Skip to content

Issues: bytedance/lightseq

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

152 Open 106 Closed
152 Open 106 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

About inference speed compared to TRT16? [急急如律令]
#490 opened Mar 19, 2023 by xiao2mo
3
About Vit encoder output consistency during inference?
#488 opened Mar 16, 2023 by xiao2mo
@zjersey
2
[Running Fail] Assert failed at transformer_encoder_layer.py at line 342
#487 opened Mar 9, 2023 by AlexwellChen
en2fr和en2de的模型结构存在差异？
#485 opened Mar 8, 2023 by MeJerry215
2
有什么方法将fairseq transformer的weight 转换为 lightseq transformer的weight？
#484 opened Mar 7, 2023 by MeJerry215
GPU speedup vs CTranslate2
#469 opened Feb 20, 2023 by nghuyong
beam search
#455 opened Feb 13, 2023 by hg123-we
Performance measurement with Pytorch/MLIR, Tensorflow/XLA
#451 opened Jan 27, 2023 by Kangmo
1
转化之后的hdf5模型太大，lightseq 加载的时候支持多卡部署吗？
#450 opened Jan 16, 2023 by Liuchunyangboy
1
Is there a plan to support the T5-v1_1 model?
#448 opened Jan 9, 2023 by dengcunqin
1
How to use lightseq for bert's mlm training?
#446 opened Dec 30, 2022 by xiao12mm
2
[Question]: How to compile lightseq
#445 opened Dec 29, 2022 by FrostML
4
Possible memory leak in DecSelfAttentionLayer
#443 opened Dec 27, 2022 by Kangmo
2
Question : About construction of total_cache_k, total_cache_v in Transformer
#442 opened Dec 26, 2022 by Kangmo
4
How to ensemble lightseq models? & the memory usage is too big when generating
#440 opened Dec 21, 2022 by baoguo1995
3
Is it compatible with swin-t
#439 opened Dec 20, 2022 by Chaoran-F
1
export and infer fairseq transformer model
#438 opened Dec 13, 2022 by koukan3
4
[Triton] Multilingual Transformer Fails on 2nd request
#433 opened Nov 30, 2022 by Csinclair0
9
能否支持Fairseq 0.12.2版本
#431 opened Nov 29, 2022 by moseshu
2
Error assert emb_size % emb_dim == 0
#430 opened Nov 29, 2022 by moseshu
1
README里面的【Speedup of Transformer Inference】是哪个模型的，这边用里面的VIT用例测试的性能只有2.64倍？
#428 opened Nov 24, 2022 by Wayne-Bfx
4
Multi GPU triton failures
#427 opened Nov 22, 2022 by Csinclair0
4
What should I do if I want to use lightseq to accelerate MarianMTModel
#422 opened Nov 20, 2022 by Youggls
@zjersey
7
How to use test/ls_quant_bert.py?
#418 opened Nov 11, 2022 by gjm441
1
Is it possible to accelerate mbart by lightseq?
#416 opened Nov 4, 2022 by GongCQ
2
ProTip! Mix and match filters to narrow down what you’re looking for.