Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
Clear current search query, filters, and sorts
17 Open 108 Closed
17 Open 108 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

server: add support for local image path loading for server examples python python script changes server
#16874 opened Oct 30, 2025 by cchadowitz Loading…
15
Vulkan: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language testing Everything test related Vulkan Issues specific to the Vulkan backend
#16686 opened Oct 20, 2025 by safranowith Loading…
17
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) examples ggml changes relating to the ggml tensor library for machine learning python python script changes
#16574 opened Oct 14, 2025 by pockers21 Loading…
12
llama: Attempt to add ModernBert model Model specific python python script changes
#14014 opened Jun 4, 2025 by huydt84 Loading…
76
webui: Allow editing file attachments when editing messages. examples server
#13645 opened May 20, 2025 by nauful Loading…
@ngxson
5
Fix Vulkan glslc invocation command lines ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#13289 opened May 3, 2025 by kangalio Loading…
1
2
Updated readme file for rpc server examples
#12052 opened Feb 24, 2025 by SudaisAlam Loading…
5
Supporting Velvet model python python script changes testing Everything test related
#11716 opened Feb 6, 2025 by fbuciuni90 Loading…
10
Add information for Podman as well as Docker documentation Improvements or additions to documentation
#11660 opened Feb 4, 2025 by rhatdan Loading…
5
server: Add timeout to stop the server automatically when idling for too long. examples server
#10742 opened Dec 9, 2024 by Sumandora Loading…
12
Refactor projector_type enum to enum class for type safety and clarity examples
#10618 opened Dec 1, 2024 by wangqin0 Loading…
2 of 4 tasks
2
add FP8 support to gguf/llama: build Compilation issues examples ggml changes relating to the ggml tensor library for machine learning script Script related Tensor Encoding Scheme https://github.com/ggerganov/llama.cpp/wiki/Tensor-Encoding-Schemes testing Everything test related
#10055 opened Oct 26, 2024 by Djip007 • Draft
1 of 3 tasks
74
Added support to select GPU using metal on Apple Intel or Apple Silicon using --main-gpu index Apple Metal https://en.wikipedia.org/wiki/Metal_(API) examples ggml changes relating to the ggml tensor library for machine learning Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8962 opened Aug 10, 2024 by ifeanyipossibilities Loading…
2 of 4 tasks
4
Fix false flags used in termux demo in README.md bugfix fixes an issue or bug Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8252 opened Jul 2, 2024 by Quantaindew Loading…
2 of 4 tasks
2
Update server.cpp example with correct startup sequence examples Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level server/webui
#6739 opened Apr 18, 2024 by mann1x • Draft
22
Attempt to fix pre-tokenizer
#5613 opened Feb 20, 2024 by bobqianic • Draft
17
Update gpt2 preprocess and add deepseek coder preprocess
#4070 opened Nov 14, 2023 by DOGEwbx Loading…
47
ProTip! Follow long discussions with comments:>50.