Profile-guided GPU kernel optimizer for AMD/RDNA3. Auto-tunes llama.cpp MMVQ kernels per model shape. 2x decode speedup on 7900 XTX.
☆71Sep 5, 2026Updated 2 months ago
Alternatives and similar repositories for kernel-anvil
Users that are interested in kernel-anvil are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆14Sep 10, 2026Updated 2 months ago
- ☆29Oct 7, 2026Updated last month
- NEW ROCmfp4 format for llama.cpp☆159Jun 13, 2026Updated 4 months ago
- ☆86Sep 10, 2026Updated 2 months ago
- Custom HIP inference engine for AMD MI50/MI60 (gfx906)☆19Oct 4, 2026Updated last month
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- FlashAttention-style custom attention backend for vLLM on AMD MI50/MI60/Radeon VII (gfx906). Downstream fork of mixa3607/ML-gfx906 with r…☆19Apr 22, 2026Updated 6 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs - Optimized for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI…☆95Oct 8, 2026Updated last month
- ☆96Updated this week
- ☆30May 12, 2026Updated 6 months ago
- Fresh builds of llama.cpp with AMD ROCm™ acceleration☆818Updated this week
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- ML software (llama.cpp, ComfyUI, Strata, Maya, ...) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆380Updated this week
- A simple python-based terminal tool to manage llama.cpp☆13Sep 30, 2025Updated last year
- A fast, polished, local Web UI for llama-server, vLLM, and OpenAI-compatible APIs - with charts, diagrams, and MCP tools.☆32Oct 26, 2026Updated 2 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- vLLM GGUF plugin fork — Qwen3.5/3.6 hybrid (GDN) serving: iq4_xs mmvq perf, MTP speculative decode, MoE draft support☆12Updated this week
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆431Oct 22, 2026Updated 3 weeks ago
- A simple no-install web UI for Ollama and OAI-Compatible APIs!☆31Jan 30, 2025Updated last year
- Tiny evaluation of leading LLMs on competitive programming problems☆15Apr 10, 2026Updated 7 months ago
- Thin wrapper around GGML to make life easier☆49Jul 26, 2026Updated 3 months ago
- Define LXC containers using syntax similar to docker-compose, retrieve OCI images as LXC templates, and share LXC containers as OCI image…☆19Oct 2, 2026Updated last month
- Optimized build of llama.cpp for gfx906/Vega20.☆25Updated this week
- Portable vLLM builds with AMD ROCm acceleration for Lemonade☆81Sep 9, 2026Updated 2 months ago
- Turn an authenticated X feed into NotebookLM-ready source bundles and podcast inputs.☆10Apr 8, 2026Updated 7 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.
- ☆65Jul 10, 2025Updated last year
- A general-purpose LLM harness and coding agent implemented as a single, hackable Bash script.☆12Nov 1, 2026Updated last week
- llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both☆59Updated this week
- Turbo1Bit: Combining 1-bit LLM weights (Bonsai) with TurboQuant KV cache compression for maximum inference efficiency. 4.2x KV cache comp…☆30Apr 2, 2026Updated 7 months ago
- Llama.cpp runner/swapper and proxy that emulates LMStudio / Ollama backends☆61Aug 21, 2025Updated last year
- Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streamin…☆22Feb 18, 2026Updated 8 months ago
- ☆20Sep 4, 2025Updated last year
- Ollama 0.12.3 + ROCm 7.1 for AMD MI50 (gfx906) Docker image☆11Apr 9, 2026Updated 7 months ago
- ☆14Apr 13, 2026Updated 6 months ago
- 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.
- A set of performant RDNA/HIP patches against llama.cpp focusing on high speed inferencing with numerics assurance☆241Updated this week
- A high-performance RCCL / NCCL (ROCm Communication Collectives Library) plugin for Thunderbolt 5 that enables GPU-to-GPU communication ac…☆78Nov 4, 2026Updated last week
- Tensor library for machine learning☆37Oct 23, 2026Updated 2 weeks ago
- Open-source local AI server configs, GFX906 runtime maintenance, reproducible benchmarks, and QC methods for affordable AI research infra…☆17Jul 1, 2026Updated 4 months ago
- ☆25Feb 10, 2026Updated 9 months ago
- dockerfiles, compose files, benchmarks for 2x R9700 serving☆27Updated this week
- ComfyUI node for fast int8 model, fp8 model, VAE on RDNA3/3.5☆40Updated this week
Are these results useful?