llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both
☆51Oct 17, 2026Updated this week
Alternatives and similar repositories for llama-halo-hybrid
Users that are interested in llama-halo-hybrid are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- HRX, LOOM, Mac, and AMD running top speed kernels with a self optimizing engine.☆33Updated this week
- Strix Halo (gfx1151) + XDNA2 NPU inference fork: Qwen3.8 Flash-Next UD-IQ4_XS with MTP. About 2,000 tok/s prefill (GPU + NPU, 2,013 at 8K…☆48Updated this week
- The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1787.54 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B …☆797Updated this week
- (WIP) An ansible playbook to harden a docker host to the CIS CE Benchmark requirements☆31Oct 13, 2025Updated last year
- This is a mirror of the Strix Halo HomeLab wiki, to browse the wiki click on the link below☆73Aug 31, 2026Updated last month
- 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.
- 中文推文与文章的诊断、创作和精修 Skill☆39Aug 31, 2026Updated last month
- 🚿 Llaminar: an LLM inferencing engine in C++.☆45Oct 9, 2026Updated last week
- Tool used in initramfs to seal/unseal FDE key to the TPM☆28Jan 27, 2022Updated 4 years ago
- Agentic practices knowledge base + supporting software toolkit☆44Aug 14, 2026Updated 2 months ago
- Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.☆257Sep 7, 2026Updated last month
- The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)☆1,018Updated this week
- Ethiopian Literature edited in TEI☆10Oct 6, 2026Updated last week
- LLM inference in C/C++☆236Updated this week
- ☆89Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Timeline director for the MiniMax H3 video model in ComfyUI — shots, camera moves and audio cues compiled into the structured prompt H3 r…☆66Sep 16, 2026Updated last month
- ☆12Jan 2, 2025Updated last year
- CherryPick is a modular, open-source dependency injection ecosystem for Dart and Flutter☆12Oct 1, 2026Updated 2 weeks ago
- Easy access to unsaved files for vscode.☆13Jul 10, 2025Updated last year
- Mirall - Secure large file transfer. No cloud. No middleman☆55Updated this week
- Convert Transkribus PAGE-XML to standard PAGE-XML☆12Dec 10, 2025Updated 10 months ago
- ☆82Sep 10, 2026Updated last month
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark (fork)☆45Oct 5, 2026Updated last week
- A project devoted to cleaner, simpler styling in Flutter.☆13Dec 7, 2019Updated 6 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.
- ☆50Updated this week
- Data and description for the dataset Digital Peter.☆12Sep 5, 2022Updated 4 years ago
- ☆20Apr 12, 2026Updated 6 months ago
- LLM inference in C/C++☆64Updated this week
- A simple Pong game in Flutter☆10Oct 19, 2019Updated 6 years ago
- Digital texts in Prakrit☆11Sep 14, 2025Updated last year
- ☆15Feb 10, 2020Updated 6 years ago
- OCR-D wrapper for prima-pagetopdf☆10Oct 30, 2025Updated 11 months ago
- Character-level conversion between Hebrew text and Latin transliteration using deep learning - a demonstration of seq2seq training.☆16Jun 27, 2023Updated 3 years 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.
- GLM-5.3-Flash NVFP4 on 4x NVIDIA DGX Spark: vLLM TP4, DFlash2 adaptive draft, measured FP8 vs NVFP4 vs EXL3 vs SGLang☆37Sep 29, 2026Updated 2 weeks ago
- State-of-the-art 1B OCR model - Local version of HuggingFace demo. Created by Claude Code, orchestrated by TheAwakenOne619.☆34Feb 10, 2026Updated 8 months ago
- A command line tool for translation of Flutter ARB files☆16Jul 3, 2026Updated 3 months ago
- CPU-GPU hybrid inference for DeepSeek-V4 on NVIDIA SM80+ (A100/RTX 4090 etc.), forked from yhfgyyf/vllm-deepseek-v4-sm89.☆60Sep 16, 2026Updated last month
- ☆46Jul 22, 2026Updated 2 months ago
- Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini P…☆189Updated this week
- llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): example: 95+ tok/s over a 100K-token gen…☆181Updated this week