https://github.com/brontoguana/krasis
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
https://github.com/brontoguana/krasis
cpu-inference gguf-model-support gpu-inference high-performance-inference hybrid-inference inference-engine inference-optimization large-language-models llama-cpp-alternative llm-inference mixture-of-experts transformer
Last synced: 10 days ago
JSON representation
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
- Host: GitHub
- URL: https://github.com/brontoguana/krasis
- Owner: brontoguana
- License: other
- Created: 2026-02-09T17:54:07.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2026-04-01T12:52:40.000Z (27 days ago)
- Last Synced: 2026-04-03T04:53:10.296Z (25 days ago)
- Topics: cpu-inference, gguf-model-support, gpu-inference, high-performance-inference, hybrid-inference, inference-engine, inference-optimization, large-language-models, llama-cpp-alternative, llm-inference, mixture-of-experts, transformer
- Language: C++
- Homepage:
- Size: 372 MB
- Stars: 398
- Watchers: 8
- Forks: 21
- Open Issues: 15
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
Awesome Lists containing this project
- awesome-local-llm - krasis - a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware (Inference engines)