Skip to content

Issues: OpenNMT/CTranslate2

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.

Sign up for GitHub

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

118 Open 510 Closed
118 Open 510 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

opus-mt-en-zh does not respect the end token
#1694 opened May 11, 2024 by l3utterfly
Can't hide GPUs to get_cuda_device_count()
#1693 opened May 7, 2024 by mattiadg
2
How to compile from source on windows 11?
#1692 opened May 5, 2024 by ivanhe123
1
Unexpected inference results from Flan-T5 XXL converted to ctranslate2 with version 4.2.1 and 4.1.1 (using tensor parallel) bug Something isn't working
#1691 opened May 2, 2024 by gk-kd
4
target_prefix latency
#1689 opened Apr 30, 2024 by SimonBenhamou
2
New Llama3 sample script not working:
#1688 opened Apr 30, 2024 by BBC-Esq
3
Dynamic LoRA switching enhancement New feature or request
#1686 opened Apr 27, 2024 by MrigankRaman
1
Problem converting Phi3-instruct-128k; "su" rope scaling in Phi-3
#1685 opened Apr 26, 2024 by BBC-Esq
1
OpenELM Support
#1684 opened Apr 26, 2024 by jncraton
Build Ctranslate2 for android
#1683 opened Apr 26, 2024 by glory03023
[Feature Request] Support Epsilon Sampling enhancement New feature or request
#1681 opened Apr 25, 2024 by radinplaid
Anomalous T5 results using GPU inference on a 4090 graphics card
#1679 opened Apr 25, 2024 by taishan1994
3
[Feature Request] add a classification / estimation layer on top of Encoders enhancement New feature or request
#1678 opened Apr 25, 2024 by vince62s
1
BENCHmarking new flash attention!
#1676 opened Apr 24, 2024 by BBC-Esq
10
faster-whisper inferencing problem
#1673 opened Apr 24, 2024 by glory03023
2
Does fairseq transform align can returns the alignment result?
#1668 opened Apr 16, 2024 by itaybar
3
include/ctranslate2/ops/flash-attention/flash_fwd_launch_template.h(15): error: identifier "__grid_constant__" is undefined
#1664 opened Apr 12, 2024 by twmht
3
Asking about the return_scores during generation
#1661 opened Apr 10, 2024 by freyaya123
7
Error when converting NMT model with ALiBi or RoPe enhancement New feature or request question Further information is requested
#1657 opened Apr 7, 2024 by randomicity
15
Benchmarking Whisper on ctranslate2, llama.cpp, and bitsandbytes
#1650 opened Mar 27, 2024 by BBC-Esq
1
Support for Zephyr and other "StableLmForCausalLM" models?
#1649 opened Mar 26, 2024 by BBC-Esq
2
Whisper batch generation is not faster than loops
#1648 opened Mar 26, 2024 by evanarlian
5
translate_iterable is not properly handling max_input_length
#1646 opened Mar 24, 2024 by winstxnhdw
2
Intel Advanced Matrix Extensions (AMX) support enhancement New feature or request
#1632 opened Feb 29, 2024 by ahmetcanik
1
[INFO] cuDNN with fusions
#1629 opened Feb 23, 2024 by mnicely
1
ProTip! Add no:assignee to see everything that’s not assigned.