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

296 Open 3,164 Closed
296 Open 3,164 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

llama3 quantization error bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8247 opened Jul 2, 2024 by tomgm777
1
Investigate gemma 2 generation quality enhancement New feature or request
#8240 opened Jul 1, 2024 by ngxson
88
Feature Request: Support for CodeSage enhancement New feature or request
#8224 opened Jun 30, 2024 by unclemusclez
4 tasks done
[feature request] Ability to import/export sessions from the UI.
#8220 opened Jun 30, 2024 by 0wwafa
8
device Vulkan0 does not support 16-bit storage.
#8219 opened Jun 30, 2024 by 0wwafa
NEW UI options don't reflect the OLD UI options.
#8217 opened Jun 30, 2024 by 0wwafa
Bug: Docker ROCm crashs, only works on metal compiled. bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#8213 opened Jun 29, 2024 by rudiservo
3
Bug: ld: symbol(s) not found for architecture arm64 Apple Metal https://en.wikipedia.org/wiki/Metal_(API) bug Something isn't working high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8211 opened Jun 29, 2024 by quarterturn
22
Show: FUTO-org Keyboard with llama.cpp-powered auto-correction and on-device finetuning
#8204 opened Jun 29, 2024 by Green-Sky
Bug: Unable to generate the model output correctly bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8202 opened Jun 29, 2024 by Smupk2778
5
Feature Request: Installable package via winget enhancement New feature or request help wanted Extra attention is needed
#8188 opened Jun 28, 2024 by ngxson
4 tasks done
1
LLava/ MobileVLM on android platform
#8185 opened Jun 28, 2024 by sreenivasraghavan71
Feature Request: Why is there no pre-compiled Windows version of AMD ROCm? enhancement New feature or request
#8169 opened Jun 27, 2024 by wangzi7654321
4 tasks done
1
Bug: error loading model: llama_model_loader: failed to load model bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#8154 opened Jun 27, 2024 by Smupk2778
2
Request: Add support for Qwen2 Embedding model: Alibaba-NLP/gte-Qwen2-7B-instructFeature enhancement New feature or request
#8152 opened Jun 27, 2024 by palindsay
4 tasks done
1
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
1
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) stale
#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) stale
#8127 opened Jun 26, 2024 by perp
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 stale
#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
1
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) stale
#8112 opened Jun 25, 2024 by ghchris2021
3
Bug: abort on Android (pixel 8 pro) android Issues specific to Android bug Something isn't working high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8109 opened Jun 25, 2024 by nivibilla
9
Add Support for Bamboo LLM enhancement New feature or request stale
#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) stale
#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) stale
#8096 opened Jun 24, 2024 by takosalad
1
23
ProTip! Follow long discussions with comments:>50.