Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / OpenNMT/CTranslate2 issues and pull requests

#1660 - fix gemma bug

Pull Request - State: closed - Opened by minhthuc2502 11 months ago

#1659 - Fix to enter BestSampler route when temperature is 0.

Pull Request - State: closed - Opened by masa-oi 11 months ago - 1 comment

#1658 - [Gemma] GELU should be approx tanh not exact

Issue - State: closed - Opened by NeonBohdan 11 months ago - 2 comments

#1657 - Error when converting NMT model with ALiBi or RoPe

Issue - State: open - Opened by randomicity 11 months ago - 15 comments
Labels: enhancement, question

#1655 - int8 quantization not working

Issue - State: closed - Opened by homink 11 months ago - 1 comment

#1654 - When building from source missing C++ libraries

Issue - State: closed - Opened by anterart 11 months ago - 6 comments

#1653 - Deploying with model and tensor parallelism

Issue - State: closed - Opened by subhalingamd 11 months ago - 4 comments

#1652 - Trigger github action

Pull Request - State: closed - Opened by XomaDev 11 months ago - 1 comment

#1651 - Flash attention

Pull Request - State: closed - Opened by minhthuc2502 11 months ago - 3 comments

#1650 - Benchmarking common LLMs on ctranslate2, llama.cpp, and bitsandbytes

Issue - State: open - Opened by BBC-Esq 11 months ago - 1 comment

#1649 - Support for Zephyr and other "StableLmForCausalLM" models?

Issue - State: closed - Opened by BBC-Esq 11 months ago - 3 comments

#1648 - Whisper batch generation is not faster than loops

Issue - State: open - Opened by evanarlian 11 months ago - 5 comments

#1647 - Fix 'ValueError' in 'ct2-opennmt-py-converter' for Unsupported '--self_attn_type'

Pull Request - State: closed - Opened by chingizof 11 months ago - 2 comments

#1646 - `translate_iterable` is not properly handling `max_input_length`

Issue - State: open - Opened by winstxnhdw 11 months ago - 2 comments

#1645 - Support Translator with persistent cpu cache

Pull Request - State: closed - Opened by anterart 11 months ago - 2 comments

#1644 - Mixtral support

Pull Request - State: open - Opened by minhthuc2502 11 months ago - 2 comments

#1643 - Fix mistake in adding bias in TP mode

Pull Request - State: closed - Opened by minhthuc2502 11 months ago

#1642 - Translator.unload_model(to_cpu=True) takes long time

Issue - State: closed - Opened by anterart 11 months ago - 8 comments

#1641 - PROBLEM converting phi2, phi1.5, and phi1 models

Issue - State: closed - Opened by BBC-Esq 12 months ago - 8 comments

#1640 - Fix classifiers cuda 12

Pull Request - State: closed - Opened by minhthuc2502 12 months ago

#1639 - add t5encoderonly support

Pull Request - State: closed - Opened by BBC-Esq 12 months ago

#1638 - Bump version 4.1.0

Pull Request - State: closed - Opened by minhthuc2502 12 months ago

#1637 - Fix the shape of c in gemm ops with a transpose

Pull Request - State: closed - Opened by minhthuc2502 12 months ago

#1636 - [Converter] read variable by chunk if size > max value of int

Pull Request - State: closed - Opened by minhthuc2502 12 months ago

#1635 - Update the pip package

Issue - State: closed - Opened by mubeen-qlu 12 months ago - 1 comment

#1634 - System error while converting Aya101

Issue - State: closed - Opened by msharara1998 12 months ago - 4 comments

#1632 - Intel Advanced Matrix Extensions (AMX) support

Issue - State: open - Opened by ahmetcanik 12 months ago - 1 comment
Labels: enhancement

#1631 - Support Gemma model

Pull Request - State: closed - Opened by minhthuc2502 12 months ago - 3 comments

#1630 - Whisper models no longer work on Windows cuda after CTranslate2 4.0.0

Issue - State: closed - Opened by Pikurrot 12 months ago - 2 comments

#1629 - [INFO] cuDNN with fusions

Issue - State: open - Opened by mnicely 12 months ago - 1 comment

#1628 - Problem with GPU allocation after updating to CTranslate2 4.0.0

Issue - State: closed - Opened by carolinaxxxxx almost 1 year ago - 1 comment

#1627 - Please support gemma arch

Issue - State: closed - Opened by NeonBohdan almost 1 year ago - 8 comments

#1626 - When is flash attention supported

Issue - State: closed - Opened by dingjingzhen about 1 year ago - 3 comments

#1625 - Please add Unbabel Tower - Translation Model support

Issue - State: closed - Opened by carolinaxxxxx about 1 year ago

#1624 - update GPU supported info for package

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago

#1623 - Update changelog for new release 4.0.0

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago

#1622 - Fix regression of perf after mistral dev

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago - 1 comment

#1621 - LLAMA: Get tokens in the range of the vocab size

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago

#1620 - Likely bug: log_prob is not affected by sampling_temperature

Issue - State: closed - Opened by YuchenLi01 about 1 year ago - 1 comment

#1619 - nning this:

Issue - State: closed - Opened by silvacarl2 about 1 year ago - 2 comments

#1617 - Asynchronous execution: High latency when retrieving results

Issue - State: open - Opened by mvidela31 about 1 year ago - 1 comment

#1616 - Output tokens logits

Issue - State: open - Opened by SimonBenhamou about 1 year ago - 15 comments

#1615 - DirectML Support

Issue - State: open - Opened by gdiaz384 about 1 year ago - 3 comments
Labels: enhancement

#1614 - Support sequence_bias when decoding

Issue - State: open - Opened by mc-marcocheng about 1 year ago

#1613 - v3.24 examples/wngt2020 reply on missing header: ctranslate2/translator_pool.h

Issue - State: closed - Opened by wcdr about 1 year ago - 3 comments

#1612 - Failed to convert fine-tuned whisper large-v2 model

Issue - State: closed - Opened by yaoandy107 about 1 year ago - 2 comments

#1611 - Implement to_device() for python bindings, add unit tests

Pull Request - State: closed - Opened by ozancaglayan about 1 year ago - 9 comments

#1610 - Exception when using some T5 model

Issue - State: open - Opened by Horikitasaku about 1 year ago - 1 comment

#1609 - [Feature] CANN Backend support

Issue - State: open - Opened by 3manifold about 1 year ago

#1608 - Exported OpenNMT models producing unexpected prediction lengths

Issue - State: closed - Opened by dmar1n about 1 year ago - 1 comment

#1607 - MPS Support for Mac Apple Silicon?

Issue - State: open - Opened by AdamEXu about 1 year ago - 5 comments
Labels: enhancement

#1606 - CANN Backend support

Pull Request - State: open - Opened by 3manifold about 1 year ago - 3 comments

#1605 - Whisper encodings differ in batch vs serial

Issue - State: open - Opened by ExarchD about 1 year ago

#1604 - Can install CTranslate2 in ppc64?

Issue - State: open - Opened by jesulo about 1 year ago - 1 comment

#1603 - OpenVino GPU plugin support

Issue - State: closed - Opened by hlevring about 1 year ago - 1 comment

#1602 - Qwen Support

Issue - State: closed - Opened by Vincent131499 about 1 year ago - 4 comments

#1601 - perf: conv1d quantization

Pull Request - State: closed - Opened by ebraraktas about 1 year ago - 11 comments

#1600 - build: armv7 and android static omp support

Pull Request - State: open - Opened by ebraraktas about 1 year ago - 1 comment

#1599 - support tensor parallel

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago - 1 comment

#1598 - feat: add ruy sgemm implementation

Pull Request - State: closed - Opened by ebraraktas about 1 year ago - 4 comments

#1597 - perf: implement Conv1D with im2col and GEMM

Pull Request - State: closed - Opened by ebraraktas about 1 year ago - 4 comments

#1596 - bump version v3.24.0

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago

#1595 - Chat example and TinyLlama/TinyLlama-1.1B-Chat-v1.0

Issue - State: closed - Opened by AIWintermuteAI about 1 year ago - 1 comment

#1594 - feature request: support 4d attention masks

Issue - State: open - Opened by poedator about 1 year ago

#1593 - Mixtral-8x7B support

Issue - State: closed - Opened by tobrun about 1 year ago - 3 comments

#1592 - Support of new option offset to ignore token score of special tokens

Pull Request - State: closed - Opened by ASenart about 1 year ago - 2 comments

#1591 - sqlcoder (7b) from mistral model

Issue - State: closed - Opened by JunHyungKang about 1 year ago - 1 comment

#1590 - update cuda 11.2 to cuda 12.2

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago - 21 comments

#1589 - model to translate fron latin to spanish

Issue - State: closed - Opened by halaneji about 1 year ago - 1 comment

#1588 - faster_whisper batch operation time-consuming

Issue - State: open - Opened by dyyzhmm about 1 year ago - 9 comments

#1587 - Yi-6B-Chat convert failed.

Issue - State: closed - Opened by ninehills about 1 year ago - 1 comment

#1586 - Can we support CoreML of apple silicon?

Issue - State: open - Opened by ILG2021 about 1 year ago

#1585 - updated documentation

Issue - State: closed - Opened by BBC-Esq about 1 year ago - 1 comment
Labels: documentation

#1584 - Bad Performance after convert the OpenNMT-py model to ct2 model

Issue - State: closed - Opened by CreamyLong about 1 year ago - 4 comments

#1582 - Prefix tokens are ignored during translation with NLLB model

Issue - State: closed - Opened by winstxnhdw about 1 year ago - 1 comment

#1581 - fix onmt converter

Pull Request - State: closed - Opened by vince62s about 1 year ago

#1580 - [Feature request] providing C API

Issue - State: closed - Opened by hellodword about 1 year ago - 1 comment

#1579 - All samples are the same if include_prompt_in_result=False

Issue - State: closed - Opened by darabos about 1 year ago - 2 comments

#1576 - finetuned whisper model can not use “initial_prompt”

Issue - State: open - Opened by v-yunbin about 1 year ago - 1 comment

#1575 - [Feature request] Allowing StorageView.to() method to support moving between devices

Issue - State: closed - Opened by AtomAnu about 1 year ago - 5 comments
Labels: enhancement

#1574 - bump v3.23.0

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago

#1573 - Can someone update the latest version on pypi ?

Issue - State: closed - Opened by PL508 about 1 year ago

#1572 - fix forward batch

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago - 1 comment

#1571 - Support for core42/jais-13b-chat (Arabic LLM)

Issue - State: open - Opened by Apoorv7092 about 1 year ago - 4 comments

#1570 - Mistral errors when doing forward_batch

Issue - State: closed - Opened by NeonBohdan about 1 year ago

#1568 - Adding PhiConfig

Pull Request - State: closed - Opened by michaelfeil about 1 year ago - 8 comments

#1567 - Context Extension with Ctranslate2

Issue - State: open - Opened by pranavbhat12 about 1 year ago - 1 comment

#1566 - Inefficient tokens suppression during BeamSearch

Issue - State: open - Opened by rilshok about 1 year ago - 1 comment

#1565 - check alignment_heads in gen config before using

Pull Request - State: closed - Opened by minhthuc2502 about 1 year ago - 1 comment

#1564 - 'GenerationConfig' object has no attribute 'alignment_heads'

Issue - State: closed - Opened by takenori-y about 1 year ago - 3 comments

#1563 - CUDA 12.1 support coming and CUBLAS and CUDNN?

Issue - State: closed - Opened by BBC-Esq about 1 year ago - 2 comments

#1562 - ValueError: unsupported device mps

Issue - State: open - Opened by jk2K about 1 year ago - 1 comment

#1561 - bump v3.22.0

Pull Request - State: closed - Opened by nguyendc-systran about 1 year ago