Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
574 Open 7,539 Closed
574 Open 7,539 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

memory: Hybrid context shift examples
#17009 opened Nov 4, 2025 by gabe-l-hart Loading…
1
2
sync : ggml ggml changes relating to the ggml tensor library for machine learning script Script related
#17008 opened Nov 4, 2025 by ggerganov Loading…
webui: fix keyboard shortcuts for new chat & edit chat title examples server
#17007 opened Nov 4, 2025 by chansikpark Loading…
1
sampling : add support for GPU sampling (wip) testing Everything test related
#17004 opened Nov 4, 2025 by danbev • Draft
4 tasks
Clarify the endpoint that webui uses examples server
#17001 opened Nov 4, 2025 by openingnow Loading…
Q4/Q8 Tiled Gemm Optimization. ggml changes relating to the ggml tensor library for machine learning
#16999 opened Nov 4, 2025 by shalinib-ibm Loading…
1
kleidiai: add optimized per-channel kernels for Q8_0 ggml changes relating to the ggml tensor library for machine learning
#16993 opened Nov 4, 2025 by chaxu01 Loading…
CUDA: add stream-based concurrency ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16991 opened Nov 4, 2025 by am17an • Draft
2 tasks
2
CUDA: fix crash on uneven context ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#16988 opened Nov 4, 2025 by JohannesGaessler Loading…
1
6
ggml-hexagon: graceful fallback for older socs where rpcmem_alloc2 and FASTRPC_GET_URI is unsupported ggml changes relating to the ggml tensor library for machine learning
#16987 opened Nov 4, 2025 by l3utterfly • Draft
1
Add circular tiling support to conv2d and pad, for Vulkan, CUDA, and CPU (used for making seamless textures) 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
#16985 opened Nov 4, 2025 by Phylliida Loading…
4
Mamba2 SSD Apple Metal 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 testing Everything test related
#16982 opened Nov 3, 2025 by gabe-l-hart • Draft
3
mtmd: improve struct initialization examples
#16981 opened Nov 3, 2025 by ngxson • Draft
vulkan: Use spec constants for conv2d s/d/p and kernel W/H ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16978 opened Nov 3, 2025 by jeffbolznv Loading…
4
vulkan: fuse rms_norm + mul + rope (+ view + set_rows) ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#16977 opened Nov 3, 2025 by jeffbolznv Loading…
1
webui: Add a "Continue" Action for Assistant Message examples server
#16971 opened Nov 3, 2025 by allozaur Loading…
1
4
sycl: flash-attention implementation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#16969 opened Nov 3, 2025 by ye-NX Loading…
5
s390x: disable vxe for cross-compilation by default ggml changes relating to the ggml tensor library for machine learning
#16966 opened Nov 3, 2025 by AlekseiNikiforovIBM Loading…
Refactor llm_chat_template_from_str to avoid throwing exceptions
#16965 opened Nov 3, 2025 by AnonN10 Loading…
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 bssrdf Loading…
15
Model: Minimax M2 - chat support testing Everything test related
#16946 opened Nov 2, 2025 by pwilkin Loading…
11
bench : cache the llama_context state at computed depth examples
#16944 opened Nov 2, 2025 by ggerganov Loading…
8
Model: add openPangu-Embedded model Model specific python python script changes
#16941 opened Nov 2, 2025 by Lpzhan931 Loading…
39
Add e2e tests for embedding raw flag devops improvements to build systems and github actions examples python python script changes testing Everything test related
#16940 opened Nov 2, 2025 by SamMalayek • Draft
4
doc: Windows + clang/ninja build guide format cleanup documentation Improvements or additions to documentation
#16939 opened Nov 2, 2025 by jsjtxietian Loading…
2
ProTip! no:milestone will show everything without a milestone.