Performance when using Ctranslate for GPT2?
|
|
0
|
591
|
December 13, 2023
|
OpenNMT-py v3.4.3 released - blazing fast beam search inference
|
|
4
|
1058
|
June 15, 2024
|
Need support for Continuous batching of incoming requests
|
|
1
|
669
|
September 19, 2023
|
Single words incorrect translation
|
|
3
|
901
|
July 28, 2023
|
Cannot scale well with multiple GPUs
|
|
32
|
5005
|
November 8, 2022
|
General questions to improve performance
|
|
10
|
1490
|
October 28, 2022
|
Sentencepiece decoder working inconsistently
|
|
3
|
770
|
June 14, 2022
|
OpeNMT-tf memory error
|
|
7
|
690
|
May 16, 2022
|
Deploying ctranslate2 on production
|
|
1
|
1283
|
April 25, 2022
|
OpenNMT-tf with Ampere GPUs
|
|
11
|
1791
|
April 14, 2022
|
Transformer Parameters for Low-Resource Machine Translation
|
|
0
|
1780
|
March 21, 2022
|
CTranslate2 generate a vocabulary mapping file of M2M100
|
|
1
|
1104
|
February 4, 2022
|
CUDA Out-of-memory issue with horovod
|
|
7
|
2573
|
November 30, 2021
|
Translation example from OpenNMT documentation
|
|
3
|
1296
|
September 14, 2021
|
Shared Vocab usage & workflow
|
|
2
|
1942
|
August 14, 2021
|
Decreasing run time
|
|
2
|
1240
|
April 25, 2021
|
Training performance boost with OpenNMT-tf v2.17.0!
|
|
4
|
1246
|
March 23, 2021
|
Lesser BLEU score compared to Fairseq
|
|
5
|
3443
|
September 10, 2020
|
Language Model Accuracy
|
|
1
|
1198
|
August 21, 2020
|
Reduction in size of checkpoints: `--train_from` arg
|
|
3
|
1084
|
August 12, 2020
|
ONMT multiprocess inference on CPU in production
|
|
3
|
2317
|
July 10, 2020
|
Fast CPU decoding
|
|
3
|
2813
|
October 11, 2019
|
Linguistic features surprisingly decrease the performance!
|
|
19
|
5720
|
May 14, 2019
|
Does converting trained model from FP32 to FP16 improve inference performance?
|
|
2
|
3232
|
April 30, 2019
|
Multi-GPUs is slower than single GPU
|
|
12
|
6814
|
April 16, 2019
|
Advice on new GPU
|
|
10
|
2337
|
January 1, 2019
|
Translating huge number of sentences
|
|
2
|
1316
|
December 12, 2018
|
What is the relationship between ppl, accuracy and bleu scores in machine translation? In my experiment, although ppl and accuracy on the validationset are greatly improved, Bleu scores is reduced
|
|
0
|
3043
|
November 25, 2018
|
Is the speed of CTranslate faster than that of lua version?
|
|
13
|
3452
|
June 18, 2018
|
Why Lua/Torch? (Please don't hate me for this question.)
|
|
8
|
13219
|
June 4, 2018
|