Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,119 Open 11,535 Closed
1,119 Open 11,535 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

llama: R-SWA reference sliding window attention for Unlimited-OCR examples model Model specific python python script changes
#24975 opened Jun 24, 2026 by sfallah Contributor • Draft
1 task done
openvino: Update to OV 2026.2.1, self-contained release packages, operator improvements devops improvements to build systems and github actions documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning OpenVINO
#24974 opened Jun 24, 2026 by ravi9 Contributor Loading…
4
chat: harden caps check examples
#24973 opened Jun 24, 2026 by pwilkin Member Loading…
1
ggml: add Rockchip NPU (RKNPU2) backend for RK3588 build Compilation issues ggml changes relating to the ggml tensor library for machine learning vibe-coded Created with heavy use of LLM assistants, requires human verification
#24972 opened Jun 24, 2026 by alexinthesky Loading…
2 of 5 tasks
2
common : honor case_sensitive argument in jinja sort and dictsort jinja parser Issues related to the jinja parser testing Everything test related
#24971 opened Jun 24, 2026 by dnislno Loading…
3
server: use status code 403 for disabled features examples python python script changes server/ui server
#24970 opened Jun 24, 2026 by ngxson Collaborator Loading…
1
mtmd: add unlimited-ocr (converter, full MHA) examples python python script changes
#24969 opened Jun 24, 2026 by sfallah Contributor Loading…
common: remove unused json-partial testing Everything test related
#24968 opened Jun 24, 2026 by ngxson Collaborator Loading…
vulkan: disable MMVQ on AMD UMA devices ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#24966 opened Jun 24, 2026 by winstonma Contributor Loading…
1
opencl: support non-contig rows in norm ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#24965 opened Jun 24, 2026 by lhez Contributor • Draft
Improve Server OAI Responses API streaming compatibility examples server
#24957 opened Jun 23, 2026 by boondocklabs Contributor Loading…
server : create context checkpoint on slot restore examples server
#24956 opened Jun 23, 2026 by julio50 Loading…
hexagon: MUL_MAT and MUL_MAT_ID rework : 32x32 tiled weight repack, kernel-params, cached graphs documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Hexagon python python script changes script Script related testing Everything test related
#24954 opened Jun 23, 2026 by max-krasnyansky Member Loading…
bench: Fix misc. bug #24951 - Standard Deviation issues examples
#24953 opened Jun 23, 2026 by surfidaho Loading…
refactor(server): move speculative init to speculative.cpp examples server
#24952 opened Jun 23, 2026 by wadealexc Loading…
cli : move to HTTP-based implementation examples server
#24948 opened Jun 23, 2026 by ngxson Collaborator Loading…
14
cuda : prevent integer truncation and overflow errors when using KQ mask strides in flash_attn_mask_to_KV_max kernel CUDA Related to the CUDA backend ggml changes relating to the ggml tensor library for machine learning
#24945 opened Jun 23, 2026 by fairydreaming Collaborator Loading…
1
1
server : disable embeddings/pooling on the speculative draft/MTP context examples server
#24942 opened Jun 23, 2026 by liminfei-amd Contributor Loading…
1 task done
1
sycl : clamp softmax input to avoid underflow 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. SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#24941 opened Jun 23, 2026 by Jassieluo Loading…
1
llama : meta split state for combined gate+up ffn_up (phi3)
#24936 opened Jun 23, 2026 by krystophny Loading…
1
llama : synchronize context before backend teardown testing Everything test related
#24935 opened Jun 23, 2026 by krystophny Loading…
3
Lllama sampler speedups/fixes testing Everything test related
#24934 opened Jun 23, 2026 by matthiasstraka Contributor Loading…
docs: note ROCm HIP SDK 7.1.1 + MSVC >=14.40 <cmath> build failure and workaround (Windows) documentation Improvements or additions to documentation
#24929 opened Jun 23, 2026 by Dixon-Cider Loading…
Fix conditional to display 'LLAMA_SPLIT_MODE_TENSOR not implemented for architecture' message
#24926 opened Jun 23, 2026 by kdkd Loading…
Minimax M3 EAGLE3 Support model Model specific python python script changes testing Everything test related
#24925 opened Jun 23, 2026 by nick-tonjum Loading…
1
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.