Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
981 Open 10,553 Closed
981 Open 10,553 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

examples : enable llama-eval type check examples merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. python python script changes
#22988 opened May 12, 2026 by CISC Member Loading…
CI : support IOT device (IQ9) devops improvements to build systems and github actions python python script changes script Script related
#22987 opened May 12, 2026 by zhiyuan8 Contributor Loading…
opencl: add q5_0 and q5_1 MoE for Adreno ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#22985 opened May 12, 2026 by shaofeiqi Contributor Loading…
webui: Deduplicate model aliases in data + handle single/multiple aliases in UI examples server/webui server
#22979 opened May 12, 2026 by allozaur Contributor Loading…
1
4
ggml-webgpu: Enable NVIDIA self-hosted CI devops improvements to build systems and github actions
#22976 opened May 12, 2026 by reeselevine Contributor • Draft
vulkan : transpose A-matrix data layout for K-quant mul_mat performance ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#22970 opened May 12, 2026 by Alex-JP-93 Loading…
3
[SYCL] update by stable version of compute-runtime devops improvements to build systems and github actions
#22968 opened May 12, 2026 by arthw Contributor • Draft
spec : update CLI arguments for better consistency examples server
#22964 opened May 12, 2026 by ggerganov Member Loading…
5
convert : lock MiniCPM-V 4.6 chat_template default enable_thinking in… python python script changes
#22963 opened May 12, 2026 by tc-mb Contributor Loading…
6
server : emit empty input field in anthropic streaming tool_use content_block_start examples server
#22960 opened May 12, 2026 by Biilow-Bailang Loading…
1
update openvino.md validated models section documentation Improvements or additions to documentation OpenVINO
#22959 opened May 12, 2026 by ravi9 Contributor Loading…
vulkan: Pad Q3_K/Q6_K tensors out to 32-bit alignment ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#22951 opened May 11, 2026 by TheBlueMatt Contributor Loading…
12
[Tensor Parallel] Enable Auto parameter fitting in split-mode tensor documentation Improvements or additions to documentation
#22950 opened May 11, 2026 by gaugarg-nv Contributor Loading…
5
hexagon: fix OpenCL not found error when building hexagon backend documentation Improvements or additions to documentation
#22946 opened May 11, 2026 by Russyyds Contributor Loading…
1
ggml-cpu: avoid treating all host RAM as free ggml changes relating to the ggml tensor library for machine learning
#22939 opened May 11, 2026 by fl0rianr Contributor Loading…
1
webui: Move static build output from repo code to HF Bucket build Compilation issues devops improvements to build systems and github actions examples server/webui server
#22937 opened May 11, 2026 by allozaur Contributor Loading…
1
@ggerganov
30
tests: support multi-op perf groups in test-backend-ops testing Everything test related
#22934 opened May 11, 2026 by zzzzwc Contributor Loading…
vulkan: opt mul_mat_vecq for mi50 ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#22933 opened May 11, 2026 by chraac Contributor Loading…
8
UMA buffers prefer host-visible memory ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#22930 opened May 11, 2026 by winstonma Loading…
5
server: fix checkpoints creation examples server testing Everything test related
#22929 opened May 11, 2026 by jacekpoplawski Contributor Loading…
9
kv-cache: use -t threads for IQ4 packing from ggml code ggml changes relating to the ggml tensor library for machine learning
#22928 opened May 11, 2026 by shikaku2 Loading…
common: improve --fit host-memory accounting for CPU and iGPU ggml changes relating to the ggml tensor library for machine learning
#22922 opened May 10, 2026 by fl0rianr Contributor Loading…
8
webui: preserve system message on edit cancel examples server/webui server
#22911 opened May 10, 2026 by ServeurpersoCom Contributor Loading…
webui: fix theme from --webui-config-file not applied on first load (fresh localStorage) examples server/webui server
#22902 opened May 10, 2026 by ServeurpersoCom Contributor Loading…
1
fix(quantize): add NVFP4 default type mapping and scale tensors examples
#22897 opened May 10, 2026 by t-timms Loading…
2
ProTip! no:milestone will show everything without a milestone.