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 2
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.

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

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

Issues list

Feature Request: Support FlashAttention-3 enhancement New feature or request
#9700 opened Sep 30, 2024 by hg0428
4 tasks done
Bug: quality decreases in embeddings models bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9695 opened Sep 30, 2024 by Maxon081102
Bug: cannot find tokenizer merges in model file bug Something isn't working high priority Very important issue high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9692 opened Sep 30, 2024 by nd791899
Bug: illegal hardware instruction when running on M3 mac Sequoia installed with brew bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9676 opened Sep 28, 2024 by Ben-Epstein
Bug: baby-llama fails bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9674 opened Sep 28, 2024 by sfadaei
Bug: Issue building hipBLAS error: call to undeclared function '_mm256_dpbusd_epi32' bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9666 opened Sep 27, 2024 by Zhaeong
Bug: Termux adreno 618 vulkan support bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#9664 opened Sep 27, 2024 by akac97
Error: llama_model_load: error loading model: failed to open ggml-bagel-2.8b-v0.2-q8_0.gguf bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9656 opened Sep 26, 2024 by vineel96
Bug: server crashes when embedding model is passed in the -m parameter bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9652 opened Sep 26, 2024 by mesibo
Feature Request: sgemm.cpp : Q5_0 support enhancement New feature or request
#9651 opened Sep 26, 2024 by Srihari-mcw
4 tasks done
Feature Request: Molmo 72B vision support enhancement New feature or request
#9645 opened Sep 25, 2024 by Kreijstal
4 tasks done
Bug: IQ3_M is significantly slower than IQ4_XS on AMD, is it expected? bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9644 opened Sep 25, 2024 by Nekotekina
Llama-3.2 11B Vision Support
#9643 opened Sep 25, 2024 by yukiarimo
Bug: server (New UI) ChatML templates are wrong bug-unconfirmed good first issue Good for newcomers medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable) server/webui
#9640 opened Sep 25, 2024 by ivanstepanovftw
Bug: Assertion '__n < this->size()' failed. bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9636 opened Sep 25, 2024 by Luke100000
Bug: python: can't open file 'llama.cpp/convert.py': [Errno 2] No such file or directory bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9632 opened Sep 24, 2024 by AmosBunde
Do llama.cpp support input_embeds? bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9630 opened Sep 24, 2024 by OswaldoBornemann
Bug: Failed to run qwen2-57b-a14b-instruct-fp16. bug Something isn't working good first issue Good for newcomers high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9628 opened Sep 24, 2024 by tang-t21
Bug: [Hardware: ppc64le] On ppc64le llama.cpp only uses 1 thread by default and not half of all threads as it does on x86 bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9623 opened Sep 24, 2024 by mgiessing
Bug: [SYCL] crash since b-3805 bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#9612 opened Sep 23, 2024 by easyfab
Bug: llama-server web UI resets the text selection during inference on every token update bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9608 opened Sep 23, 2024 by mashdragon
Feature Request: OpenVINO backend support request enhancement New feature or request
#9601 opened Sep 23, 2024 by aropb
4 tasks done
Feature Request: Word Llama enhancement New feature or request
#9600 opened Sep 23, 2024 by TalonBvV
4 tasks done
ProTip! Adding no:label will show everything without a label.