forked from huggingface/text-generation-inference
-
Notifications
You must be signed in to change notification settings - Fork 43
Issues: huggingface/tgi-gaudi
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Incorrect answer with openai compatible penalty parameters
#238
opened Oct 17, 2024 by
Spycsh
2 of 4 tasks
Generation stopped too early without hitting stop condition
#223
opened Sep 18, 2024 by
minmin-intel
2 of 4 tasks
llama3.1-70B-instruct 422 error Template error: unknown test: test iterable is unknown (in <string>:99)
#218
opened Sep 3, 2024 by
minmin-intel
2 of 4 tasks
When running llama2 7b, inference some 2k length prompt concurrently will cause TGI service crash.
#216
opened Aug 30, 2024 by
yao531441
4 tasks
Best Performance for a single card for Llama-2-7b-chat-hf
#196
opened Jul 29, 2024 by
AdityaKulshrestha
setting token flags still results in console warning
#195
opened Jul 28, 2024 by
endomorphosis
2 of 4 tasks
low throughput while using TGI-Gaudi on bigcode/starcoderbase-3b on Gaudi2
#166
opened Jun 22, 2024 by
vishnumadhu365
3 of 4 tasks
ProTip!
no:milestone will show everything without a milestone.