-
Notifications
You must be signed in to change notification settings - Fork 14k
Pull requests: ggml-org/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
opencl: update ops
documentation
Improvements or additions to documentation
#17904
opened Dec 10, 2025 by
lhez
Loading…
docs: use port 8080 in Docker examples
documentation
Improvements or additions to documentation
#17903
opened Dec 10, 2025 by
utsumi-fj
Loading…
model: add glm-asr support
examples
python
python script changes
#17901
opened Dec 10, 2025 by
piDack
Loading…
ggml: correct inaccurate comments for GGML_OP_MUL_MAT backward pass [no ci]
ggml
changes relating to the ggml tensor library for machine learning
#17899
opened Dec 10, 2025 by
csmyx
Loading…
cuda : add missing support check for xielu
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#17895
opened Dec 9, 2025 by
CISC
Loading…
ggml-hexagon: mm for mtmd
ggml
changes relating to the ggml tensor library for machine learning
script
Script related
#17894
opened Dec 9, 2025 by
joeldushouyu
Loading…
vulkan: support GGML_OP_DIAG
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17893
opened Dec 9, 2025 by
jeffbolznv
Loading…
vulkan: Multi-pass softmax for large number of cols
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#17892
opened Dec 9, 2025 by
jeffbolznv
Loading…
CUDA: fix unpadded strides in MMA FA kernel
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#17891
opened Dec 9, 2025 by
JohannesGaessler
Loading…
convert: allow using quantized Mistral weight
python
python script changes
#17889
opened Dec 9, 2025 by
ngxson
Loading…
vulkan: Fix data race/hang in scalar/cm1 flash attention
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17887
opened Dec 9, 2025 by
jeffbolznv
Loading…
ggml-alloc : fix reuse-parent logic for misaligned sizes
ggml
changes relating to the ggml tensor library for machine learning
#17884
opened Dec 9, 2025 by
ggerganov
Loading…
HIP: enable mmf for RDNA3
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
#17879
opened Dec 9, 2025 by
zhang-hui-yulo
Loading…
Vulkan: Improve mul_mat_vec_iq1_s speed
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#17874
opened Dec 8, 2025 by
lovedheart
Loading…
vulkan: Allow non-pow2 n_experts in topk_moe
ggml
changes relating to the ggml tensor library for machine learning
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#17872
opened Dec 8, 2025 by
jeffbolznv
Loading…
metal: use shared buffers on eGPU
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
ggml
changes relating to the ggml tensor library for machine learning
#17866
opened Dec 8, 2025 by
jdemeule
Loading…
Server: router per model config
examples
server
#17859
opened Dec 8, 2025 by
ServeurpersoCom
Loading…
examples: fix memory leak for simple example
examples
#17854
opened Dec 8, 2025 by
lizhenneng
Loading…
Webui: copy prompt and attachments
examples
server
#17841
opened Dec 7, 2025 by
ServeurpersoCom
Loading…
[SYCL] fix softmax for iGPU
ggml
changes relating to the ggml tensor library for machine learning
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#17838
opened Dec 7, 2025 by
NeoZhangJianyu
Loading…
debug:Adding CPU-side visual trace for hexagon
ggml
changes relating to the ggml tensor library for machine learning
script
Script related
#17837
opened Dec 7, 2025 by
Ethan-a2
Loading…
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.