Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
Clear current search query, filters, and sorts
476 Open 6,193 Closed
476 Open 6,193 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

feat: perf opt quant build Compilation issues ggml changes relating to the ggml tensor library for machine learning
#14548 by chraac was closed Jul 6, 2025 Loading…
vulkan: fix rms_norm+mul fusion ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#14545 by jeffbolznv was merged Jul 6, 2025 Loading…
1
4
eval-callback : check for empty input examples
#14539 by ggerganov was merged Jul 5, 2025 Loading…
1
metal : disable fast math in all quantize kernels Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#14528 by ggerganov was merged Jul 4, 2025 Loading…
vulkan: Handle updated FA dim2/3 definition ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#14518 by jeffbolznv was merged Jul 5, 2025 Loading…
3
graph : prepare for 4D mask
#14515 by ggerganov was merged Jul 4, 2025 Loading…
batch : add n_used count
#14512 by ggerganov was merged Jul 4, 2025 Loading…
batch : add optional for sequential equal split
#14511 by ggerganov was merged Jul 4, 2025 Loading…
opencl: broadcast for soft_max ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#14510 by lhez was merged Jul 3, 2025 Loading…
2
vulkan: support mixed/deepseekR1 FA head sizes ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#14509 by jeffbolznv was merged Jul 3, 2025 Loading…
4
gguf-py : add support for chat template jinja files python python script changes
#14508 by CISC was merged Jul 2, 2025 Loading…
3
sync : ggml ggml changes relating to the ggml tensor library for machine learning script Script related
#14507 by ggerganov was merged Jul 2, 2025 Loading…
ggml : fix FA mask dim 2 and 3 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
#14505 by ggerganov was merged Jul 3, 2025 Loading…
9
sycl: Fix conditional enabling following arch checks for ggml-sycl ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#14504 by s-Nick was merged Jul 3, 2025 Loading…
model : add support for apple/DiffuCoder-7B-cpGRPO python python script changes
#14502 by gabriellarson was closed Jul 2, 2025 Loading…
5
ggml : remove kompute backend build Compilation issues devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning Kompute https://github.com/KomputeProject/kompute/ script Script related testing Everything test related
#14501 by ggerganov was merged Jul 3, 2025 Loading…
CUDA: broadcasting for FlashAttention mask ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#14500 by JohannesGaessler was merged Jul 2, 2025 Loading…
Enables CUDA graphs in CUDA docker image compilation. devops improvements to build systems and github actions
#14499 by aendk was closed Jul 2, 2025 Loading…
1
CUDA: add dynamic shared mem to softmax, refactor general usage ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#14497 by am17an was merged Jul 2, 2025 Loading…
6
ci : add OpenCL to labeler workflow devops improvements to build systems and github actions
#14496 by CISC was merged Jul 2, 2025 Loading…
simple-chat : fix context-exceeded condition examples
#14494 by ggerganov was merged Jul 2, 2025 Loading…
1
1
github : add OpenCL backend to issue templates devops improvements to build systems and github actions
#14492 by EZForever was merged Jul 2, 2025 Loading…
opencl : skip empty nodes on cgraph compute ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#14491 by EZForever was merged Jul 2, 2025 Loading…
1
5
opencl: preventing buffer overflows in debugging utils ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#14490 by zhouwg was merged Jul 2, 2025 Loading…
2
opencl: update upscale to support align corners ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#14488 by lhez was merged Jul 2, 2025 Loading…
ProTip! Add no:assignee to see everything that’s not assigned.