[go: up one dir, main page]
Skip to content

Pull requests: OpenNMT/CTranslate2

New pull request New
Clear current search query, filters, and sorts
28 Open 1,083 Closed
28 Open 1,083 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Directly register finalized model variables
#1058 opened Jan 27, 2023 by guillaumekln • Draft
Use non blocking CUDA streams
#1177 opened Apr 20, 2023 by guillaumekln • Draft
Manually destroy cuBLAS and cuDNN handles before threads exit
#1201 opened Apr 28, 2023 by guillaumekln • Draft
Keep FFN output layer in float32 for T5 models
#1239 opened May 23, 2023 by guillaumekln • Draft
3
Accept left offsets in the masked softmax operator
#1370 opened Jul 27, 2023 by guillaumekln • Draft
Accept left offsets in the rotary embeddings layer
#1372 opened Jul 27, 2023 by guillaumekln • Draft
Accept left offsets when applying position encodings
#1374 opened Jul 28, 2023 by guillaumekln • Draft
Accept variable-length batch prompts for Whisper
#1457 opened Sep 7, 2023 by guillaumekln • Draft
Add RoBERTaConfig to TransformerConverter
#1510 opened Oct 10, 2023 by bhavnicksm Loading…
2
convert opennmt py on the fly and inference with model in memory
#1578 opened Dec 6, 2023 by minhthuc2502 • Draft
build: armv7 and android static omp support
#1600 opened Jan 12, 2024 by ebraraktas Loading…
1
CANN Backend support
#1606 opened Jan 26, 2024 by 3manifold Loading…
1
3
Mixtral support
#1644 opened Mar 18, 2024 by minhthuc2502 • Draft
2
add rope alibi to encoder
#1687 opened Apr 29, 2024 by vince62s Loading…
17
Use specific CMAKE_CUDA_COMPILER instead of forcing CMake to use the same compiler for both CXX and CUDA
#1710 opened May 25, 2024 by alexlnkp Loading…
1
[*] improve log message for storage view content
#1718 opened Jun 4, 2024 by tirivo Loading…
5
[WIP] HQQ Quant 4 bit
#1738 opened Jul 8, 2024 by minhthuc2502 Loading…
Implement python bindings for profiler
#1739 opened Jul 8, 2024 by yehudaorel Loading…
1
1
IBM Power10 (VSX, MMA) support for ppc64le
#1748 opened Jul 25, 2024 by Dagamies Loading…
Converter falcon 2
#1750 opened Jul 30, 2024 by minhthuc2502 Loading…
Reintroduce support for GPUs with Compute Capability 5.0
#1766 opened Aug 27, 2024 by giuliopaci Loading…
Bump actions/download-artifact from 3 to 4.1.7 in /.github/workflows dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#1770 opened Sep 3, 2024 by dependabot bot Loading…
Accept variable-length batch prompts for Whisper
#1784 opened Sep 18, 2024 by MahmoudAshraf97 Loading…
21
Shallow Contextual Biasing for Whisper
#1789 opened Sep 23, 2024 by zwycl Loading…
Small improvements
#1801 opened Oct 16, 2024 by BBC-Esq Loading…
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.