ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants
☆107Jul 12, 2026Updated this week
Alternatives and similar repositories for ROCmFPX
Users that are interested in ROCmFPX are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- NEW ROCmfp4 format for llama.cpp☆132Jun 13, 2026Updated last month
- RDNA-native LLM inference engine in Rust.☆482Updated this week
- ☆56Jun 30, 2026Updated 2 weeks ago
- ☆50Updated this week
- AMD Strix Halo / Ryzen AI Halo local LLM setup and benchmark guide for Ryzen AI MAX+ 395 and Radeon 8060S: Ollama, llama.cpp Vulkan/RADV,…☆215Updated 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.
- Decentralizing distribution of open-source AI models.☆15Updated 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…☆219Jul 6, 2026Updated last week
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆40Updated this week
- A high-performance RCCL / NCCL (ROCm Communication Collectives Library) plugin for Thunderbolt 5 that enables GPU-to-GPU communication ac…☆47Jul 7, 2026Updated last week
- ☆66Updated this week
- Fast LLM speculative inference server for consumer hardware.☆2,656Updated this week
- tested hermes agent recipes: configs, deploys, mcp, automations. copy, run, build.☆100Updated this week
- A monochrome (ish) neovim colour theme☆10Apr 23, 2026Updated 2 months ago
- ☆467Jun 17, 2026Updated 3 weeks 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.
- Ardumoto Motor Driver Shield for Arduino, created by and available from SparkFun Electronics☆10Aug 13, 2019Updated 6 years ago
- A Python DSL for Apple Metal GPU compute☆25Jun 20, 2026Updated 3 weeks ago
- Profile-guided GPU kernel optimizer for AMD/RDNA3. Auto-tunes llama.cpp MMVQ kernels per model shape. 2x decode speedup on 7900 XTX.☆61Jul 7, 2026Updated last week
- TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fa…☆74Updated this week
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆128Updated this week
- DFlash & TurboQuant in llama.cpp with up to 3x faster generation and 7.5x more KV cache in same VRAM☆772Updated this week
- LLM training & inference in python/C++ with web UI☆36Updated this week
- Interactive Jacobian-Lens visualizer and live steerer for GGUF models on llama.cpp☆63Updated this week
- Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration☆600Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A local-first Windows AI assistant with a multi-model council pipeline, Python sandbox, web search, and cloud AI support. Free. Private. …☆17Updated this week
- Audiobook creation app supporting too many TTS models (Qwen3-TTS, OmniVoice, VibeVoice, etc), focused on high-quality output. Plus audio-…☆165Updated this week
- Setup wizard for Hermes Gateway Desktop☆30Jul 2, 2026Updated last 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…☆46May 10, 2026Updated 2 months ago
- Five Bottlenecks, Five Fixes: How We Avoid Leaving Training Performance on the Table☆19Mar 13, 2026Updated 4 months ago
- Llama.cpp launcher with integrated huggingface☆59Jun 25, 2026Updated 2 weeks ago
- ☆22Updated this week
- LLAMA Turboquant implementation with CUDA support☆687Updated this week
- ☆12May 17, 2018Updated 8 years ago
- 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.
- ☆11Sep 5, 2025Updated 10 months ago
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆416Jul 3, 2026Updated last week
- LM Studio Plugin to mark a directory full of documents as a RAG source and another directory as the Vectorstore and build a RAG for use i…☆53Jul 7, 2026Updated last week
- Starlink gRPC for Golang☆21Updated this week
- CLI for CAT721☆11Dec 5, 2024Updated last year
- ☆55Jun 8, 2026Updated last month
- ☆13Mar 20, 2018Updated 8 years ago