-
Notifications
You must be signed in to change notification settings - Fork 10.5k
Pull requests: ggerganov/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
ci
: only *write ccache in "push to master" jobs
devops
Add information for Podman as well as Docker
documentation
Improvements or additions to documentation
#11660
opened Feb 4, 2025 by
rhatdan
Loading…
CUDA: non-contiguous (RMS) norm support
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#11659
opened Feb 4, 2025 by
JohannesGaessler
Loading…
common : change longest common subsequence to substring [no ci]
examples
server
#11657
opened Feb 4, 2025 by
danbev
Loading…
CUDA: support for mat. mul. with ne03 != ne13
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#11656
opened Feb 4, 2025 by
JohannesGaessler
Loading…
swift : revert package changes
devops
improvements to build systems and github actions
#11650
opened Feb 4, 2025 by
jhen0409
Loading…
Add supports for Janus vision encoder and projector [WIP]
examples
python
python script changes
#11646
opened Feb 4, 2025 by
ravenouse
Loading…
1 of 4 tasks
Added quantization for the visual projector LLAVA, Qwen2VL
examples
#11644
opened Feb 4, 2025 by
samkoesnadi
Loading…
[Important] Added README to the Qwen2VL implementation
examples
#11642
opened Feb 4, 2025 by
samkoesnadi
Loading…
Attempt to add the https://en.wikipedia.org/wiki/Metal_(API)
examples
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
mllama
support
Apple Metal
cmake: include folder and common folder is private to llama library
#11631
opened Feb 3, 2025 by
mofosyne
Loading…
HIP: force max threads per block to be 1024
ggml
changes relating to the ggml tensor library for machine learning
#11621
opened Feb 3, 2025 by
fxzjshm
Loading…
server : add try..catch to places not covered by set_exception_handler
examples
server
#11620
opened Feb 3, 2025 by
ngxson
Loading…
ci: add bash script to check if llama-impl.h was included erroneously
devops
improvements to build systems and github actions
script
Script related
#11617
opened Feb 3, 2025 by
mofosyne
Loading…
Clean up Test Script + Update it to work on Instruct Tuned Models
examples
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#11610
opened Feb 3, 2025 by
Mr-Thack
Loading…
scripts: added inline script metadata per PEP 723
python
python script changes
script
Script related
#11597
opened Feb 2, 2025 by
isaac-mcfadyen
Loading…
De-duplicate fmt and format functions and optimize
examples
#11596
opened Feb 2, 2025 by
ericcurtin
Loading…
vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations
devops
improvements to build systems and github actions
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#11595
opened Feb 2, 2025 by
remyoudompheng
•
Draft
vulkan: add environment variable to avoid VRAM allocation
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#11592
opened Feb 2, 2025 by
wbruna
Loading…
Previous Next
ProTip!
Filter pull requests by the default branch with base:master.