Skip to content

Issues: SJTU-IPADS/PowerInfer

Beta
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

113 Open 76 Closed
113 Open 76 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

Predictor training details question Further information is requested
#255 opened May 13, 2025 by WayneKe-Giftjoker
合作咨询
#254 opened May 12, 2025 by dingtine
1
section 6.3.1, computational constraint is not implemented question Further information is requested
#253 opened Apr 27, 2025 by jaeyoon-enerzai
Architecture "SparseLlamaForCausalLM" not supported! question Further information is requested
#252 opened Apr 18, 2025 by fxnie
Your LoRA file question Further information is requested
#251 opened Apr 16, 2025 by kimjoohyungsd
Question on GGUF file question Further information is requested
#250 opened Apr 15, 2025 by kimjoohyungsd
Support for deepseekV3 enhancement New feature or request
#249 opened Mar 29, 2025 by sorasoras
3 tasks done
请问下离线部分预测器的代码有开源吗 question Further information is requested
#248 opened Mar 18, 2025 by BenetnaschAlkaid
Fix incorrect sorting of activation_files causing improper FFN offload bug-unconfirmed Unconfirmed bugs
#247 opened Mar 11, 2025 by prisem123
3 tasks done
1
Is it possible to run DeepSeek-R1-Distill-Llama-70B or a 4-bit quantified version on consumer grade computers? This is of great significance question Further information is requested
#244 opened Feb 13, 2025 by wusu2016
1
A More User-Friendly Command-Line Interface
#238 opened Jan 25, 2025 by wisman-tccr
Does my PCIe degradation affects my inference speed? I have already deployed PowerInfer successfully, but encountered a PCIe degradation problem. question Further information is requested
#237 opened Jan 23, 2025 by victayria77
2
Where are the weights of the sparse predictor? question Further information is requested
#236 opened Jan 10, 2025 by Yues007
1
Which version of falcon-40b model used in llama.cpp reference in the demo? question Further information is requested
#235 opened Dec 25, 2024 by wuooo339
3 tasks done
How to OPT model with PowerInfer? question Further information is requested
#234 opened Dec 24, 2024 by wuooo339
3 tasks done
6
llama-7b-relu.powerinfer.gguf 进行 q8_0 量化后推理结果全是### question Further information is requested
#233 opened Dec 23, 2024 by JocelynPanPan
Error: the provided PTX was compiled with an unsupported toolchain bug-unconfirmed Unconfirmed bugs
#229 opened Nov 3, 2024 by jiangzizi
3 tasks done
about the use of OPT model question Further information is requested
#228 opened Oct 21, 2024 by bobzhang208
add new model in power-infer2 question Further information is requested
#227 opened Oct 21, 2024 by Francis235
1
Qualcomm chips support question Further information is requested
#226 opened Oct 21, 2024 by Francis235
Question about the perplexity question Further information is requested
#225 opened Oct 13, 2024 by eljrte
关于注意力块权重如何分配？ question Further information is requested
#224 opened Oct 4, 2024 by Yues007
2
请问我该如何获得opt模型相关的weight文件？ question Further information is requested
#223 opened Sep 23, 2024 by a1bc2def6g
2
统计predictor的overhead question Further information is requested
#220 opened Sep 16, 2024 by guanchenl
3 tasks done
Help! Want a toy example to run matmul with q40 weight by cuda kernel question Further information is requested
#219 opened Sep 11, 2024 by Eutenacity
ProTip! Find all open issues with in progress development work with linked:pr.