Nothing Special   »   [go: up one dir, main page]
Skip to content

Issues: Adlik/Adlik

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

25 Open 156 Closed
25 Open 156 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
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

Intel Gaudi environment
#664 opened Aug 13, 2024 by JieUpup
Adlik support FastTransformer for deploying GPT model enhancement New feature or request
#661 opened Mar 22, 2023 by amadeus-zte
@shiyingjin
Adlik Serving should support GPT model, make it convenient to use.
#657 opened Feb 27, 2023 by amadeus-zte
@shiyingjin
Support convert Pytorch or TF model to Enflame model directly through Adlik compiler work in progress
#642 opened Dec 22, 2022 by amadeus-zte
@shiyingjin @shimei0203
1
Adlik serving support to run original runtime model without Adlik compiler. enhancement New feature or request
#560 opened Mar 3, 2022 by amadeus-zte
@shiyingjin
Failed to convert torch model to onnx format model bug Something isn't working
#545 opened Nov 30, 2021 by XueweiHan21
@shiyingjin @nengyinyibeiwu
Adlik serving can not run faster_rcnn model when batch size > 1 with openvino runtime. bug Something isn't working
#543 opened Nov 18, 2021 by EmberYS
@EmberYS
Cannot compile onnx model to tf serving, error message "Path not found"
#538 opened Nov 9, 2021 by XueweiHan21
添加中文文档 documentation Improvements or additions to documentation
#532 opened Oct 29, 2021 by ITU-AIChallenge-ZTE
@shiyingjin
Adlik support ONNX runtime enhancement New feature or request
#526 opened Oct 14, 2021 by amadeus-zte
@shiyingjin
Adlik support to search tvm schedule
#525 opened Oct 14, 2021 by amadeus-zte
Could autotvm search best performance with int8-format weight and activation? enhancement New feature or request
#524 opened Oct 14, 2021 by amadeus-zte
@shiyingjin
Adlik support Xilinx device enhancement New feature or request
#523 opened Oct 14, 2021 by amadeus-zte
@shiyingjin
checkpoint到其他模型不能正确的显示Path not Found
#512 opened Aug 30, 2021 by 94Bo
Why are the tail latency of one picture in benchmark mostly equal ?
#507 opened Aug 23, 2021 by mistoFENG
@mistoFENG @XueweiHan21
Support custom-defined ops in openvino deferred
#501 opened Jul 29, 2021 by amadeus-zte
Use TF-TRT on NVIDIA T4 GPU to perform fasterrcnn model inference error
#497 opened Jul 26, 2021 by XueweiHan21
Support detectron2 model--faster-rcnn
#437 opened Apr 12, 2021 by amadeus-zte
@XueweiHan21 @ChengcanWang-zte
对Windows平台部署的支持 deferred enhancement New feature or request
#396 opened Jan 5, 2021 by OneWayCat
3
Please provide formal external interface document. documentation Improvements or additions to documentation
#391 opened Dec 19, 2020 by amadeus-zte
@KellyZhang2020
Adlik should support AMD GPU hardware. deferred enhancement New feature or request
#256 opened Aug 11, 2020 by amadeus-zte
@shiyingjin
Make predict interface no longer rely on tensorflow deferred enhancement New feature or request
#232 opened Jul 23, 2020 by shiyingjin
@shiyingjin
Suggest new features deferred
#226 opened Jul 16, 2020 by AIIABenchmark
@shiyingjin
2
Refactor model_config.proto becames essential when there are more and more runtimes enhancement New feature or request
#137 opened Apr 26, 2020 by shiyingjin
Add more CI tests for building on macOS enhancement New feature or request
#40 opened Oct 29, 2019 by EFanZh
1 of 6 tasks
ProTip! Follow long discussions with comments:>50.