Pinned issues
Issues
- 1
- 1
Linker Failing when Building Python Wheel
#1838 opened by ab-tools - 1
adopt modern bert please!
#1837 opened by BBC-Esq - 1
falcon3 support please?
#1834 opened by BBC-Esq - 0
add exaone pretty please?
#1836 opened by BBC-Esq - 0
Phi4 support please?
#1835 opened by BBC-Esq - 0
FP16 support for CPU devices
#1833 opened by Narfi03 - 0
[QUESTION] [MULTI-TO-MULTI] How specify source and target language with mBart (multi-to-multi) from C++ to translate text...
#1831 opened by wcdr - 1
Reintroduce support for Compute Capability 5.0
#1765 opened by giuliopaci - 11
CUDNN 9 support
#1780 opened by AndrewMead10 - 25
- 2
Cannot install CTranslate2
#1817 opened by victorwoo - 0
OPENCL / CLBLAST support?
#1829 opened by 0wwafa - 0
Support X-ALMA 🤖 Quality Translation at Scale
#1828 opened by carolinaxxxxx - 2
Support EuroLLM 🤖
#1827 opened by carolinaxxxxx - 7
NO LOGITS RETURNS AFTER GENERATE
#1779 opened by LAnCeBabY - 2
libcudnn_cnn problem
#1826 opened by 781574155 - 2
- 0
Whisper model returns empty logits array
#1822 opened by MahmoudAshraf97 - 1
Use multiple GPUs to process queue
#1816 opened by theodufort - 6
Performance Regression in Whisper models when timestamp generation is enabled
#1783 opened by MahmoudAshraf97 - 1
RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version
#1814 opened by SwAt1563 - 1
Possible premature temporary removal of flash attention?
#1809 opened by BBC-Esq - 2
- 0
Hope Moshi model can be supported
#1813 opened by YLQY - 0
pkg_resources going to be phased out I think?
#1812 opened by BBC-Esq - 3
correct docs regarding flash attention
#1777 opened by BBC-Esq - 20
A question regarding Faster Whisper
#1802 opened by MahmoudAshraf97 - 0
Use C++ for text generation tasks
#1804 opened by JocelynPanPan - 1
- 0
- 9
How to use 4-bit AWQ?
#1776 opened by BBC-Esq - 3
Release 4.4.0 and flash attention with python [WIP]
#1775 opened by BBC-Esq - 0
How to deploy the NLLB model exported from CTranslate2 framework to Android?
#1799 opened by LiPengtao0504 - 3
Mistral-Nemo not working
#1793 opened by BBC-Esq - 0
NLLB translation mask or skip some tokens
#1798 opened by ekmekovski - 0
OpenBLAS ERROR
#1797 opened by JocelynPanPan - 2
Error when converting llama-3.2-11b-vision-instruct
#1794 opened by AlexMisiulia - 6
Using a partitioned A100 GPU via MIG with device_index and faster_index causing ctranslate2 error
#1788 opened by johnrisby - 0
Missing converter : XLMRobertaFlashConfig
#1790 opened by ExtReMLapin - 0
Model is twice as large on first load
#1787 opened by winstxnhdw - 2
- 3
How to early stop an encoding call?
#1768 opened by mariano54 - 1
build failed on jetson agx orin (Error generating file: build/CMakeFiles/ctranslate2.dir/src/ops/flash-attention/./ctranslate2_generated_flash_fwd_split_hdim96_fp16_sm80.cu.o)
#1771 opened by cyu021 - 0
Can I convert a ctranslate2 model to onnx?
#1773 opened by ashwingopinath - 2
- 1
Error while converting to Ctranslate2 from openNMTPy.
#1767 opened by aryan1165 - 0
Failed to convert microsoft/Phi-3-medium-128k-instruct
#1764 opened by rbgo404 - 0
Support for DeepSeek models
#1763 opened by ByteForge786 - 0