Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,043 Open 10,958 Closed
1,043 Open 10,958 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

agentic: question + todowrite + artifact tools examples python python script changes server/ui server
#23831 opened May 28, 2026 by LPFchan Loading…
1
mtmd-debug: add color and rainbow mode examples
#23829 opened May 28, 2026 by ngxson Contributor Loading…
2
fix(tps): correct off-by-one in decode token count for generation TPS examples server
#23828 opened May 28, 2026 by paul90317 Loading…
1
vocab: Support tokenizer for LFM2.5-8B-A1B python python script changes
#23826 opened May 28, 2026 by tdakhran Contributor Loading…
3
Removes PDL enrollment of launch_fattn kernels to fix bug on DGX Spark ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23825 opened May 28, 2026 by aendk Contributor Loading…
8
app : move licences to llama-app build Compilation issues examples server
#23824 opened May 28, 2026 by angt Member Loading…
mtmd: fix gemma 4 projector pre_norm examples
#23822 opened May 28, 2026 by ngxson Contributor Loading…
1
Bug fix: Hexagon support for llama-cli and llama-server examples server
#23821 opened May 28, 2026 by ymcki Contributor Loading…
2
kleidiai : dynamic chunck-based scheduling for hybrid execution ggml changes relating to the ggml tensor library for machine learning
#23819 opened May 28, 2026 by chaxu01 Collaborator Loading…
server : checkpoint before every user turn boundary examples server
#23814 opened May 28, 2026 by reedmayhew18 Loading…
[SYCL] Support Q4_1, Q5_0, Q5_1 in Flash-attention 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
#23812 opened May 28, 2026 by arthw Contributor Loading…
Add minicpm5 tool call parser jinja parser Issues related to the jinja parser testing Everything test related
#23802 opened May 28, 2026 by zhangtao2-1 Contributor Loading…
3 tasks done
26
Sync zDNN branch lineage ggml changes relating to the ggml tensor library for machine learning IBM zDNN issues specific to IBM zDNN Accelerator python python script changes script Script related
#23799 opened May 28, 2026 by jrepp Loading…
2
Loongarch: Add some lsx support ggml changes relating to the ggml tensor library for machine learning merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge.
#23798 opened May 28, 2026 by MQ-mengqing Contributor Loading…
vendor: update BoringSSL to 0.20260526.0
#23794 opened May 28, 2026 by cabelo Contributor Loading…
Speed up ggml_gemv_q4_K_8x8_q8_K ggml changes relating to the ggml tensor library for machine learning
#23793 opened May 28, 2026 by zephyr111 Loading…
TP: quantized KV cache support ggml changes relating to the ggml tensor library for machine learning
#23792 opened May 27, 2026 by JohannesGaessler Contributor Loading…
6
[ZenDNN] docs zendnn added information about Q8 support documentation Improvements or additions to documentation
#23791 opened May 27, 2026 by truecoder34 Contributor Loading…
common: fix HTTPS handshake on Windows, harden HTTP client
#23787 opened May 27, 2026 by ServeurpersoCom Contributor Loading…
7
Improve tagged tool parsing with reasoning testing Everything test related
#23773 opened May 27, 2026 by bartdeboer • Draft
2
vulkan: add pipeline barriers for memcpy read/write operations ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#23770 opened May 27, 2026 by 0cc4m Contributor Loading…
10
fix: duplicated "the" in compare-llama-bench and minicpmv-surgery comments examples python python script changes script Script related
#23768 opened May 27, 2026 by vip892766gma Loading…
fix(cuda): sanitize invalid Blackwell smpbo values ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23766 opened May 27, 2026 by peter941221 • Draft
1
1
llama: use f16 mask for FA to save VRAM
#23764 opened May 27, 2026 by am17an Contributor Loading…
17
vulkan: fix UMA performance by preferring cached host memory and handling non… ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#23762 opened May 27, 2026 by winstonma Contributor Loading…
4
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.