issues
search
OpenNMT
/
CTranslate2
Fast inference engine for Transformer models
https://opennmt.net/CTranslate2
MIT License
3.25k
stars
287
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Error when converting llama-3.2-11b-vision-instruct
#1794
AlexMisiulia
opened
1 hour ago
0
Mistral-Nemo not working
#1793
BBC-Esq
opened
15 hours ago
0
Run Phi3.5's "longrope" RoPE scaling type to make Phi3.5 compatible
#1792
BBC-Esq
opened
20 hours ago
0
fix crashing on cpu
#1791
minhthuc2502
opened
3 days ago
0
Missing converter : XLMRobertaFlashConfig
#1790
ExtReMLapin
opened
5 days ago
0
Shallow Contextual Biasing for Whisper
#1789
zwycl
opened
6 days ago
0
Using a partitioned A100 GPU via MIG with device_index and faster_index causing ctranslate2 error
#1788
johnrisby
opened
6 days ago
1
Model is twice as large on first load
#1787
winstxnhdw
opened
1 week ago
0
fix logits vocab
#1786
minhthuc2502
closed
4 days ago
2
Mistral nemo
#1785
minhthuc2502
closed
1 week ago
0
Accept variable-length batch prompts for Whisper
#1784
MahmoudAshraf97
opened
1 week ago
15
Performance Regression in Whisper models when timestamp generation is enabled
#1783
MahmoudAshraf97
opened
1 week ago
2
Python process crashes on exit under Windows with CUDA
#1782
TechInterMezzo
opened
1 week ago
1
Difference translation result after convert to ctranslate
#1781
hieunguyenquoc
opened
1 week ago
2
CUDNN 9 support
#1780
AndrewMead10
opened
2 weeks ago
4
NO LOGITS RETURNS AFTER GENERATE
#1779
LAnCeBabY
opened
2 weeks ago
5
Wav2Vec2Bert ASR Inference Support
#1778
homink
closed
2 weeks ago
6
correct docs regarding flash attention
#1777
BBC-Esq
opened
2 weeks ago
3
How to use 4-bit AWQ?
#1776
BBC-Esq
opened
2 weeks ago
9
Release 4.4.0 and flash attention with python [WIP]
#1775
BBC-Esq
opened
2 weeks ago
2
bump version 4.4.0
#1774
minhthuc2502
closed
2 weeks ago
0
Can I convert a ctranslate2 model to onnx?
#1773
ashwingopinath
opened
3 weeks ago
0
support minimum gemma 2
#1772
minhthuc2502
closed
3 weeks ago
0
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
cyu021
opened
3 weeks ago
1
Bump actions/download-artifact from 3 to 4.1.7 in /.github/workflows
#1770
dependabot[bot]
opened
3 weeks ago
0
Inference failed with "axis 2 has dimension xxxx but expected yyyy" error
#1769
GangLiCN
opened
3 weeks ago
2
How to early stop an encoding call?
#1768
mariano54
closed
2 weeks ago
3
Error while converting to Ctranslate2 from openNMTPy.
#1767
aryan1165
opened
1 month ago
1
Reintroduce support for GPUs with Compute Capability 5.0
#1766
giuliopaci
opened
1 month ago
0
Reintroduce support for Compute Capability 5.0
#1765
giuliopaci
opened
1 month ago
1
Failed to convert microsoft/Phi-3-medium-128k-instruct
#1764
rbgo404
opened
1 month ago
1
Support for DeepSeek models
#1763
ByteForge786
opened
1 month ago
0
Convert Ctranslate2 model to Pytorch or TorchScript or PyTorch Lightning
#1762
aryan1165
opened
1 month ago
0
Convert model.bin (fp32) to model.bin (int8)
#1761
aryan1165
opened
1 month ago
4
Bart models missing "embed_scale"
#1760
l3utterfly
opened
1 month ago
1
When I run online for a long time, the gpu memory will get bigger and bigger
#1759
dingjingzhen
opened
1 month ago
0
Wav2Vec2 upgrade with Conv1D options
#1758
homink
closed
1 month ago
3
set_random_seed does not make temperature based decoding deterministic
#1757
ozancaglayan
opened
1 month ago
2
Support for ARM64 on Windows
#1756
JanVlietinck
opened
1 month ago
3
Add log probs for all tokens
#1755
minhthuc2502
closed
1 month ago
0
Docker images not published
#1754
ales-t
closed
1 month ago
2
CI failing in the several recent PRs
#1753
homink
closed
1 month ago
2
Flash Attention regurgitates repeated tokens - seq2seq
#1752
ArtanisTheOne
opened
1 month ago
1
fix: implement llama3 RoPE scaling type and fix converter
#1751
ebraraktas
closed
1 month ago
6
Converter falcon 2
#1750
minhthuc2502
opened
2 months ago
0
feat: grouped conv1d
#1749
ebraraktas
closed
1 month ago
9
IBM Power10 (VSX, MMA) support for ppc64le
#1748
Dagamies
opened
2 months ago
0
Fix CI
#1747
minhthuc2502
closed
1 month ago
0
Bump torch from 2.1.0 to 2.2.0 in /python/tests
#1746
dependabot[bot]
closed
1 month ago
0
Llama 3.1 support please?
#1745
BBC-Esq
closed
1 month ago
2
Next