Skip to content

Issues: intel/intel-npu-acceleration-library

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

35 Open 37 Closed
35 Open 37 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

CPU execution time better than NPU?
#128 opened Oct 4, 2024 by jovinod
Thanks. I think the issue has been fixed in my Ubuntu after recreate the environment.
#127 opened Sep 26, 2024 by slllu1
2
return none when use torch.load to load a quantize_model
#126 opened Sep 20, 2024 by ev-day
1
Support for Arch Linux-based distributions
#125 opened Sep 20, 2024 by jhmeinke
[BUG]: wrong argtype definitions when calling the c++ lib from python
#124 opened Sep 19, 2024 by Naplesoul
can't adapt to the new transformer version
#121 opened Sep 6, 2024 by hyppo6688
failed to do pip install intel_npu_acceleration_library
#120 opened Sep 3, 2024 by andyyeh75
Is there any plan to support llama.cpp?
#118 opened Aug 26, 2024 by piDack
Example on README throws TypeError: LlamaAttention.forward() got an unexpected keyword argument 'position_embeddings'` when executed
#117 opened Aug 23, 2024 by mgagvani
6
Is there going to be support for other distros besides Ubuntu?
#116 opened Aug 16, 2024 by epangelias
Endeavouros Support
#114 opened Aug 5, 2024 by pirr
Weight asymmetric quantization
#113 opened Aug 1, 2024 by kyang-06
Performance regression of version 1.3.0
#112 opened Aug 1, 2024 by plusbang
Why Llama series int4 quantization has fp16 attention layers? bug Something isn't working
#111 opened Jul 30, 2024 by kyang-06
@alessandropalla
2
After passing a certain amount of prompts, llama3 spits out the chat template
#110 opened Jul 27, 2024 by enricorampazzo
2
[Llama3.1 8B] Need pass your input's attention_mask to obtain reliable results.
#109 opened Jul 26, 2024 by ChenYuYeh
6
Library .dll is not loaded when not built from source
#102 opened Jul 22, 2024 by enricorampazzo
2
backend/ops.py:get_supported_ops references functions (power and log_softmax) not available in the 1.3.0 library .dll
#101 opened Jul 22, 2024 by enricorampazzo
Does it support Ubuntu 24.04?
#95 opened Jul 11, 2024 by yuankdou
5
Visualize NPU Performance in Linux
#94 opened Jul 9, 2024 by neeleshg23
4
Enable graph mode for LLM inference
#89 opened Jul 5, 2024 by xduzhangjiayu
9
Does this library support Qwen/Qwen2-7B-Instruct？ bug Something isn't working
#85 opened Jul 2, 2024 by qwebug
@alessandropalla
5
LLM-7B performance
#82 opened Jul 1, 2024 by xduzhangjiayu
2
Dose linear support input_tensor with dtype int8?
#57 opened Jun 14, 2024 by Septend-fun
4
NPU computation is not fully occupied while running LLM model
#55 opened Jun 13, 2024 by nigue3025
3
ProTip! Find all open issues with in progress development work with linked:pr.