issues
search
ELS-RD
/
transformer-deploy
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
https://els-rd.github.io/transformer-deploy/
Apache License 2.0
1.65k
stars
150
forks
source link
Fix/update Triton + ORT
#116
Closed
pommedeterresautee
closed
2 years ago
pommedeterresautee
commented
2 years ago
update Triton docker image (ORT 1.12.0)
fix bug in tokenizer padding
update text + fix T5 notebook following #114 and release of ORT 1.12.0
fix a bug and fix TRT warnings (raised by 8.4 version)
pin some dependency versions following remarks from @gaetansnl
fix #117
ayoub-louati
commented
2 years ago
I added the last commit to fix the model path
fix #117