TurboQuant KV cache compression for llama.cpp — HIP/ROCm port for AMD RDNA3 (gfx1100)
☆55Oct 30, 2026Updated this week
Alternatives and similar repositories for llama.cpp-turboquant-hip
Users that are interested in llama.cpp-turboquant-hip are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- World's first TurboQuant KV cache compression for llama.cpp on AMD ROCm (RX 9070 / gfx1201)☆21Apr 28, 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 4 months ago
- RDNA-native LLM inference engine in Rust.☆786Updated this week
- LLM inference in C/C++☆28Updated this week
- Fresh builds of llama.cpp with AMD ROCm™ acceleration☆799Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A way to visualize nginx config files☆10Nov 21, 2022Updated 3 years ago
- 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…☆237Oct 13, 2026Updated 2 weeks ago
- ☆24Sep 20, 2026Updated last month
- ROCmFPX llama.cpp fork for Windows 🏆 — native build, headless OpenAI-compatible server & benchmarks. Tested on AMD Strix Halo (gfx1151),…☆11Aug 15, 2026Updated 2 months ago
- A colourscheme for mauve lovers☆16Sep 2, 2026Updated 2 months ago
- Run Baidu Unlimited-OCR on AMD GPUs at 56 tok/s with zero accuracy loss — one command. Only 16GB VRAM required.☆16Aug 1, 2026Updated 3 months ago
- ComfyUI node for fast fp16-fp8 mixed precision matmul on RDNA3/3.5 without native fp8☆40Updated this week
- ☆43Apr 26, 2026Updated 6 months ago
- Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).☆126Jul 11, 2026Updated 3 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Abliterated DeepSeek-V4.1-Flash-1017 (FP8 dense, FP4 experts) on 4x RTX PRO 6000 with vLLM-Moet r21 and DSpark: 371-376 tok/s single-stre…☆31Updated this week
- Automated Deployment of AMD ROCm 7.1.1 and PyTorch 2.11.0 (nightly@ROCm7.1) AI Stack for Ubuntu 22.04/24.04 on CDNA 3, RDNA4 and RDNA3. T…☆25May 5, 2026Updated 5 months ago
- Command center LLM-powered IDE. Featuring terminal, streaming chat, and code editor. Mobile-first UI, NestJS backend.☆13Jun 14, 2026Updated 4 months ago
- ☆13Jan 12, 2026Updated 9 months ago
- Multi-agent code simplification skill for Hermes Agent. 3 parallel sub-agents (Hygiene, Clarity, Correctness) with risk-tiered applicatio…☆22Aug 16, 2026Updated 2 months ago
- Containerized Opinionated Agent Orchestration Platform☆15Mar 8, 2026Updated 7 months ago
- Runs parallel subagents and then syncs them with git worktrees☆16Dec 29, 2025Updated 10 months ago
- Step-by-step guide to cross-flash the AMD Radeon Pro V620 to a Radeon Pro W6800 for display output, home-lab compatibility, and fan contr…☆16Sep 16, 2026Updated last month
- A SOTA room equalizer☆13Updated this 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++☆64May 7, 2026Updated 5 months ago
- Module 3: Reproducible Research and Data Analysis☆11Nov 14, 2019Updated 6 years ago
- Curated AMD GPU compatibility index and CLI for AI workloads☆32May 23, 2026Updated 5 months ago
- Desktop application for instant AI-powered text transformation. Translate, correct, summarize, and change the tone of any text, anywhere,…☆35Dec 29, 2025Updated 10 months ago
- llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% t…☆433Updated this week
- Read-Only source code mirror, Proxmox uses mailing list workflow for development.☆27Aug 21, 2026Updated 2 months ago
- MiniMax-H3 Fun ControlNet for ComfyUI. Depth, canny, pose, HED or MLSD video driving H3 frame by frame, built on ComfyUI's own H3 blocks.☆50Sep 15, 2026Updated last month
- Custom node to load models in int8-(convrot) & now int4-/convrot) for speed gains on AMD GPU's with ROCM. (should work with nvidia gpus …☆51Oct 17, 2026Updated 2 weeks ago
- Turn a Snapdragon phone into a Linux gaming handheld. Mainline Linux, Steam in Game Mode, Windows games through Proton ARM64. No Android.☆25Updated 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.
- Mind Garden makes it easy to take notes that link to other notes.☆11Mar 15, 2021Updated 5 years ago
- Truthful local registry and event stream for running coding agents☆12Updated this week
- 🎭 Battle-tested plugins for Hermes Agent — zero core patches. Native vision bypass, multi-agent context injection, and more.☆54Jun 17, 2026Updated 4 months ago
- ☆15Aug 7, 2026Updated 2 months ago
- Memory Ring v3.4.0 — Sovereign Identity Architecture☆14Aug 7, 2026Updated 2 months ago
- Advanced interoperability middleware for GPGPU acceleration. Facilitates cross vendor hardware abstraction and API translation for parall…☆105Sep 8, 2026Updated last month
- Estimation and Prediction of Wet Season Calendar and Soil Water Balance for Agriculture☆16Feb 28, 2025Updated last year