hao-ai-lab/Consistency_LLM
Consistency Large Language Models (CLLMs) use Jacobi decoding to generate multiple tokens in parallel, dramatically reducing LLM inference latency.
Not currently ranked — collecting fresh signals.
star history
CLLMs are trained to map any randomly initialized n-token sequence to the same result as auto-regressive decoding in as few steps as possible. This enables efficient parallel decoding rather than the sequential token-by-token generation used in standard LLMs. The models demonstrate substantial generation speedups across various tasks while maintaining output quality.
Frequently asked
- What is hao-ai-lab/Consistency_LLM?
- Consistency Large Language Models (CLLMs) use Jacobi decoding to generate multiple tokens in parallel, dramatically reducing LLM inference latency.
- Is Consistency_LLM open source?
- Yes — hao-ai-lab/Consistency_LLM is open source, released under the Apache-2.0 license.
- What language is Consistency_LLM written in?
- hao-ai-lab/Consistency_LLM is primarily written in Python.
- How popular is Consistency_LLM?
- hao-ai-lab/Consistency_LLM has 415 stars on GitHub.
- Where can I find Consistency_LLM?
- hao-ai-lab/Consistency_LLM is on GitHub at https://github.com/hao-ai-lab/Consistency_LLM.