 months ago
- TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained …☆844Aug 4, 2026Updated 2 weeks ago
- LLM inference in C/C++☆125,279Updated 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.
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,322Updated this week
- 3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.☆1,598Updated this week
- vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-strea…☆51May 10, 2026Updated 3 months ago
- Fast, lossless LLM inference via dual-view diffusion decoding.☆476Aug 12, 2026Updated last week
- Running a big model on a small laptop☆4,082Mar 19, 2026Updated 5 months ago
- Using LLMs for iteratively exploring the solution search space at scale.☆744Aug 15, 2026Updated last week
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆483Apr 17, 2026Updated 4 months ago