-
Notifications
You must be signed in to change notification settings - Fork 8.6k
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
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
Bug: Embedding endpoint takes exponential time to process a long unknown token
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8029
opened Jun 20, 2024 by
skoulik
Bug: Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
-fPIC
compiler flag missing in cmake build?
bug-unconfirmed
low severity
#8028
opened Jun 20, 2024 by
uwu-420
Bug: Inference is messed up in llama-server+default ui and llama-cli but works in llama-server+openweb ui
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8027
opened Jun 20, 2024 by
JMPSequeira
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
Bug: Or Feature? Tokenization mutates whitespaces into double-whitespace tokens when add_prefix_space is true (default)
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8023
opened Jun 20, 2024 by
cmp-nct
Feature Request: Support for Florence-2 Vision Models
enhancement
New feature or request
#8012
opened Jun 19, 2024 by
criminact
server: Bring back multimodal support
enhancement
New feature or request
llava
LLaVa and multimodal
server
#8010
opened Jun 19, 2024 by
ngxson
Nit: Is Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
--config Release
necessary?
bug-unconfirmed
low severity
#8005
opened Jun 19, 2024 by
uwu-420
Bug: llama-server + LLava 1.6 hallucinates
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8001
opened Jun 19, 2024 by
farnazj
Bug: ggml-cuda.cu: error: call of overloaded 'forward<std::array<float, 16>&>(std::array<float, 16>&)' is ambiguous
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8000
opened Jun 19, 2024 by
vt-alt
Bug: UwU Emergency! Control Vectors for Qwen2 and Command-r Models Need Fixing!
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7999
opened Jun 19, 2024 by
HatsuneMikuUwU33
Bug: Vulkan backend not detecting multiple GPUs anymore
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7997
opened Jun 19, 2024 by
richardanaya
Feature Request: Support for Meta Chameleon 7B and 34B
enhancement
New feature or request
#7995
opened Jun 18, 2024 by
arch-btw
4 tasks done
Bug: Unable to load grammar from Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
json.gbnf
example
bug-unconfirmed
medium severity
#7991
opened Jun 18, 2024 by
vecorro
The image generated by dockerfile cannot be used
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7987
opened Jun 18, 2024 by
liuda1980
The image generated by dockerfile cannot be used
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7986
opened Jun 18, 2024 by
liuda1980
SIMD Everywhere
enhancement
New feature or request
#7983
opened Jun 17, 2024 by
apcameron
4 tasks done
Bug: Unable to call llama.cpp inference server with llama 3 model
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7978
opened Jun 17, 2024 by
apar2021
Bug: The output of the lama-clI is not the same as the output of the lama-server
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7973
opened Jun 17, 2024 by
ztrong-forever
Bug: b3028 breaks mixtral 8x22b
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7969
opened Jun 17, 2024 by
steampunque
Feature Request: Nemotron-4-340B-Instruct Support
enhancement
New feature or request
#7966
opened Jun 17, 2024 by
rankaiyx
4 tasks done
Latest vulkan version doesn't follow instruction
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7965
opened Jun 17, 2024 by
duynt575
Facing issue while converting finetune LLaVA Mistral model to gguf
#7963
opened Jun 16, 2024 by
INZA111
Previous Next
ProTip!
Exclude everything labeled
bug
with -label:bug.