FlashAttention-style custom attention backend for vLLM on AMD MI50/MI60/Radeon VII (gfx906). Downstream fork of mixa3607/ML-gfx906 with replacement HIP kernels and a vllm.general_plugins entry point.
☆19Apr 22, 2026Updated 6 months ago
Alternatives and similar repositories for gfx906-fa-vllm
Users that are interested in gfx906-fa-vllm 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…☆95Oct 8, 2026Updated last month
- ☆30May 12, 2026Updated 5 months ago
- ☆32Sep 30, 2026Updated last month
- triton for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆48Dec 8, 2025Updated 11 months ago
- LLM inference in C/C++☆75Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Strata 0.2.3 (engine 0.1.48) for AMD gfx906 (MI50/MI60/Radeon VII): rocBLAS solution table, Qwen3.6/Ornith engine restored, DFlash2 build…☆27Nov 1, 2026Updated last week
- vLLM for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60☆436Feb 20, 2026Updated 8 months ago
- Optimized VLLM for Ampere☆25Oct 18, 2026Updated 3 weeks ago
- Thoth is a powerful tool to support collaborative systematic reviews. Developed as a multi-platform solution, Thoth aims to automate impo…☆11Jun 9, 2026Updated 5 months ago
- ☆18Jan 3, 2026Updated 10 months ago
- Unlocking NVIDIA CMP 90HX (GA102): kernel 6.12☆48Aug 22, 2026Updated 2 months ago
- A database of knowledge around inference & training on GFX906 GPUs https://skyne98.github.io/wiki-gfx906/☆19Feb 21, 2026Updated 8 months ago
- Local Research Agent , uses Ollama as inference engine. Embedding model for semantic matching of topics for better reports. Prints report…☆13Jan 9, 2026Updated 10 months ago
- A persistent AI character that reads world news, builds memories with retrieval, and evolves an emotional state over time.☆13Mar 22, 2026Updated 7 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆12Feb 8, 2025Updated last year
- Validate the usable size of your local LLM cache under pressure☆12Sep 26, 2026Updated last month
- Multi-GPU prefill acceleration for llama.cpp☆16Oct 23, 2026Updated 2 weeks ago
- [ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models☆28Jul 3, 2026Updated 4 months ago
- Take back your LG webOS TV: one-click rooting (SlopBro) + persistent telemetry/ACR/voice/ads/update blocking via reversible userspace hoo…☆18Nov 2, 2026Updated last week
- vLLM on AMD RDNA4 (gfx1201 / RX 9070 XT-9070): clone-and-docker-compose-up, with a W4A8-FP8-WMMA MoE kernel☆14Jul 18, 2026Updated 3 months ago
- This is a repository for documenting the setup and performance of MI100s in popular inference engines.☆20Oct 8, 2026Updated last month
- Container driven LLM control for VLLM & llama models☆14Oct 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.☆71Sep 5, 2026Updated 2 months 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.
- Custom VA-API video driver for AMD BC-250, using Vulkan RDNA 2 compute shaders to enable H.264 hardware-accelerated encoding.☆16Sep 26, 2026Updated last month
- Advanced interoperability middleware for GPGPU acceleration. Facilitates cross vendor hardware abstraction and API translation for parall…☆109Sep 8, 2026Updated 2 months ago
- A python framework to develop games with real world object tracking (using cameras) combined with projection mapping☆13Apr 28, 2021Updated 5 years ago
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆19Apr 26, 2026Updated 6 months ago
- Qwen3.8-27B and Qwen3.6-35B-A3B local inference engine for Vulkan and Metal☆80Updated this week
- Proxima lets existing GPUs serve 4x more concurrent requests☆26Aug 19, 2026Updated 2 months ago
- A high-throughput LLM serving engine with non-uniform KV cache compression, built on vLLM☆16Sep 9, 2026Updated 2 months ago
- Dockerized environment to ease odoo development☆18Updated this week
- MCP server for web fetching with Cloudflare bypass, Trafilatura extraction, and smart routing. Free, self-hosted, no API keys.☆92Sep 6, 2026Updated 2 months ago
- 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.
- HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with PrismML Q1_0_G128 1-bit quant support, RotorQuant, TurboQuant, EAGLE3 and P-EAGLE sp…☆25Jun 23, 2026Updated 4 months ago
- SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35…☆133Sep 30, 2026Updated last month
- VENDORIZED in lucebox-hub. Fork of llama.cpp, ggml graph for lucebox inference engine☆29Jul 8, 2026Updated 4 months ago
- vLLM fork for pascal gpu☆18Mar 13, 2026Updated 7 months ago
- A Darwin/XNU Based Operating System☆25Sep 12, 2026Updated last month
- It lets an AI agent put a live, interactive page on any screen you own, and brings what you do on it back into the conversation.☆26Updated this week
- Optimized build of llama.cpp for gfx906/Vega20.☆24Updated this week
Are these results useful?