Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
613 Open 7,935 Closed
613 Open 7,935 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

Update ops md (Metal, BLAS)
#17768 opened Dec 4, 2025 by gabe-l-hart Loading…
1
docs(server): clarify that --ctx-size is total context divided among parallel slots examples server
#17767 opened Dec 4, 2025 by kitaekatt Loading…
1
1
metal : attach residency sets to queue Apple Metal https://en.wikipedia.org/wiki/Metal_(API) examples ggml changes relating to the ggml tensor library for machine learning
#17766 opened Dec 4, 2025 by ggerganov Loading…
1
Add a search field on model selector / improve mobile display examples server
#17765 opened Dec 4, 2025 by ServeurpersoCom Loading…
1
ggml webgpu: unary op suppport, code refactoring, ops support documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning python python script changes
#17764 opened Dec 4, 2025 by reeselevine Loading…
1
server : add development documentation examples server
#17760 opened Dec 4, 2025 by ngxson Loading…
3
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 bssrdf Loading…
CANN: Refactor is_matched_graph for better maintainability Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#17758 opened Dec 4, 2025 by rauletorresc Loading…
cann: refactor ACL graph cache Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#17752 opened Dec 4, 2025 by wangweixuan Loading…
1
server: handle limiting maximum reasoning budget examples server
#17750 opened Dec 4, 2025 by aviallon • Draft
23
Fix race conditions in threadpool when dealing with dynamic/frequent n_threads changes ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#17748 opened Dec 4, 2025 by max-krasnyansky Loading…
2
CUDA: fix FA VKQ accumulator overflow ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17746 opened Dec 3, 2025 by JohannesGaessler Loading…
1
8
Remove deprecated trigger_words support from grammar sampler
#17745 opened Dec 3, 2025 by yifant-code • Draft
model: add llama 4 scaling for mistral-large (deepseek arch) model Model specific
#17744 opened Dec 3, 2025 by ngxson Loading…
Fix menu shrinking examples server
#17742 opened Dec 3, 2025 by ServeurpersoCom Loading…
@ServeurpersoCom
CANN: implement the SSM_CONV operator Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#17737 opened Dec 3, 2025 by 0Marble Loading…
8
convert: support Mistral 3 Large MoE python python script changes
#17730 opened Dec 3, 2025 by ngxson Loading…
9
CANN: In the ROPE operator, yarn_ramp uses cache Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#17725 opened Dec 3, 2025 by TianHao324 Loading…
3
common : add parser for ministral/mistral large 3 documentation Improvements or additions to documentation examples server testing Everything test related
#17713 opened Dec 3, 2025 by aldehir Loading…
4
vulkan: Use one row per workgroup for f32 mmv ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#17711 opened Dec 3, 2025 by jeffbolznv Loading…
build: for GGML_BACKEND_DL, ggml need not depend on backend ggml changes relating to the ggml tensor library for machine learning
#17709 opened Dec 3, 2025 by jeffbolznv Loading…
5
common: Deepseek V3.2 tool call parser testing Everything test related
#17707 opened Dec 3, 2025 by hksdpc255 Loading…
CANN: Support fusion operator that supports mul and add Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#17706 opened Dec 3, 2025 by TianHao324 • Draft
cuda: optimize SOLVE_TRI using registers and FMAF ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17703 opened Dec 2, 2025 by wsbagnsv1 Loading…
14
vulkan: add more num_blocks instantiations in rms_norm ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#17701 opened Dec 2, 2025 by jeffbolznv Loading…
ProTip! no:milestone will show everything without a milestone.