Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
644 Open 8,465 Closed
644 Open 8,465 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

vulkan: Check maxStorageBufferRange in supports_op ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18709 opened Jan 9, 2026 by jeffbolznv Loading…
fix text spacing in print_info
#18708 opened Jan 9, 2026 by ddh0 Loading…
ggml webgpu: clamp available memory on 32-bit systems ggml changes relating to the ggml tensor library for machine learning
#18707 opened Jan 9, 2026 by reeselevine Loading…
ggml-metal: Clean up files used for embedded build Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#18705 opened Jan 9, 2026 by DaAwesomeP Loading…
opencl: add expm1 op ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#18704 opened Jan 8, 2026 by shaofeiqi Loading…
1
[WIP] ggml-opencl: op args init refactoring ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#18701 opened Jan 8, 2026 by chraac • Draft
server : use different seeds for child completions examples python python script changes server
#18700 opened Jan 8, 2026 by ggerganov Loading…
2
Confirm --hard flag necessity in pr2wt.sh reset operation
#18699 opened Jan 8, 2026 by Copilot AI • Draft
@ggerganov
3
Improving inference speed for the repack buffer type on NUMA architectures ggml changes relating to the ggml tensor library for machine learning
#18698 opened Jan 8, 2026 by zzjianhui Loading…
common : add --license to display embedded licenses build Compilation issues python python script changes script Script related
#18696 opened Jan 8, 2026 by angt Loading…
1
scripts : pr2wt.sh reset to remote head script Script related
#18695 opened Jan 8, 2026 by ggerganov Loading…
1
5
Webui/file upload examples server
#18694 opened Jan 8, 2026 by ServeurpersoCom Loading…
1
7
debug : include LLAMA_POOLING_TYPE_UNSPECIFIED in pooling check examples
#18692 opened Jan 8, 2026 by danbev Loading…
2
ggml-cuda: extend concat support for more types ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18690 opened Jan 8, 2026 by Lourdle Loading…
1
model: try to improve Qwen3 Next model Model specific python python script changes
#18683 opened Jan 8, 2026 by ngxson • Draft
18
vulkan: Use VK_EXT_shader_64bit_indexing to handle large mat_mul(_id) ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#18678 opened Jan 7, 2026 by jeffbolznv Loading…
Autoparser - complete refactoring of parser architecture documentation Improvements or additions to documentation examples model Model specific python python script changes script Script related server testing Everything test related
#18675 opened Jan 7, 2026 by pwilkin • Draft
5
Fix integer overflow in GGUF tensor parsing ggml changes relating to the ggml tensor library for machine learning
#18674 opened Jan 7, 2026 by alexanderkent Loading…
19
cmake: fix cli build when LLAMA_BUILD_SERVER=OFF examples server
#18670 opened Jan 7, 2026 by AsbjornOlling Loading…
6
HIP: adjust RDNA3.5 MMQ kernel selction logic ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18666 opened Jan 7, 2026 by JohannesGaessler Loading…
9
server: support image+text input for embeddings (Qwen3-VL-Embedding) examples server
#18665 opened Jan 7, 2026 by ngxson • Draft
3
server: fix n_cmpl not skipping processing prompt examples server
#18663 opened Jan 7, 2026 by ngxson Loading…
6
MCP MVP enhancement New feature or request examples server/webui server
#18655 opened Jan 7, 2026 by allozaur • Draft
47
docs: update ops.md for CANN backend documentation Improvements or additions to documentation
#18654 opened Jan 7, 2026 by hipudding Loading…
CANN: support gated linear attn Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#18653 opened Jan 7, 2026 by hipudding Loading…
3
ProTip! Mix and match filters to narrow down what you’re looking for.