orthrus
by chiennv2000 · GitHub
Fast, lossless LLM inference via dual-view diffusion decoding.
⭐ Stars
460
🍴 Forks
20
📜 License
MIT
Commercial use OK📅 Created
2026
🔄 Last commit
2 mo ago
🏷️ Category
diffusion-language-models
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-21
📄 About
Fast, lossless LLM inference via dual-view diffusion decoding.
❓ Frequently asked questions
What is orthrus?
Fast, lossless LLM inference via dual-view diffusion decoding.
Is orthrus open source?
orthrus is an open-source project. It is released under the MIT license.
Is orthrus free?
Yes. orthrus is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/chiennv2000-orthrus.html)
🧬 Shares DNA with🧬 View the DNA map →
SqueezeLLM
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
★ 722 · efficient-inference
sharesefficient-inferencelarge-language-models
dLLM-RL
[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, poweri…
★ 512 · code-generation
sharesdiffusion-language-modelslarge-language-models
LLMCompiler
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
★ 1.9k · efficient-inference
sharesefficient-inferencelarge-language-models
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.