Skip to content

Issues: SJTU-IPADS/PowerInfer

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

72 Open 58 Closed
72 Open 58 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

Why AXPY? question Further information is requested
#185 opened May 13, 2024 by richardweii
关于在A100显卡上测得的效果异常的疑问 question Further information is requested
#184 opened May 4, 2024 by bulaikexiansheng
1
请问大神有支持LLama 3 70B 的计划吗？ enhancement New feature or request
#183 opened May 1, 2024 by xiasw81
在A100-80G上无法找到cuda的情况 question Further information is requested
#182 opened Apr 24, 2024 by bulaikexiansheng
2
Where is the definition or addition location of GGML_USE_HYBRID_THREADING? question Further information is requested
#172 opened Mar 25, 2024 by wfloveiu
2
two questions that i want to solve question Further information is requested
#167 opened Mar 18, 2024 by yeptttt
2
Will we have instruct fine-tuned model support in the future? question Further information is requested
#164 opened Mar 13, 2024 by ZeonfaiHo
3 tasks done
1
[Question]: High PPL on wikitext2 of ReLU-LLAMA-7B for language modeling tasks question Further information is requested
#162 opened Mar 11, 2024 by llCurious
3 tasks done
2
24GB的显存只能占用12GB，CUDA占用也不到10%。但是CPU占用100%内存占用35GB question Further information is requested
#159 opened Mar 3, 2024 by NerounCstate
1
[ROCm] Is AMD ROCm support available in near future? enhancement New feature or request
#158 opened Feb 29, 2024 by Orion-zhen
3 tasks done
3
The CUDA compiler identification is unknown And PowerInfer was compiled without cuBLAS question Further information is requested
#157 opened Feb 29, 2024 by LHQUer
1
是否有计划兼容openai API风格的计划？
#155 opened Feb 27, 2024 by shmily91
1
关于token生成速率的计算问题
#150 opened Feb 22, 2024 by bulaikexiansheng
3
Please make a tinyllama v1.0 version for use.
#148 opened Feb 20, 2024 by kolinfluence
1
关于LLaMA-70B-PowerInfer-GGUF的chat版本 question Further information is requested
#143 opened Feb 6, 2024 by NerounCstate
1
possible to do one that can fit into 7GB vram? question Further information is requested
#141 opened Feb 4, 2024 by sprappcom
2
Will using only CPU be faster than llama.cpp? question Further information is requested
#140 opened Feb 2, 2024 by liutt1312
1
How to understand the codes of llama.cpp? question Further information is requested
#130 opened Jan 24, 2024 by BHbean
2
not enough space in the buffer with long prompts bug-unconfirmed Unconfirmed bugs
#129 opened Jan 23, 2024 by RachelShalom
3 tasks done
2
BenchMark 复现遇到了问题 question Further information is requested
#128 opened Jan 23, 2024 by wahaha22
8
how to show the outputs result on a web-service? or how can i get the result of inferrence for other application? question Further information is requested
#126 opened Jan 22, 2024 by xujiangyu
2 of 3 tasks
3
provided PTX was compiled with an unsupported toolchain
#122 opened Jan 16, 2024 by thangld201
1
Benchmarks question Further information is requested
#121 opened Jan 15, 2024 by hasanar1f
2
where can I download the predictor of Relu-Falcon-40B (float16)? question Further information is requested
#120 opened Jan 15, 2024 by chenglimin
7
No CUDA toolset found question Further information is requested
#119 opened Jan 15, 2024 by c469591
5
ProTip! Exclude everything labeled bug with -label:bug.