-
Notifications
You must be signed in to change notification settings - Fork 11.9k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add comprehensive test for llama_batch/sbatch/ubatch concepts
testing
Everything test related
#13764
opened May 24, 2025 by
Zijie-Tian
•
Draft
vulkan: readd GGML_VULKAN_PERF
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#13761
opened May 24, 2025 by
netrunnereve
Loading…
mtmd : add support for Qwen2-Audio and SeaLLM-Audio
documentation
Improvements or additions to documentation
examples
python
python script changes
#13760
opened May 24, 2025 by
ngxson
Loading…
convert : fix nomic-bert-moe mask token
python
python script changes
#13757
opened May 24, 2025 by
CISC
Loading…
SYCL: Add mrope kernel
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13755
opened May 24, 2025 by
qnixsynapse
Loading…
SYCL: Temporarily revert "sycl: simplify bin_bcast_kernel (#13383)"
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13752
opened May 24, 2025 by
qnixsynapse
Loading…
SYCL: add gelu_erf kernel
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13749
opened May 24, 2025 by
qnixsynapse
Loading…
Multimodal: Added Moondream2 model and fixed ggml.org link
documentation
Improvements or additions to documentation
#13745
opened May 24, 2025 by
ddpasa
Loading…
cmake : set Compilation issues
RPATH
to $ORIGIN
on Linux (#13740)
build
#13741
opened May 24, 2025 by
sunhaitao
Loading…
SYCL: Implement few same quantized type copy kernels
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13739
opened May 24, 2025 by
qnixsynapse
•
Draft
Move page cache via mbind to prevent cross-NUMA access
build
Compilation issues
#13731
opened May 23, 2025 by
vishalc-ibm
Loading…
remove templates from soft_max_f32_submitter to allow SYCL graph updates
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13724
opened May 23, 2025 by
lslusarczyk
Loading…
ggml : riscv: add xtheadvector support
ggml
changes relating to the ggml tensor library for machine learning
#13720
opened May 23, 2025 by
xctan
Loading…
Replace alert and confirm with custom modals.
examples
server
#13711
opened May 22, 2025 by
igardev
Loading…
common/llama: align structures for reduce cacheline size on 64bit platforms
examples
server
#13710
opened May 22, 2025 by
GermanAizek
Loading…
add GGML_USE_NUMA_MIGRATE feature to optimize cross NUMA op computation
examples
ggml
changes relating to the ggml tensor library for machine learning
#13649
opened May 20, 2025 by
wenlujon
Loading…
MLA kv cache: fix split graph backend assignment when kv cache store on CPU
#13648
opened May 20, 2025 by
xiang1guo
Loading…
webui: Allow editing file attachments when editing messages.
examples
server
#13645
opened May 20, 2025 by
nauful
Loading…
sycl: add find_package call for OpenCL
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13643
opened May 19, 2025 by
AD2605
Loading…
sycl: Add more debug prints
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#13640
opened May 19, 2025 by
Rbiessy
Loading…
[CANN]: add the basic supports of Flash Attention kernel
Ascend NPU
issues specific to Ascend NPUs
documentation
Improvements or additions to documentation
ggml
changes relating to the ggml tensor library for machine learning
#13627
opened May 19, 2025 by
shibizhao
Loading…
Previous Next
ProTip!
Exclude everything labeled
bug
with -label:bug.