vLLM support?
#5 opened 1 day ago
by
GLECO
Use torch.inference_mode() and disable gradient checkpointing
#4 opened 29 days ago
by
prathamj31
Fix config.json for batching
#3 opened about 2 months ago
by
HatimF
Integrate with Transformers & Sentence Transformers
🤝
2
#2 opened about 2 months ago
by
tomaarsen
Update README.md
#1 opened about 2 months ago
by
ghita-ha