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

327 Open 2,941 Closed
327 Open 2,941 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

Bug: converting model from HF to GGUF gives error bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8134 opened Jun 26, 2024 by thesyntaxinator
Bug: After running for a while, the llama-server exhibits extremely high CPU usage, resulting in timeouts for all requests. bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8128 opened Jun 26, 2024 by moqimoqidea
Bug: Missing required key: general.description bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#8127 opened Jun 26, 2024 by perp
Bug: llama3 8b gradient unsupported? bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8124 opened Jun 26, 2024 by 0wwafa
1
Feature Request: It would be convenient and faster if users could specify that the model data used for a RPC-server instance is already available by some fast(er) means (file system GGUF, whatever). enhancement New feature or request
#8114 opened Jun 25, 2024 by ghchris2021
4 tasks done
1
Feature Request: Provide means to quantify the restriction of RAM/VRAM usage for each GPU and system RAM. enhancement New feature or request
#8113 opened Jun 25, 2024 by ghchris2021
4 tasks done
Bug: [RPC] RPC apparently isn't honoring backend memory capacity et. al. bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8112 opened Jun 25, 2024 by ghchris2021
2
Bug: abort on Android (pixel 8 pro) bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8109 opened Jun 25, 2024 by nivibilla
1
Add Support for Bamboo LLM enhancement New feature or request
#8099 opened Jun 24, 2024 by ffroquemartinez
4 tasks done
Bug: llama.cpp apparently exits with '[end of text]' before processing prompt if prompt is ~2048 tokens bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8098 opened Jun 24, 2024 by hnfong
Bug: Crashes at the end of startup during first prompt processing bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#8096 opened Jun 24, 2024 by takosalad
1
23
Vulkan backend regression: gibberish output when layers offloaded to GPU bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8092 opened Jun 24, 2024 by Adriankhl
2
[feature request] conversion to gguf in a more pure form.
#8086 opened Jun 24, 2024 by 0wwafa
2
Bug: similar sizes suggest some heavy shared component in all 38 llama-* binaries (which now weigh 14 GB in total) bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8080 opened Jun 23, 2024 by mirekphd
5
Bug: llama-server crashes when started with --embeddings bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8076 opened Jun 23, 2024 by marcingomulkiewicz
6
Bug: JSON Schema - enum behind a $ref generates an object with unrestricted properties bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8073 opened Jun 23, 2024 by cikkle
3
win7 failed
#8072 opened Jun 23, 2024 by EverythingForAI
1
Bug: Persistent hallucination even after re-running llama.cpp bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8070 opened Jun 22, 2024 by Edw590
4
Bug: brew install on a Mac bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8065 opened Jun 22, 2024 by mneedham
1
Bug: LoRA Finetuning fails for GPU offloading bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#8061 opened Jun 22, 2024 by Ther-nullptr
Bug: ABI problem in binary file "llama-b3187-bin-win-msvc-arm64.zip" bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8050 opened Jun 21, 2024 by Billzhong2022
1
Bug: moondream2 inference not correct (severe quality degradation compared to reference) bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8037 opened Jun 20, 2024 by cmp-nct
我想convert一个比较大的模型时报错Unable to allocate 1.96 GiB for an array with shape (128256, 8192) and data type float16如何解决 bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8030 opened Jun 20, 2024 by zhaoyuchen1128
1
Bug: -fPIC compiler flag missing in cmake build? bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8028 opened Jun 20, 2024 by uwu-420
Bug: Qwen2-72B-Instruct (and finetunes) Q4_K_M generates random output bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8025 opened Jun 20, 2024 by anunknowperson
2
ProTip! Exclude everything labeled bug with -label:bug.