LLM inference in C/C++
☆64May 7, 2026Updated 4 months ago
Alternatives and similar repositories for llama-cpp-turboquant
Users that are interested in llama-cpp-turboquant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,052Apr 23, 2026Updated 5 months ago
- ☆41Mar 31, 2026Updated 6 months ago
- HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with PrismML Q1_0_G128 1-bit quant support, RotorQuant, TurboQuant, EAGLE3 and P-EAGLE sp…☆26Jun 23, 2026Updated 3 months ago
- LLM inference in C/C++☆2,414Updated this week
- TurboQuant llama.cpp fork with optimized turbo4 kernels for Gemma 4 D=256/512 heads — lazy K/V, batch decode, warp-cooperative write. 120…☆37Apr 5, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 30…☆54Jul 2, 2026Updated 3 months ago
- Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity sim…☆27Aug 22, 2026Updated last month
- 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…☆232Updated this week
- Qwen4-Exp (Qwen3.8-Flash-Next) SWA + MTP + PLE-on-iswa — bounded deep-context decode w/ long-range recall, TBQ4 4.25 bpv KV, DSpark + Rot…☆95Sep 24, 2026Updated last week
- Experimental llama.cpp fork for inference research and development☆879Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,143Updated this week
- LLM inference in C/C++☆56Updated this week
- Pure PyTorch implementation of HISA (Hierarchical Indexed Sparse Attention) as a drop-in plugin for HuggingFace models☆16Apr 7, 2026Updated 5 months ago
- Implementation for IceCache: Memory-Efficient KV-cache Management for Long-Sequence LLMs (ICLR 2026).☆25Jun 9, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆418Updated this week
- FlashInfer: Kernel Library for LLM Serving (Windows build & kernels)☆19Jul 1, 2026Updated 3 months ago
- Simplifies development, reduces developer frustration, and speeds up website creation process.☆14Jan 20, 2023Updated 3 years ago
- Let's try and finetune the OpenAI consistency decoder to work for SDXL☆25Dec 3, 2023Updated 2 years ago
- Experimental LLM inference in C/C++☆40May 15, 2026Updated 4 months ago
- LLM inference in C/C++☆839Updated this week
- Car Monitoring System | سیستم نظارت بر خودرو☆15Nov 8, 2024Updated last year
- A sparse attention kernel supporting mix sparse patterns☆28May 20, 2026Updated 4 months ago
- ☆38Dec 10, 2025Updated 9 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.
- Superseded by github.com/poisonxa16/pxa — PXA, the set-and-forget engine for Pascal and Volta☆24Sep 8, 2026Updated 3 weeks ago
- The local inference server for coding agents. Pure Rust, one binary, Apple Silicon + NVIDIA. Anthropic + OpenAI APIs; the KV cache surviv…☆19Sep 24, 2026Updated last week
- Founder of omnipkg — Run multiple conflicting Python package & interpreter versions concurrently in one environment in milliseconds. On @…☆16Apr 27, 2026Updated 5 months ago
- ☆34Updated this week
- "O(log N) MoE Expert routing via RT Core ray tracing. BVH traversal replaces matrix multiplication in neural language models."☆84Apr 13, 2026Updated 5 months ago
- ☆17Apr 10, 2024Updated 2 years ago
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆475Aug 17, 2026Updated last month
- A framework for efficient model inference with omni-modality models☆30Updated this week
- Advanced intelligent-automation capabilities converge in NodeSync, optimizing node interactions across a scalable, modern, cloud-agnostic…☆13May 12, 2026Updated 4 months ago
- 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 speculative inference server for heterogeneous hardware & consumer GPUs☆2,887Updated this week
- I love building modern web apps, exploring AI-powered development, and solving real-world problems with code. Currently focusing on MERN …☆21Feb 11, 2026Updated 7 months ago
- ☆22Aug 26, 2025Updated last year
- Cheat sheets for various commands and scripts☆17Aug 20, 2026Updated last month
- A C# .netstandard client library for the Kraken REST and Websocket Spot and Futures API focusing on clear usage and models☆73Apr 7, 2024Updated 2 years ago
- llama.cpp fork with additional SOTA quants and improved performance☆3,272Updated this week
- Python Advanced☆18Nov 30, 2023Updated 2 years ago