Profile-guided GPU kernel optimizer for AMD/RDNA3. Auto-tunes llama.cpp MMVQ kernels per model shape. 2x decode speedup on 7900 XTX.
☆64Jul 7, 2026Updated 3 weeks 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:
- A char level language model ,this repo is just for learning .☆18Jun 14, 2026Updated last month
- LLM inference in C/C++, but for GFX906!☆20Jul 15, 2026Updated 2 weeks ago
- Random AI notes for working with local models or playing around with random machine learning bits.☆61Jun 7, 2026Updated last month
- A high-throughput and memory-efficient inference and serving engine for LLMs - Optimized for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI…☆77Jun 23, 2026Updated last month
- LLM inference in C/C++☆16Updated this week
- 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.
- ☆22May 12, 2026Updated 2 months ago
- RDNA-native LLM inference engine in Rust.☆496Updated this week
- NEW ROCmfp4 format for llama.cpp☆139Jun 13, 2026Updated last month
- LLM training & inference in python/C++ with web UI☆37Updated this week
- Tiny evaluation of leading LLMs on competitive programming problems☆14Apr 10, 2026Updated 3 months ago
- ☆14Dec 26, 2025Updated 7 months ago
- ☆63Jul 10, 2025Updated last year
- Llama.cpp runner/swapper and proxy that emulates LMStudio / Ollama backends☆60Aug 21, 2025Updated 11 months ago
- Fast fp16-fp8 mixed precision matmul on RDNA3/3.5 GPUs without native fp8☆34Updated 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.
- ☆55Updated this week
- Tensor library for machine learning☆36Updated this week
- ☆21Sep 4, 2025Updated 11 months ago
- LLM inference in C/C++☆17Updated this week
- ONNX speech pipeline library for ASR, diarization, VAD, and denoising☆19Jun 14, 2026Updated last month
- ☆84Mar 23, 2026Updated 4 months ago
- Decentralizing distribution of open-source AI models.☆16Updated this week
- ☆25Feb 10, 2026Updated 5 months ago
- A high-performance RCCL / NCCL (ROCm Communication Collectives Library) plugin for Thunderbolt 5 that enables GPU-to-GPU communication ac…☆56Jul 7, 2026Updated 3 weeks ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- A PowerShell script to fully automate the setup of `llama.cpp` on Windows. It installs all prerequisites, including the correct CUDA Tool…☆16May 12, 2026Updated 2 months ago
- Project code for training LLMs to write better unit tests + code☆22May 19, 2025Updated last year
- Messy repo filled with messy tests about hardware and LLMs. Built for me, public for you.☆44Updated this week
- Lightweight Python tool using Optuna for tuning llama.cpp flags: towards optimal tok/s for your machine☆42Jun 30, 2025Updated last year
- High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU…☆17Jul 6, 2026Updated 3 weeks ago
- ☆145May 29, 2026Updated 2 months ago
- A simple python module to read Infiray C200/P200/etc. IRG thermal image files☆17Nov 5, 2025Updated 8 months ago
- Extract a single expert from a Mixture Of Experts model using slerp interpolation.☆19May 26, 2024Updated 2 years ago
- Local LLM Server Manager + LlaMA.cpp + Chat☆17Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.☆18Mar 20, 2026Updated 4 months ago
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆162Updated this week
- ☆24Updated this week
- Local benchmarking UI for LLMs and AI agents☆22Apr 13, 2026Updated 3 months ago
- 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…☆50May 10, 2026Updated 2 months ago
- llama.cpp fork with AMD XDNA2 NPU backend for Ryzen AI MAX (npu5/XDNA2) — matrix multiply offload via XRT☆19Apr 1, 2026Updated 4 months ago
- ☆44Apr 26, 2026Updated 3 months ago