Skip to content
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

83 Open 74 Closed
83 Open 74 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
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
运行Example中的ls_bert报错，TypeError: infer(): incompatible function arguments
#286 opened Mar 17, 2022 by zhouyonglong
1
output wrong
#284 opened Mar 10, 2022 by bino282
1
Support various sampling configuration (repetition_penalty, length_penalty etc)
#283 opened Mar 10, 2022 by codertimo
1
QuantTransformer inference error
#282 opened Mar 9, 2022 by dearchill
2
如何重新初始化模型
#279 opened Mar 7, 2022 by ckxkexing
1
FP32模式下通过源码编译安装问题
#271 opened Mar 1, 2022 by zejunwang1
2
According to Guidance , it occurs hydra errors when excuting training code of "sh examples/training/fairseq/ls_fairseq_wmt14en2de.sh"
#270 opened Feb 28, 2022 by loulianzhang
2
lightseq.inference has no attribute 'bert'
#266 opened Feb 14, 2022 by boxiaowave
4
Bug when decoder vocab size is small
#263 opened Jan 26, 2022 by anaivebird
1
about Bart export
#260 opened Jan 20, 2022 by lonelydancer
1
undefined symbol errors for libtransformer_server.so
#259 opened Jan 18, 2022 by kaierlong
8
bart topk sample result is wrong
#256 opened Jan 9, 2022 by lonelydancer
7
请问下现在支持unilm吗？ unilm的加速会跟encoder-decoder差不多吗
#254 opened Jan 6, 2022 by zhanghaoie
1
what is the difference between config.pbtxt in serving and config.yml generated in neurst training? How can I generate the config.pbtxt? Thanks...
#252 opened Dec 31, 2021 by ghtwht
1
when will lightdeq support Cuda 11.0?
#251 opened Dec 30, 2021 by YINGPENGZH
12
Can I get attention weights from lightseq?
#250 opened Dec 30, 2021 by King-Hell
1
need support of conformer
#248 opened Dec 23, 2021 by nemoramo
1
did lightseq compare with marian ?
#247 opened Dec 21, 2021 by butterluo
1
lightseq.Transformer这个类不存在，要怎么使用?transformer.cc.cu要怎么使用？
#246 opened Dec 21, 2021 by ljwmusclenlper
4
[Inference] Support GPT-J-6B
#245 opened Dec 20, 2021 by Leezekun
9
what about the vocab.txt of gpt2? Is it the same as bert 21128 words?
#244 opened Dec 20, 2021 by YINGPENGZH
3
mt5
#243 opened Dec 17, 2021 by xv44586
2
性能问题
#242 opened Dec 17, 2021 by 520jefferson
1
the same arch's num parameters in lightseq is different from fairseq
#239 opened Dec 13, 2021 by yzy5630
2
你好，当bert 采用 UNILM 方案做文本生成的时候 ，请问lightseq可以提供 beamsearch的加速功能嘛？
#232 opened Nov 26, 2021 by zcuuu
4
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.