Skip to content

Pull requests: ggml-org/llama.cpp

New pull requestNew
Clear current search query, filters, and sorts
43 Open 519 Closed
43 Open 519 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 reviewsReview requiredApproved reviewChanges requested
Assignee
Filter by who’s assigned
Assigned to nobodyLoading
Sort
Sort by
NewestOldestMost commentedLeast commentedRecently updatedLeast recently updatedBest match
Most reactions
👍👎😄🎉😕❤️🚀👀

Pull requests list

Build CUDA architectures 120 and 121 by default (RTX5000 and GB10) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17970 opened Dec 12, 2025 by DaAwesomePLoading…
mtmd, llama: add GLM4V vision-language model support examples ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#17967 opened Dec 12, 2025 by eelbazLoading…
11
CUDA: experimental native mxfp4 support for blackwell [WIP] ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17906 opened Dec 10, 2025 by am17an • Draft
1 of 2 tasks
32
[DRAFT] CUDA: Improve performance via less synchronizations between token ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17795 opened Dec 5, 2025 by aendk • Draft
7
Fix too stringent check on CUDA "fast copy" (can_be_transposed) condition and extend with one more case ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17759 opened Dec 4, 2025 by bssrdfLoading…
model : add ASR support for LFM2-Audio-1.5B examples ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes testing Everything test related
#17694 opened Dec 2, 2025 by tdakhran • Draft
1
Add Support for Microsoft Phi-3.5 Vision Instruct Models Apple Metal https://en.wikipedia.org/wiki/Metal_(API) Ascend NPU issues specific to Ascend NPUs build Compilation issues devops improvements to build systems and github actions documentation Improvements or additions to documentation examples ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes script Script related server testing Everything test related Vulkan Issues specific to the Vulkan backend
#17687 opened Dec 2, 2025 by z-manoj • Draft
8
Feature/kimi linear support ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#17592 opened Nov 29, 2025 by cacaviewLoading…
58
Add PagedAttention support (experimental, CUDA only) examples ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs server
#17579 opened Nov 28, 2025 by ericcurtin • Draft
6
HIP: Add RDNA3 WMMA support to MMF ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17495 opened Nov 25, 2025 by unverbrauchtLoading…
31
mtmd: Add DeepSeekOCR Support examples ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#17400 opened Nov 20, 2025 by sfallahLoading…
73
ggml : enhance rel-pos and window ops with CUDA support ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17383 opened Nov 19, 2025 by bluebreadLoading…
9
CUDA: add CONV_3D operator support documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17255 opened Nov 14, 2025 by YaelGitAccountLoading…
4
CUDA & CPU: support F32 kernel type for CONV_TRANSPOSE_2D ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17094 opened Nov 8, 2025 by AgainstEntropyLoading…
15
sampling : add support for backend sampling Apple Metal https://en.wikipedia.org/wiki/Metal_(API) build Compilation issues examples ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes server testing Everything test related
#17004 opened Nov 4, 2025 by danbevLoading…
17 of 25 tasks
82
Mamba2 SSD Apple Metal https://en.wikipedia.org/wiki/Metal_(API) examples ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#16982 opened Nov 3, 2025 by gabe-l-hart • Draft
20
CUDA: add implicit conv3d ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#16948 opened Nov 2, 2025 by bssrdfLoading…
30
Enable CUDA graphs for embed gemma 300m ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16844 opened Oct 29, 2025 by ArshM17-NVLoading…
3
Add basic support for MXFP6_MOE quantization examples ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#16777 opened Oct 26, 2025 by horasalLoading…
6
Implement and use cuda graph plans ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16548 opened Oct 13, 2025 by wishstudioLoading…
30
Add hipblasLt implementation for batched gemm to improve performance for CDNA3 only ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16457 opened Oct 7, 2025 by peizhang56Loading…
5
ggml-cuda: Vulkan direct conv 2D ported to CUDA ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16088 opened Sep 18, 2025 by etasnadiLoading…
39
Deterministic inference mode (CUDA): RMSNorm, MatMul, Attention, KV-cache documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs script Script related testing Everything test related
#16016 opened Sep 15, 2025 by creatorrr • Draft
3
--numa mirror: mirror model weights to every Numa node in the system Apple Metal https://en.wikipedia.org/wiki/Metal_(API) Ascend NPU issues specific to Ascend NPUs devops improvements to build systems and github actions examples ggml changes relating to the ggml tensor library for machine learning IBM zDNN issues specific to IBM zDNN Accelerator Nvidia GPU Issues specific to Nvidia GPUs OpenCL Issues specific to the OpenCL backend python python script changes SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#16000 opened Sep 15, 2025 by dbsanfte • Draft
22
CUDA: print CUDART_VERSION on init ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#15853 opened Sep 7, 2025 by JohannesGaesslerLoading…
4
ProTip! What’s not been updated in a month: updated:<2025-11-12.