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

#1193 - Different output for inference running inside a docker container on CPU

Issue - State: closed - Opened by kafan1986 over 1 year ago - 1 comment

#1191 - Update Ruy submodule to commit 363f2522

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1190 - Llama 7B generator incorrectly creates sequence_ids from input tokens

Issue - State: closed - Opened by vancoykendall over 1 year ago - 1 comment

#1189 - Add token streaming example in the documentation

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1187 - Make callback argument public

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1186 - Support peft's LoRa for HF transformer models.

Issue - State: open - Opened by Palmik over 1 year ago - 4 comments
Labels: enhancement

#1185 - How much memory do I need to convert GPT-NeoX?

Issue - State: closed - Opened by palladium123 over 1 year ago - 2 comments

#1183 - Idea: support for embeddings

Issue - State: closed - Opened by janekb04 over 1 year ago - 10 comments

#1182 - Accept multiple tokens in argument end_token

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1181 - Importing `numpy` after `ctranslate2` causes segfault

Issue - State: open - Opened by janekb04 over 1 year ago

#1180 - Support GPT-NeoX architecture

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1179 - Implement fused rotary kernel

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1178 - Expose CTranslate2::ctranslate2 as CMake package

Pull Request - State: closed - Opened by HennerM over 1 year ago - 1 comment

#1177 - Use non blocking CUDA streams

Pull Request - State: open - Opened by guillaumekln over 1 year ago

#1176 - GPT-NeoX

Issue - State: closed - Opened by sudo-carson over 1 year ago - 1 comment
Labels: enhancement

#1175 - CUDA 12 Support

Issue - State: closed - Opened by jzju over 1 year ago - 3 comments

#1174 - Prevent generating segments with zero duration

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1172 - Also load weights as FP16 when converting to int8_float16

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1170 - Fix Whisper.align crash when num_frames//2 <= median_filter_width

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1169 - Idea: Add CoreML / Apple Neural Engine backend

Issue - State: open - Opened by janekb04 over 1 year ago

#1166 - Optimize quantization of FP16 weights during conversion

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1165 - Add method generate_tokens to return a generator of tokens

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1164 - Add note on Visual C++ runtime dependency on Windows

Pull Request - State: closed - Opened by jordimas over 1 year ago

#1163 - CTranslate2 missing dependency in Windows

Issue - State: closed - Opened by jordimas over 1 year ago - 1 comment

#1162 - Train Model Load

Issue - State: open - Opened by syngokhan over 1 year ago - 3 comments

#1161 - Token Streaming

Issue - State: closed - Opened by henyee over 1 year ago - 2 comments

#1159 - Clarify that the Docker image contains the required NVIDIA libs

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1158 - Implement rotary embeddings and support the GPT-J model

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1157 - Positional Encoding RuntimeError

Issue - State: closed - Opened by VarunGumma over 1 year ago - 1 comment

#1156 - how to convert other GPT-like models ? (or how to write my own converter)

Issue - State: closed - Opened by phineas-pta over 1 year ago - 3 comments

#1155 - Docker: exec format error on linux/arm64/v8

Issue - State: open - Opened by gcervantes8 over 1 year ago - 1 comment
Labels: enhancement

#1154 - Run error with ruy on AArch64

Issue - State: closed - Opened by MingyangW over 1 year ago - 8 comments

#1153 - Support float16 on ARM CPUs with native float16 support

Issue - State: open - Opened by FlippFuzz over 1 year ago - 3 comments
Labels: enhancement, cpu

#1151 - Unable to convert fairseq model

Issue - State: closed - Opened by bil-ash over 1 year ago - 3 comments

#1150 - Fix synchronization issue when the model input is a CUDA storage

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1149 - Apply new OpenNMT-py option decoder_start_token

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1148 - Enable the Ruy backend in Python wheels for macOS ARM64

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1147 - Select the correct device when copying a StorageView instance

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1145 - Add generation option include_prompt_in_result

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1144 - Add method Whisper.encode to cache and reuse the encoded features

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1143 - Remove unnecessary wrapper for the StorageView Python bindings

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1141 - Build a single instance of CudaAsyncAllocator

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1140 - Ideas for better performance

Issue - State: open - Opened by hobodrifterdavid over 1 year ago - 12 comments

#1139 - issue converting user fine-tuned whisper models

Issue - State: closed - Opened by laphang over 1 year ago - 2 comments

#1138 - Is there an example how to do CTranslate2 Whisper inference in C++ ?

Issue - State: closed - Opened by sv2 over 1 year ago - 1 comment

#1137 - How to verify if my local build has openMP support

Issue - State: closed - Opened by maxcribe over 1 year ago - 30 comments

#1136 - Fix condition in DTW backtrace

Pull Request - State: closed - Opened by guillaumekln over 1 year ago

#1127 - Faster llama

Issue - State: open - Opened by maiquangtuan over 1 year ago - 35 comments
Labels: enhancement

#1119 - Does batch inference introduce performance gains?

Issue - State: closed - Opened by ItakeLs over 1 year ago - 3 comments
Labels: question

#1113 - Get whisper's model result contain token score

Issue - State: closed - Opened by shumeirao over 1 year ago - 1 comment

#1104 - Int4 Support

Issue - State: open - Opened by fmac2000 over 1 year ago - 6 comments
Labels: enhancement

#1077 - Feature request: Word level scores

Issue - State: open - Opened by ItakeLs over 1 year ago - 11 comments
Labels: enhancement

#1075 - Will this work with stable-ts?

Issue - State: closed - Opened by bakermanbrian over 1 year ago - 5 comments

#1074 - Strange output of Flan-T5-Large when using float16 converted model

Issue - State: open - Opened by Matthieu-Tinycoaching over 1 year ago - 25 comments
Labels: enhancement

#1072 - Feature request: AMD GPU support with oneDNN AMD support

Issue - State: open - Opened by santhoshtr over 1 year ago - 43 comments
Labels: enhancement, help wanted

#1064 - Use of Flan-t5 for answer generation

Issue - State: closed - Opened by Matthieu-Tinycoaching over 1 year ago - 5 comments

#1052 - Splitting LLM layers across multiple GPUs

Issue - State: closed - Opened by JOHW85 over 1 year ago - 6 comments
Labels: enhancement

#1024 - Score: How to get translation `score`

Issue - State: closed - Opened by tahirahmad2030 almost 2 years ago - 3 comments
Labels: question

#1008 - Support encoder-only models like BERT

Issue - State: closed - Opened by guillaumekln almost 2 years ago - 9 comments
Labels: enhancement

#932 - TypeError: cannot pickle 'ctranslate2.translator.Translator' object

Issue - State: closed - Opened by Matthieu-Tinycoaching almost 2 years ago - 5 comments

#896 - Implement end_sequence for text generation

Issue - State: closed - Opened by juliensalinas about 2 years ago - 4 comments
Labels: enhancement

#835 - support different pre_norm and layernorm_embedding in TransformerSpec for EncoderDecoderModel huggingface

Issue - State: closed - Opened by nlpcat over 2 years ago - 4 comments
Labels: enhancement

#832 - Transformers Marian produces translation that ends in gibberish for multilingual models

Issue - State: closed - Opened by raphaelmerx over 2 years ago - 5 comments
Labels: bug

#796 - Support for RNN based decoder units

Issue - State: open - Opened by harishankar-gopalan over 2 years ago - 9 comments
Labels: enhancement

#693 - Can batch translation on CPU result in different output?

Issue - State: open - Opened by robertBrnnn over 2 years ago - 9 comments
Labels: question, cpu

#578 - Support speech-to-text Transformer model

Issue - State: closed - Opened by gfiameni almost 3 years ago - 7 comments
Labels: enhancement

#559 - Can Tensor2Tensor Export to Ctranslate2 Format?

Issue - State: closed - Opened by scotfang about 3 years ago - 5 comments
Labels: enhancement, help wanted

#375 - Vectorize GEMM output dequantization and fuse bias + ReLU

Issue - State: closed - Opened by guillaumekln over 3 years ago
Labels: enhancement, cpu

#355 - Support ARM 64-bit architecture

Pull Request - State: closed - Opened by keichi almost 4 years ago - 24 comments

#307 - Update README for next version PyPI

Pull Request - State: closed - Opened by guillaumekln almost 4 years ago

#182 - Experimental integration of MKL's packed GEMM

Pull Request - State: closed - Opened by guillaumekln over 4 years ago - 1 comment

#178 - Implement GPU TopK without TensorRT

Issue - State: closed - Opened by guillaumekln over 4 years ago - 8 comments
Labels: enhancement, help wanted, gpu

#5 - Support ONNX graphs

Issue - State: closed - Opened by guillaumekln about 5 years ago - 10 comments
Labels: enhancement