ML software (llama.cpp, ComfyUI, vLLM) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60
☆311Aug 14, 2026Updated this week
Alternatives and similar repositories for ML-gfx906
Users that are interested in ML-gfx906 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 high-throughput and memory-efficient inference and serving engine for LLMs - Optimized for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI…☆81Jun 23, 2026Updated last month
- vLLM for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆434Feb 20, 2026Updated 5 months ago
- llama.cpp-gfx906☆140Mar 22, 2026Updated 4 months ago
- vLLM for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆26Updated this week
- triton for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆48Dec 8, 2025Updated 8 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆23May 12, 2026Updated 3 months ago
- A database of knowledge around inference & training on GFX906 GPUs https://skyne98.github.io/wiki-gfx906/☆16Feb 21, 2026Updated 5 months ago
- Modified for AMD MI50 GPUs | A high-throughput and memory-efficient inference and serving engine for LLMs☆15Mar 2, 2026Updated 5 months ago
- FORK of VLLM for AMD MI25/50/60. A high-throughput and memory-efficient inference and serving engine for LLMs☆71May 4, 2025Updated last year
- Triton for AMD MI25/50/60. Development repository for the Triton language and compiler☆34Dec 15, 2025Updated 8 months ago
- The HIP Environment and ROCm Kit - A lightweight open source build system for HIP and ROCm☆1,210Updated this week
- RDNA-native LLM inference engine in Rust.☆524Updated this week
- The main repository for building Pascal-compatible versions of ML applications and libraries.☆218Aug 23, 2025Updated 11 months ago
- Random AI notes for working with local models or playing around with random machine learning bits.☆63Jun 7, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Implementation of FlashAttention-2 for Nvidia Tesla V100 / Titan V☆189Jun 30, 2026Updated last month
- A llamacpp wrapper to manage and monitor your llama server instance over a web ui.☆22Jun 16, 2026Updated 2 months ago
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆24Jan 30, 2026Updated 6 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆3,056Updated this week
- Gives agents a real browser. URL in, pruned snapshot out. Replaces Playwright, Selenium, Puppeteer. Zero deps, zero wasted tokens.☆45Jul 13, 2026Updated last month
- vLLM fork for Tesla V100 (SM70) with AWQ 4-bit support, CUDA 12.8 build flow, and validated Qwen3.5 27B/35B deployment on multi-GPU V…☆628Updated this week
- LLM speculative inference server for consumer & heterogeneous hardware☆2,762Updated this week
- The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 100+ tok/s single-reques…☆545Updated this week
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆132Updated 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.
- Flash Attention 2 implementation for Turing GPUs☆124Mar 23, 2026Updated 4 months ago
- unofficial support for rx580, rx470, Vega10, rx590, sp2048, or similar GFX803 GFX900 for zluda & Windows☆25Jan 17, 2026Updated 7 months ago
- ☆28Jul 24, 2026Updated 3 weeks ago
- ☆444Apr 4, 2025Updated last year
- High-performance FlashAttention-2 for AMD, Intel, and Apple GPUs. Drop-in replacement for PyTorch SDPA. Triton backend for ROCm (MI300X, …☆159Jan 27, 2026Updated 6 months ago
- A fork of vLLM enabling Pascal architecture GPUs☆36Feb 21, 2025Updated last year
- ☆17Oct 27, 2025Updated 9 months ago
- ☆26Jun 10, 2026Updated 2 months ago
- Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc☆5,402Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB G…☆207Updated this week
- A professional Next.js blogging platform with advanced AI-driven content generation. Auto-Blog leverages RSS feed analysis and Retrieval-…☆22Oct 8, 2025Updated 10 months ago
- GPU-accelerated voice assistant — local LLM, fine-tuned Whisper, Kokoro TTS, AMD ROCm☆21Apr 2, 2026Updated 4 months ago
- Proxy for OpenAI☆16Sep 2, 2025Updated 11 months ago
- ☆12Feb 8, 2025Updated last year
- Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over OpenAI endpoints.☆503Updated this week
- A single-user media acquisition orchestration console for Whisparr, enriched by StashDB metadata and validated against local Stash availa…☆21Jun 3, 2026Updated 2 months ago