Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
900 Open 10,016 Closed
900 Open 10,016 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

build: include libmtmd in Apple XCFramework (opt-in LLAMA_BUILD_MTMD) build Compilation issues examples
#21935 opened Apr 15, 2026 by theabecaster Loading…
5 tasks done
1
cmake: scope ASM to kleidiai on Windows ggml changes relating to the ggml tensor library for machine learning
#21934 opened Apr 15, 2026 by texasich Contributor Loading…
gguf-py: add type and range validation to GGUFWriter.add_key_value python python script changes
#21931 opened Apr 15, 2026 by anmolg1997 Loading…
1
nix: support unified apple-sdk devops improvements to build systems and github actions nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
#21928 opened Apr 14, 2026 by kushagharahi Contributor Loading…
fix: correct CPU counting on multi-NUMA and SMT systems
#21925 opened Apr 14, 2026 by mraleko Loading…
1
1
fix: llama-finetune backward pass crashes examples ggml changes relating to the ggml tensor library for machine learning
#21924 opened Apr 14, 2026 by System64fumo Loading…
1
common : add --hf-prune-old-files (-hfp) parameter to automatically delete outdated HF files
#21923 opened Apr 14, 2026 by Cr4xy Loading…
sycl : fused MoE mul_mat_vec_q for TG ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#21920 opened Apr 14, 2026 by abotsis Loading…
ggml: improve SPIR-V headers detection with __has_include while preserving original _WIN32 logic ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#21918 opened Apr 14, 2026 by EmilAskerov Loading…
1
Added sve tuned code for gemm_q8_0_4x8_q8_0() kernel ggml changes relating to the ggml tensor library for machine learning
#21916 opened Apr 14, 2026 by hrushitfujitsu Loading…
HIP: Remove unesscary NCCL_CHECK ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#21914 opened Apr 14, 2026 by IMbackK Collaborator Loading…
CUDA: require explicit opt-in for P2P access documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#21910 opened Apr 14, 2026 by JohannesGaessler Contributor Loading…
3
feat: migrate to PEP 621 and add uv support python python script changes
#21907 opened Apr 14, 2026 by dhdaines Loading…
1
1
server: ignore reasoning content from transcription api examples server
#21905 opened Apr 14, 2026 by ngxson Contributor Loading…
1
feat: add MPNet model architecture model Model specific python python script changes
#21904 opened Apr 14, 2026 by Vertex-DS Loading…
ci: disable test-backend-ops on Vulkan llvmpipe run devops improvements to build systems and github actions
#21901 opened Apr 14, 2026 by 0cc4m Contributor Loading…
1
ggml-cuda: enable concurrent streams for linear attention ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#21897 opened Apr 14, 2026 by am17an Contributor Loading…
6
ggml-cuda: Blackwell native NVFP4 support ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#21896 opened Apr 14, 2026 by michaelw9999 Contributor Loading…
9
autoparser: support case of JSON_NATIVE with per-call markers testing Everything test related
#21892 opened Apr 14, 2026 by pwilkin Member Loading…
CUDA: manage NCCL communicators in context ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#21891 opened Apr 14, 2026 by JohannesGaessler Contributor Loading…
2
7
server: add --parallel-tool-calling flag to enable by default examples server
#21890 opened Apr 14, 2026 by Linus467 Loading…
2
common : add common_chat_split_by_role testing Everything test related
#21885 opened Apr 14, 2026 by aldehir Contributor • Draft
ggml-webgpu: Command batching ggml changes relating to the ggml tensor library for machine learning WebGPU
#21873 opened Apr 13, 2026 by reeselevine Contributor • Draft
ggml-webgpu: Fix dequantization helpers to not pass in pointers 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. WebGPU
#21872 opened Apr 13, 2026 by reeselevine Contributor Loading…
1
vulkan: add barrier after writetimestamp ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#21865 opened Apr 13, 2026 by jeffbolznv Contributor Loading…
ProTip! Follow long discussions with comments:>50.