LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
- cuda-kernels
- deepspeed
- fastertransformer
- llm-inference
54,641 visible repositories in the index
1–2 of 2 · Most stars
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Transformer related optimization, including BERT, GPT