-
Notifications
You must be signed in to change notification settings - Fork 8.5k
Pull requests: ggerganov/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
gguf-py : decouple adding metadata from writing in GGUFWriter
python
python script changes
refactoring
Refactoring
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
#7827
opened Jun 8, 2024 by
compilade
Loading…
Avoid division-by-zero on 0-weights
ggml
changes relating to the ggml tensor library for machine learning
#7825
opened Jun 7, 2024 by
CISC
Loading…
CUDA: revise q8_1 data layout for mul_mat_q
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#7824
opened Jun 7, 2024 by
JohannesGaessler
Loading…
cmake : fix CMake requirement for CUDA
build
Compilation issues
#7821
opened Jun 7, 2024 by
cebtenzzre
Loading…
[WIP] Rename binaries: main → llama, server → llama-server
devops
improvements to build systems and github actions
documentation
Improvements or additions to documentation
examples
nix
Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
python
python script changes
script
Script related
server
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
Revert "[SYCL] Update rpc-server.cpp to include SYCL backend"
examples
#7808
opened Jun 6, 2024 by
slaren
Loading…
[WIP] New feature or request
review complexity : high
Generally require indepth knowledge of LLMs or GPUs
json
: support integer minimum, maximum, exclusiveMinimum, exclusiveMaximum
enhancement
WIP: Use DirectStorage with CUDA interop to more efficient load tensors
build
Compilation issues
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
#7796
opened Jun 6, 2024 by
mtavenrath
•
Draft
feat: add changes to handle jina v2 chinese code
python
python script changes
#7795
opened Jun 6, 2024 by
JoanFM
Loading…
JSON Schema to GBNF integration tests
testing
Everything test related
#7790
opened Jun 6, 2024 by
HanClinto
Loading…
use the correct SYCL context for host USM allocations
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#7777
opened Jun 5, 2024 by
bashbaug
Loading…
Fix missing libgomp.so.1 Error in Docker Container for llama.cpp
devops
improvements to build systems and github actions
#7775
opened Jun 5, 2024 by
0x4139
Loading…
Enable stream updating in the SwiftUI example
examples
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7754
opened Jun 5, 2024 by
shu223
Loading…
Fix no gcc pragma on Windows
merge ready
indicates that this may be ready to merge soon and is just holding out in case of objections
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7751
opened Jun 4, 2024 by
jojorne
Loading…
[ci] add LLAMA_CURL flags to the prebuilt binaries
devops
improvements to build systems and github actions
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7747
opened Jun 4, 2024 by
Vaibhavs10
Loading…
server : Smart selection of available slot using Longest Common Prefix
examples
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
server
#7728
opened Jun 4, 2024 by
sasha0552
Loading…
Poro-34B-chat tokenizer support
enhancement
New feature or request
python
python script changes
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7713
opened Jun 3, 2024 by
ezosa
Loading…
[SYCL] remove global variables
build
Compilation issues
ggml
changes relating to the ggml tensor library for machine learning
Intel GPU
refactoring
Refactoring
review complexity : high
Generally require indepth knowledge of LLMs or GPUs
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#7710
opened Jun 3, 2024 by
airMeng
Loading…
2 tasks
Add Intel Advanced Matrix Extensions (AMX) support to ggml
ggml
changes relating to the ggml tensor library for machine learning
performance
Speed related topics
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
#7707
opened Jun 3, 2024 by
mingfeima
Loading…
PHI3-vision gguf conversion
examples
ggml
changes relating to the ggml tensor library for machine learning
python
python script changes
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7705
opened Jun 3, 2024 by
farris
Loading…
docs: Added initial PR template with directions for doc only changes and squash merges [no ci]
devops
improvements to build systems and github actions
documentation
Improvements or additions to documentation
merge ready
indicates that this may be ready to merge soon and is just holding out in case of objections
need feedback
Testing and feedback with results are needed
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7700
opened Jun 2, 2024 by
nicolasperez19
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.