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

343 Open 2,765 Closed
343 Open 2,765 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

Bug: Incorrect memory allocation when mixing Nvidia and AMD GPU's bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7674 opened May 31, 2024 by C-monC
1
Bug: Phi-2 model tokenizer not recognized bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7667 opened May 31, 2024 by saeid93
Bug: The output of llama.cpp with Phi-3 contains Non-sense/meaningless words, Does anyone encounter the similar problem? bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7666 opened May 31, 2024 by Ross-Fan
3
When using GPU (OpenCL), the reply speed is slower and all replies are incorrect？？ bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7661 opened May 31, 2024 by QIANXUNZDL123
3
Why is convert.py missing? documentation Improvements or additions to documentation high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow) python python script changes script Script related
#7658 opened May 31, 2024 by David-AU-github
8
Refactor: Add CONTRIBUTING.md and/or update PR template with [no ci] tips devops improvements to build systems and github actions documentation Improvements or additions to documentation enhancement New feature or request help wanted Extra attention is needed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7657 opened May 30, 2024 by mofosyne
Bug: No longer makes with w64devkit bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#7655 opened May 30, 2024 by gjnave
1
Add Support for Solidity Model enhancement New feature or request
#7653 opened May 30, 2024 by kanema20
4 tasks done
Bug: DeepSeek-V2-Lite GGML_ASSERT: ggml-metal.m:1857: dst_rows <= 2048 and aborts bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7652 opened May 30, 2024 by hnfong
1
Bug: cant finetune bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#7643 opened May 30, 2024 by cabfile
1
Bug: server crashes on startup is ckt ctv specified. bug Something isn't working high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7639 opened May 30, 2024 by 0wwafa
1
Bug: server crashed today for the first time. bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7637 opened May 30, 2024 by 0wwafa
1
Feature Request: change model and lora from server api enhancement New feature or request
#7635 opened May 30, 2024 by stygmate
4 tasks done
Feature Request: Support for Yuan2-M32 enhancement New feature or request
#7632 opened May 30, 2024 by matteoserva
4 tasks done
1
Bug: SPM tokenization breaks in at least one specific case. bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7629 opened May 29, 2024 by snichols
3
Question: How to convert Yi-34B-Chat-4bits to gguf? question Further information is requested
#7623 opened May 29, 2024 by goodmaney
2 tasks done
1
Feature Request: codestral support enhancement New feature or request
#7622 opened May 29, 2024 by bachittle
4 tasks done
3
Feature: support Vulkan devices that don't support 16-bit storage enhancement New feature or request
#7620 opened May 29, 2024 by grego
4 tasks done
Feature Request: Improve Ergonomics of llama-server enhancement New feature or request
#7619 opened May 29, 2024 by abidlabs
4 tasks done
2
Question: why llama.cpp mobilevlm model(fp16) inference result is different with official pytorch project results, this is normal? question Further information is requested
#7614 opened May 29, 2024 by lijianxing123
2 tasks done
6
Bug: Inconsistent ggml-4-x86-cuda-v100 ci failures on master bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7613 opened May 29, 2024 by mofosyne
2
Question: When using finetune LoRA to fine-tune the LLaMA3-7B-4bit GGUF model, why does the training prematurely end and save the LoRA model? question Further information is requested
#7611 opened May 29, 2024 by KiraYBfice
2 tasks done
Bug: Default CTX on llama3 causes incoherence in server when 512 tokens passed in output bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7609 opened May 29, 2024 by m9e
2
Question: Why do GPU and CPU embedding outputs differ for the same input? Is normal? question Further information is requested
#7608 opened May 29, 2024 by jygmysoul
2 tasks done
Bug: [Server] Prompt caching causes subsequent identical requests to return different token probabilities bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7594 opened May 28, 2024 by reuank
ProTip! Mix and match filters to narrow down what you’re looking for.