Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
554 Open 7,272 Closed
554 Open 7,272 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

CUDA: enable FA for FP32 KV cache ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16546 opened Oct 12, 2025 by JohannesGaessler Loading…
vulkan: Improve build time for MSVC ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16545 opened Oct 12, 2025 by jeffbolznv Loading…
tests: increase NMSE threshold for q5_1 MUL_MAT tests testing Everything test related
#16544 opened Oct 12, 2025 by Erics38 Loading…
vulkan: Support FA with K/V in F32 ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#16543 opened Oct 12, 2025 by jeffbolznv Loading…
Add metal conv transpose 2d Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#16542 opened Oct 12, 2025 by iliailmer Loading…
1 task done
embedding: add raw option for --embd-output-format examples
#16541 opened Oct 12, 2025 by SamMalayek Loading…
CUDA: fix numerical issue in tile FA kernel ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16540 opened Oct 12, 2025 by JohannesGaessler Loading…
metal: add support for opt_step_sgd Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#16539 opened Oct 12, 2025 by cern1710 Loading…
chat: add defensive IBM Granite Jinja compatibility (<tool_call> and <|tool_call|> support)
#16537 opened Oct 12, 2025 by ServeurpersoCom • Draft
1
2
Vulkan MMQ Integer Dot Refactor and K-Quant support ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#16536 opened Oct 12, 2025 by 0cc4m • Draft
1 of 5 tasks
2
Update close-issue.yml devops improvements to build systems and github actions
#16535 opened Oct 12, 2025 by barneysspeedshop • Draft
server: add /slots/status endpoint for secure monitoring examples python python script changes server
#16534 opened Oct 12, 2025 by Roshankumarb31 Loading…
2
metal : FA support F32 K and V Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#16531 opened Oct 12, 2025 by ggerganov Loading…
9
metal: add support for LOG op (f32, f16) Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#16530 opened Oct 12, 2025 by RD-zhang1234 Loading…
graph : support cacheless embeddings with FA and iSWA ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#16528 opened Oct 12, 2025 by ggerganov Loading…
8
Leverage the existing GGML_F32_VEC helpers to vectorize ggml_vec_set_f32 for faster fills ggml changes relating to the ggml tensor library for machine learning
#16522 opened Oct 11, 2025 by sirus20x6 Loading…
1
ggml : fix build broken with -march=armv9-a on MacOS ggml changes relating to the ggml tensor library for machine learning
#16520 opened Oct 11, 2025 by DamonFool Loading…
1
Add server-driven parameter defaults and syncing examples server
#16515 opened Oct 11, 2025 by allozaur • Draft
1
CUDA: add fp kernel for larger batch size MoE ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#16512 opened Oct 11, 2025 by am17an Loading…
10
Feature/svelte latex regex (#16136) examples server
#16508 opened Oct 10, 2025 by srogmann Loading…
1
1
fix: add remark plugin to render raw HTML as literal text examples server
#16505 opened Oct 10, 2025 by ServeurpersoCom Loading…
1
15
vendor : sync minja
#16500 opened Oct 10, 2025 by CISC Loading…
1
Switch to using Ubuntu 25.10 vulkan/mesa devops improvements to build systems and github actions
#16497 opened Oct 10, 2025 by ericcurtin Loading…
3
Properly handle bracket delimiters for LaTeX formulas in chat message output bugfix fixes an issue or bug examples server/webui server
#16496 opened Oct 10, 2025 by allozaur • Draft
1
@allozaur
2
graph : reuse SSM graphs
#16490 opened Oct 9, 2025 by ggerganov Loading…
25
ProTip! Add no:assignee to see everything that’s not assigned.