Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
728 Open 9,033 Closed
728 Open 9,033 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

ci : fix rocm archive name devops improvements to build systems and github actions
#19808 opened Feb 22, 2026 by CISC Loading…
server: add --log-output option examples server
#19807 opened Feb 22, 2026 by tarruda Loading…
CUDA: add CDNA3 MFMA support for flash attention MMA kernel ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#19806 opened Feb 22, 2026 by Jayluci4 Loading…
3 of 4 tasks
3
common : fix improper trimming in XML parser on complete message
#19805 opened Feb 22, 2026 by aldehir Loading…
1
1
Fix wrong cli-argument in documentation examples server
#19804 opened Feb 22, 2026 by Menkalian Loading…
1
1
model: Add Kanana-2 model support python python script changes
#19803 opened Feb 22, 2026 by HelloKS Loading…
llama: end-to-end tests testing Everything test related
#19802 opened Feb 22, 2026 by JohannesGaessler • Draft
model: add qwen3omnimoe architecture support (text-only)
#19800 opened Feb 22, 2026 by SiaoZeng Loading…
1
chat: fix llama-server image placeholder issue for PaddleOCR-VL
#19799 opened Feb 22, 2026 by megemini Loading…
common : add more aliases for sampler CLI params
#19797 opened Feb 22, 2026 by ddh0 Loading…
Add model metadata loading from huggingface for use with tests requiring real model data testing Everything test related
#19796 opened Feb 22, 2026 by bartowski1182 Loading…
3
vulkan: fix coopmat1 without bf16 support ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19793 opened Feb 22, 2026 by jeffbolznv Loading…
tools : add learning-cache tool for persistent latent context examples
#19791 opened Feb 22, 2026 by arkavo-com Loading…
7 of 10 tasks
2
vulkan: fix data race in mul_mat_id shader ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19790 opened Feb 21, 2026 by jeffbolznv Loading…
jinja: correct stats for tojson and string filters jinja parser Issues related to the jinja parser testing Everything test related
#19785 opened Feb 21, 2026 by ngxson Loading…
cli : provide model with text filename examples server
#19783 opened Feb 21, 2026 by CISC Loading…
[WIP] ggml-hexagon: convert f32 to f16 - fa opt part4 ggml changes relating to the ggml tensor library for machine learning
#19780 opened Feb 21, 2026 by chraac • Draft
1
Clean up per-thread parameter buffer pool and job submission logic ggml changes relating to the ggml tensor library for machine learning
#19772 opened Feb 20, 2026 by nikhilJain17 • Draft
Document custom default webui preferences in server readme examples server
#19771 opened Feb 20, 2026 by woof-dog Loading…
quantize : refactor llama-quant.cpp (imatrix fail-early)
#19770 opened Feb 20, 2026 by ddh0 • Draft
WIP: ggml : add NVFP4 quantization type support Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes testing Everything test related Vulkan Issues specific to the Vulkan backend
#19769 opened Feb 20, 2026 by richarddd Loading…
4
vulkan: check for memory overlap before doing fusion ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19768 opened Feb 20, 2026 by jeffbolznv Loading…
Server: allow immediate reuse of http port examples server
#19763 opened Feb 20, 2026 by jpm-canonical Loading…
1
3
Proposal: Guidelines for quantization schemes
#19762 opened Feb 20, 2026 by pwilkin Loading…
11
grammar : Fix grammar root symbol check bugfix fixes an issue or bug grammar Issues related to the GBNF (grammar) code
#19761 opened Feb 20, 2026 by AsbjornOlling Loading…
4
ProTip! Add no:assignee to see everything that’s not assigned.