Skip to content

Issues: ggerganov/llama.cpp

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

357 Open 2,560 Closed
357 Open 2,560 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

selects too many cores by default on orange pi 5 (2x slower) bug-unconfirmed
#7176 opened May 9, 2024 by calculatortamer
2
Messy CUDA graph error output on mixtral/MoE models bug-unconfirmed
#7175 opened May 9, 2024 by CISC
1
5
Should we add an autolabeler for PR? devops improvements to build systems and github actions enhancement New feature or request help wanted Extra attention is needed
#7174 opened May 9, 2024 by mofosyne
2
Add support for mistral Dutch and Armenian models: Tweeties/tweety-7b-dutch-v24a and Tweeties/tweety-7b-armenian-v24a enhancement New feature or request
#7170 opened May 9, 2024 by JohnClaw
Support for Consistency Large Language Models? enhancement New feature or request
#7168 opened May 9, 2024 by unoexperto
1
how can i modify the setting,make it answer in Chinese by default enhancement New feature or request
#7167 opened May 9, 2024 by LiangZeFenglzf
2
Add metadata override and also generate dynamic default filename when converting gguf enhancement New feature or request help wanted Extra attention is needed need feedback Testing and feedback with results are needed
#7165 opened May 9, 2024 by mofosyne
@mofosyne
Looking for help for using llama.cpp with Phi3 model and LoRA bug-unconfirmed
#7164 opened May 9, 2024 by SHIMURA0
Gibberish response from server and main exits on M1 macstudio ultra with gpu (cpu ok) bug-unconfirmed
#7159 opened May 9, 2024 by jrozentur
1
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 149, got 147 bug-unconfirmed
#7157 opened May 9, 2024 by YathenStianbase
ggml-cuda.so is 90mb with -arch=all bug-unconfirmed
#7156 opened May 9, 2024 by jart
1
Impact of bf16 on Llama 3 8B perplexity? enhancement New feature or request
#7148 opened May 8, 2024 by jim-plus
4 tasks done
1
error: implicit declaration of function ‘vld1q_s8_x4’; did you mean ‘vld1q_s8_x2’? bug-unconfirmed
#7147 opened May 8, 2024 by CaptainOfHacks
Make -DLLAMA_HIP_UMA a dynamic setting. enhancement New feature or request
#7145 opened May 8, 2024 by sebastian-philipp
3 of 4 tasks
[SYCL] Implement Flash attention. enhancement New feature or request
#7141 opened May 8, 2024 by qnixsynapse
2
Is it extending pre trained model or finetuning the pretrained model?
#7137 opened May 8, 2024 by eswarthammana
Server 'penalize_nl' parameter defaults to False?
#7136 opened May 8, 2024 by AayushG159
2
common/build-info.cpp not properly updated bug-unconfirmed
#7134 opened May 8, 2024 by hpcpony
escaping escaped characters in server which leads to endless lines of escaping charachters which the textarea shows as literals bug-unconfirmed
#7131 opened May 7, 2024 by bones0
Embedding fails to run on vulkan backend bug-unconfirmed
#7130 opened May 7, 2024 by Adriankhl
4
llama : make vocabs LFS objects? enhancement New feature or request need feedback Testing and feedback with results are needed
#7128 opened May 7, 2024 by ggerganov
1
6
could we get Aryanne/Calypso-3B-alpha-v2-gguf added to the demo? enhancement New feature or request
#7126 opened May 7, 2024 by Louis654
4 tasks done
2
Minor improvement in cmake script for msvc/clang-cl enhancement New feature or request
#7121 opened May 7, 2024 by skoulik
llama : add DeepSeek-v2-Chat support good first issue Good for newcomers model Model specific
#7118 opened May 7, 2024 by DirtyKnightForVi
6
Add Support for IBM Granite enhancement New feature or request
#7116 opened May 7, 2024 by YorkieDev
10
ProTip! Find all open issues with in progress development work with linked:pr.