AMD MI210 (gfx90a/CDNA2) LLM inference optimization — TurboQuant, KIVI, per-layer KV types, FlashAttention, MoE expert caching
☆15Aug 25, 2026Updated 2 months ago
Alternatives and similar repositories for mi210-llm-stack
Users that are interested in mi210-llm-stack are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Run AMD AITER's hand-written ASM kernels on CDNA2 / gfx90a (MI210, MI250). 242 of 1,422 kernels translated, with the tests and benchmarks…☆11Sep 9, 2026Updated last month
- ☆13Updated this week
- ☆10Jul 4, 2025Updated last year
- Compile your own LLM for the Hailo-10H — an open pipeline from Hugging Face checkpoint to a self-contained HEF, served with hailo-ollama.☆23Oct 2, 2026Updated last month
- Polyhedral Template Matching algorithm for analysis of molecular dynamics simulation data☆22Mar 22, 2020Updated 6 years 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.
- Linux Mint 19 on Lenovo Thinkpad t490s☆18Jun 23, 2019Updated 7 years ago
- FlashAttention-style custom attention backend for vLLM on AMD MI50/MI60/Radeon VII (gfx906). Downstream fork of mixa3607/ML-gfx906 with r…☆17Apr 22, 2026Updated 6 months ago
- 6800% faster "os" module replacement. A drop-in replacement for Python's standard 'OS' module. Fully-rewritten, optimized, and speeded-up…☆18Feb 20, 2023Updated 3 years ago
- ☆11Dec 27, 2023Updated 2 years ago
- 一段提示词让 Codex 与 ChatGPT 分工：研究、本地执行、独立验证 | One prompt pairing Codex with ChatGPT for research, local execution and independent verification☆16Aug 2, 2026Updated 3 months ago
- A Python binding of resvg, the high-performance SVG rendering library in Rust☆14Oct 25, 2026Updated last week
- ☆10Jul 19, 2021Updated 5 years ago
- ☆15Aug 23, 2026Updated 2 months ago
- A fast C++ CIF and mmCIF parser☆11Jul 24, 2026Updated 3 months 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.
- A Los Angeles Times theme for Python's Altair statistical visualization library☆12May 20, 2021Updated 5 years ago
- Example finite element codes for coupled theories in solid mechanics.☆12Oct 9, 2025Updated last year
- Microbenchmarks showing relative performance of different Python functions/patterns.☆13Oct 3, 2025Updated last year
- 3D point cloud registration tool☆11Feb 8, 2021Updated 5 years ago
- ☆10Aug 29, 2021Updated 5 years ago
- 🏕️ A Gemini-to-Gopher proxy that bridges the smolweb to even more smolweb☆11Oct 30, 2026Updated last week
- Automated job scanning and LLM-powered scoring for IT positions in Sweden.☆33Sep 12, 2026Updated last month
- pyCSH: automated generation of realistic bulk calcium silicate hydrate (C-S-H) structures.☆13Jun 26, 2024Updated 2 years ago
- Angel - a symmetrical staggered ergonomic keyboard.☆13Jan 27, 2021Updated 5 years 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.
- Showing how to integrate CMake, C++, and pybind11☆11May 1, 2018Updated 8 years ago
- Qwen3.8-27B INT8 + DFlash2 on a rented CMP 170HX — failure analysis (private GHCR image prevented benchmark)☆17Aug 30, 2026Updated 2 months ago
- This repository serves as a directory for those looking for a MFR2-style a case for a specific keyboard☆13Apr 16, 2025Updated last year
- XQuery and OpenSCAD code for polyhedra creation☆12May 3, 2018Updated 8 years ago
- A GPU-Accelerated Clustering Algorithm that uses the Hungarian method.☆13Jan 1, 2023Updated 3 years ago
- 3D Minkowski Tensor Package☆10May 7, 2026Updated 6 months ago
- Conda recipes for Glotzer Lab software on HPC resources☆11Oct 30, 2026Updated last week
- Local AI coding pipeline on an RTX 5090: llama.cpp, Qwen3.5/3.6 MoE, Gemma 4, TurboQuant KV, OpenCode, Claude Code, MCP. 188 t/s (Qwen3.5…☆20Oct 31, 2026Updated last week
- ☆10Jun 22, 2024Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A GPU accelerated polygon clipping algorithm☆11Dec 2, 2023Updated 2 years ago
- hugepage allocator implement with rust☆13Oct 28, 2026Updated last week
- A simple Rust library implementing a 3D vector type☆11Dec 11, 2018Updated 7 years ago
- Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,86…☆134Oct 15, 2026Updated 3 weeks ago
- 🌈 Highlights similar variables on focus☆14Apr 23, 2023Updated 3 years ago
- C# tools for finding SDV seeds☆14May 10, 2026Updated 5 months ago
- Trion Core☆15Jan 2, 2026Updated 10 months ago