Skip to content

Issues: ggerganov/llama.cpp

changelog : libllama API
#9289 opened Sep 3, 2024 by ggerganov
Open 1
changelog : llama-server REST API
#9291 opened Sep 3, 2024 by ggerganov
Open 3
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

266 Open 3,613 Closed
266 Open 3,613 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: LLAMA_MAX_LAYERS must be increased to run FatLlama 1.7T bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9909 opened Oct 16, 2024 by nicoboss
1
Bug: Bug: Cmake fail to build when find MATH_LIBRARY but GGML_SYCL=OFF on windows bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9908 opened Oct 16, 2024 by czheji
Bug: gemma-2-9b-it inference speed very slow 1.73 tokens per second bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9906 opened Oct 16, 2024 by ninth99
Bug: llama.cpp does not use XTC sampler when given temperature == 0 even if temperature is not in sampler sequence bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9904 opened Oct 16, 2024 by justinsteven
7
Bug: llama runner process has terminated: GGML_ASSERT(src1t == GGML_TYPE_F32) failed bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9902 opened Oct 15, 2024 by lhwong
Bug: Inconsistency while parsing the model using llama-cli and gguf-py bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9893 opened Oct 15, 2024 by Lyutoon
4
Bug: When inferring with RWKV, an uncontrolled dialogue between 'user' and 'assistant' appears. bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9892 opened Oct 15, 2024 by guoguo1314
llama.cpp is slow on GPU bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches) Nvidia GPU Issues specific to Nvidia GPUs
#9881 opened Oct 14, 2024 by vineel96
8
Bug: Cmake/LLVM fail to build with SVE support on Windows on Arm bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9878 opened Oct 14, 2024 by xengpro
Bug: The program running model compiled by Macos15 (intel) appears garbled. bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#9873 opened Oct 13, 2024 by AdrianWangs
2
Feature Request: Nemotron chat templates enhancement New feature or request
#9864 opened Oct 12, 2024 by freebiesoft
4 tasks done
1
1
Bug: When I try to run llama-server with the --embd-normalize option, I encounter the following error: bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9863 opened Oct 12, 2024 by xanhf
1
Feature Request: [CANN] backend adapts to llama.cpp dynamic backend loading mechanism Ascend NPU issues specific to Ascend NPUs enhancement New feature or request
#9862 opened Oct 12, 2024 by leo-pony
4 tasks done
@leo-pony
Bug: fatal error: too many errors emitted, stopping now [-ferror-limit=] bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9858 opened Oct 12, 2024 by wuhongsheng
Bug: Unable to load GGUF models after update bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#9852 opened Oct 11, 2024 by FitzWM
8
Bug: Erroneous Output in llama-cli bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9848 opened Oct 11, 2024 by ericcurtin
14
Bug: llama-cli exiting on Windows after loading everything when given an initial prompt bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#9843 opened Oct 11, 2024 by Edw590
5
Bug: Llama.cpp with cuda support outputs garbage response when prompt is above 30-40ish Tokens bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9838 opened Oct 11, 2024 by bmahabirbu
7
Server UI bug: corrupted generation medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable) server/webui server
#9836 opened Oct 11, 2024 by ivanstepanovftw
It would be great to implement L-MUL
#9834 opened Oct 11, 2024 by 0wwafa
1
android examples add top_p min_keep to new_context enhancement New feature or request
#9828 opened Oct 10, 2024 by darrassi1
4 tasks done
Feature Request: NEON, SVE2, int8mm optimized kernels for IQ4, K quants ? enhancement New feature or request
#9827 opened Oct 10, 2024 by Abhranta
4 tasks done
windows on arm ,build with openblas / vulkan
#9823 opened Oct 10, 2024 by wmx-github
2
Bug: Load time on rpc server with multiple machines bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9820 opened Oct 10, 2024 by angelosathanasiadis
1
Bug: TypeError when YAML license field in README.md is a list during GGUF conversion bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9819 opened Oct 10, 2024 by gakugaku
ProTip! Find all open issues with in progress development work with linked:pr.