Skip to content

No labels!

There aren’t any labels for this repository quite yet.

70 labels

Sort
Sort
Alphabetically
Reverse alphabetically
Most issues
Fewest issues
linux
linux
Issues specific to Linux
llava
llava
LLaVa and multimodal
2
low severity
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
26
macos
macos
Issues specific to macOS
1
medium severity
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
46
merge ready
merge ready
indicates that this may be ready to merge soon and is just holding out in case of objections
model
model
Model specific
11
need feedback
need feedback
Testing and feedback with results are needed
10
need more info
need more info
The OP should provide more details about the issue
1
nix
nix
Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
3
Nvidia GPU
Nvidia GPU
Issues specific to Nvidia GPUs
8
obsolete?
obsolete?
Marker for potentially obsolete PR
9
performance
performance
Speed related topics
12
porting
porting
python
python
python script changes
54
Qualcomm QNN
Qualcomm QNN
Qualcomm's QNN(AI Direct Engine) SDK
question
question
Further information is requested
refactoring
refactoring
Refactoring
21
research 🔬
research 🔬
14
Review Complexity : High
Review Complexity : High
Generally require indepth knowledge of LLMs or GPUs
19
Review Complexity : Low
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
62
Review Complexity : Medium
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
48
script
script
Script related
6
server/api
server/api
2
server/webui
server/webui
23
server
server
33
split
split
GGUF split model sharding
3
stale
stale
47
SYCL
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
8
sync
sync
Requires sync with the ggml repo after merging