Skip to content
Navigation Menu
Toggle navigation
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Spark
Build and deploy intelligent apps
GitHub Models
Manage and compare prompts
MCP Registry
New
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
Accelerator
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search or jump to...
Search code, repositories, users, issues, pull requests...
Search syntax tips
Provide feedback
Saved searches
Use saved searches to filter your results more quickly
Sign in
Sign up
Appearance settings
Resetting focus
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
ice0
/
CTranslate2
Public
forked from
OpenNMT/CTranslate2
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security
Insights
Commits
Breadcrumbs
History for
CTranslate2
tests
on
master
User selector
All users
All time
Commit History
Commits on Sep 13, 2024
Wav2Vec2Bert ASR Inference Support (#1778)
Show description for cb16c8e
homink
and
hkwon
authored
cb16c8e
Copy full SHA for cb16c8e
Commits on Aug 13, 2024
feat: grouped conv1d (#1749)
Show description for 1000086
ebraraktas
authored
1000086
Copy full SHA for 1000086
Commits on Mar 25, 2024
perf: conv1d quantization (#1601)
Show description for 8994330
ebraraktas
authored
8994330
Copy full SHA for 8994330
Commits on Aug 28, 2023
Vectorize GEMM output dequantization and fuse bias & activation (#1402)
Show description for f3e2ac6
guillaumekln
authored
f3e2ac6
Copy full SHA for f3e2ac6
Commits on Aug 2, 2023
Fix relative positions shape when forwarding a sequence in the decoder (#1395)
guillaumekln
authored
6973aa5
Copy full SHA for 6973aa5
Commits on Jul 27, 2023
Enable GPU tests for Alibi and RotaryEmbeddings layers (#1371)
guillaumekln
authored
892b354
Copy full SHA for 892b354
Commits on Jul 17, 2023
Support bfloat16 execution on the GPU (#1316)
Show description for 7218d48
guillaumekln
authored
7218d48
Copy full SHA for 7218d48
Commits on Jun 23, 2023
Revert "Include padding tokens when counting tokens with batch_type="tokens" (#1305)" (#1314)
Show description for e62675e
guillaumekln
authored
e62675e
Copy full SHA for e62675e
Vectorize copy in the Tile CUDA operator (#1308)
guillaumekln
authored
88682ae
Copy full SHA for 88682ae
Commits on Jun 21, 2023
Include padding tokens when counting tokens with batch_type="tokens" (#1305)
guillaumekln
authored
4dc7bdd
Copy full SHA for 4dc7bdd
Commits on Jun 14, 2023
Implement TopPMask operator (#1274)
Show description for ab35689
guillaumekln
authored
ab35689
Copy full SHA for ab35689
Commits on Jun 9, 2023
Cache the Alibi tensor (#1278)
guillaumekln
authored
8d5c9a6
Copy full SHA for 8d5c9a6
Fix error when calling generate_tokens with a static prompt (#1279)
guillaumekln
authored
0cfbc78
Copy full SHA for 0cfbc78
Commits on Jun 5, 2023
Fix a performance issue when using a model with ALiBi on the GPU (#1261)
guillaumekln
authored
fde6a6c
Copy full SHA for fde6a6c
Commits on May 22, 2023
Support the MPT model from MosaicML (#1228)
guillaumekln
authored
9ce09fe
Copy full SHA for 9ce09fe
Commits on Apr 25, 2023
Add option to keep the end token in the results (#1195)
guillaumekln
authored
6cdb0a8
Copy full SHA for 6cdb0a8
Commits on Apr 21, 2023
Implement fused rotary kernel (#1179)
Show description for ba78495
guillaumekln
authored
ba78495
Copy full SHA for ba78495
Commits on Apr 17, 2023
Raise an error if end_token or suppress_sequences contain OOV tokens (#1171)
guillaumekln
authored
89a6db1
Copy full SHA for 89a6db1
Add alternative rotary implementation that slices the head dimensions (#1168)
guillaumekln
authored
4881e74
Copy full SHA for 4881e74
Support variable number of frames in Whisper.align batch implementation (#1167)
guillaumekln
authored
f9d4030
Copy full SHA for f9d4030
Commits on Apr 6, 2023
Implement rotary embeddings and support the GPT-J model (#1158)
Show description for df48126
guillaumekln
authored
df48126
Copy full SHA for df48126
Commits on Mar 21, 2023
Fix parsing of escaped characters \x.. in the Marian vocabulary file (#1135)
Show description for 648a490
guillaumekln
authored
648a490
Copy full SHA for 648a490
Commits on Mar 15, 2023
Support BLOOM language models (#1128)
guillaumekln
authored
cbdd540
Copy full SHA for cbdd540
Commits on Mar 14, 2023
Add method Whisper.align to implement word-level timestamps (#1120)
Show description for 5f9aac6
guillaumekln
authored
5f9aac6
Copy full SHA for 5f9aac6
Commits on Mar 6, 2023
Rename method to_float() to to_float32() (#1114)
guillaumekln
authored
a21e4f4
Copy full SHA for a21e4f4
Commits on Feb 21, 2023
Rename float to float32 for clarity (#1092)
guillaumekln
authored
c9ae5ed
Copy full SHA for c9ae5ed
Commits on Feb 9, 2023
Add a beam search patience factor (#1073)
guillaumekln
authored
68e507c
Copy full SHA for 68e507c
Commits on Feb 8, 2023
Implement variants of the GELU activation (#1065)
Show description for be12bac
guillaumekln
authored
be12bac
Copy full SHA for be12bac
Commits on Dec 29, 2022
Add Tanh operator (#1033)
guillaumekln
authored
c8bb82b
Copy full SHA for c8bb82b
Commits on Dec 20, 2022
Add RMSNorm op (#1026)
Show description for e020385
guillaumekln
authored
e020385
Copy full SHA for e020385
Commits on Dec 9, 2022
Add option end_token to stop the decoding on a specific token (#1014)
guillaumekln
authored
f9ca83b
Copy full SHA for f9ca83b
Improve batch generation with the Whisper model (#1012)
Show description for 338aac9
guillaumekln
authored
338aac9
Copy full SHA for 338aac9
Commits on Dec 8, 2022
Fallback to a basic Conv1D implementation when oneDNN is missing (#1010)
Show description for 2dcdf57
guillaumekln
authored
2dcdf57
Copy full SHA for 2dcdf57
Generalize Gather op to support all cases where axis == batch_dims (#1011)
Show description for a8a9078
guillaumekln
authored
a8a9078
Copy full SHA for a8a9078
Commits on Dec 7, 2022
Add option suppress_sequences to prevent the generation of sequences (#1005)
Show description for 94350b0
guillaumekln
authored
94350b0
Copy full SHA for 94350b0
Pagination
Previous
Next
You can’t perform that action at this time.
