Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
982 Open 10,621 Closed
982 Open 10,621 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

ggml: add DeepSeek V4 hyperconnection + KV ops (CPU) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#23122 opened May 15, 2026 by cchuter Loading…
1
server : fix prompt-cache reuse for hybrid/recurrent models examples server
#23121 opened May 15, 2026 by bjahoor Loading…
1 task done
4
ci : fix release symlinks devops improvements to build systems and github actions merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge.
#23119 opened May 15, 2026 by CISC Member Loading…
1
1
webui: Fix handling of MCP resource template parameters examples server/webui server
#23117 opened May 15, 2026 by kubawoo Loading…
server: honour per-request reasoning_budget_tokens in chat completions examples server testing Everything test related
#23116 opened May 15, 2026 by bernardladenthin Loading…
1
metal: reuse K/V in flash-attn vec for spec-decode Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#23114 opened May 15, 2026 by forforever73 Contributor Loading…
@ggerganov
[DRAFT] Support for Zaya1 8B model (depends on PR #22833) ggml changes relating to the ggml tensor library for machine learning model Model specific python python script changes testing Everything test related
#23112 opened May 15, 2026 by Juste-Leo2 Contributor • Draft
vendor : update cpp-httplib to 0.45.0 python python script changes script Script related
#23103 opened May 15, 2026 by cabelo Contributor Loading…
CUDA: Continue directly including cuda/iterator ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23102 opened May 15, 2026 by ORippler Collaborator Loading…
[SYCL] Level Zero detection in ggml_sycl_init ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#23097 opened May 15, 2026 by sanmai Contributor Loading…
Add TheRock 7.13 build target devops improvements to build systems and github actions
#23091 opened May 15, 2026 by superm1 Contributor Loading…
3
common : delegate assistant continuation to underlying template handlers examples server testing Everything test related
#23089 opened May 15, 2026 by aldehir Contributor • Draft
7
Performance optimization for UMA and host-visible buffers in the Vulkan backend ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#23083 opened May 15, 2026 by winstonma Loading…
1
mamba2: remove hardcoded 2x expansion factor and invalid d_inner % d_state check model Model specific python python script changes
#23082 opened May 15, 2026 by limloop Loading…
6
ggml-hexagon: add PAD op HVX kernel ggml changes relating to the ggml tensor library for machine learning Hexagon
#23078 opened May 14, 2026 by pdhinaka Contributor Loading…
convert : filter lora tensor names merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. python python script changes
#23077 opened May 14, 2026 by CISC Member Loading…
1
2
ui: Restructure repo to use tools/ui folder and ui / UI / llama-ui / LLAMA_UI naming build Compilation issues devops improvements to build systems and github actions examples script Script related server/webui server
#23064 opened May 14, 2026 by allozaur Contributor Loading…
@allozaur
20
convert : allow dequantizing some fp8 models python python script changes
#23062 opened May 14, 2026 by cora4 Loading…
download: add option to skip_download examples server
#23059 opened May 14, 2026 by ngxson Contributor Loading…
vulkan: Block-load Q3_K/Q6_K block data and subtract on 32b ints ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#23056 opened May 14, 2026 by TheBlueMatt Contributor Loading…
10
NvFP4 quantized LM head support model Model specific
#23046 opened May 14, 2026 by ynankani Contributor Loading…
13
opencl: allow loading precompiled binary kernels from library ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#23042 opened May 14, 2026 by lhez Contributor • Draft
model: discover hybrid layer types via tensor presence model Model specific
#23037 opened May 14, 2026 by generalchuckles-cm Loading…
ggml-cuda: per-arch MMQ config variable refactor into tabular structure ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23031 opened May 14, 2026 by chrismcmacken Loading…
2
chat : add Nemotron Nano v2 specialized parser testing Everything test related
#23029 opened May 14, 2026 by marcusds Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.