-
Notifications
You must be signed in to change notification settings - Fork 9.4k
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.
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
Label
Projects
Milestones
Assignee
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: Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
illegal hardware instruction
when running on M3 mac Sequoia installed with brew
bug-unconfirmed
high severity
#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: nvidia-container-cli: requirement error: unsatisfied condition: cuda>=12.6, please update your driver to a newer version, or use an earlier cuda container: unknown.
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9665
opened Sep 27, 2024 by
wencan
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
Feature Request: Add Support for MllamaForConditionalGeneration to Convert Llama 3.2 Vision Models to GGUF Format
enhancement
New feature or request
#9663
opened Sep 27, 2024 by
manishkumart
4 tasks done
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
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: Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
llama-server
web UI resets the text selection during inference on every token update
bug-unconfirmed
low severity
#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
Previous Next
ProTip!
Adding no:label will show everything without a label.