Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
608 Open 7,902 Closed
608 Open 7,902 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

cuda: optimize SOLVE_TRI using registers and FMAF
#17703 opened Dec 2, 2025 by wsbagnsv1 Loading…
vulkan: add more num_blocks instantiations in rms_norm
#17701 opened Dec 2, 2025 by jeffbolznv Loading…
llama-server: fix duplicate HTTP headers in multiple models mode examples server
#17698 opened Dec 2, 2025 by ServeurpersoCom Loading…
1
9
model : add ASR support for LFM2-Audio-1.5B examples 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
#17694 opened Dec 2, 2025 by tdakhran • Draft
1
ggml-zendnn : add ZenDNN backend for AMD CPUs documentation Improvements or additions to documentation examples ggml changes relating to the ggml tensor library for machine learning
#17690 opened Dec 2, 2025 by z-vishal Loading…
Use OpenAI-compatible /v1/models endpoint by default examples server
#17689 opened Dec 2, 2025 by allozaur Loading…
Document how to compile with Vulkan using Debian/Ubuntu packages documentation Improvements or additions to documentation
#17688 opened Dec 2, 2025 by socram8888 Loading…
Add Support for Microsoft Phi-3.5 Vision Instruct Models examples python python script changes
#17687 opened Dec 2, 2025 by z-manoj • Draft
8
vulkan : support conv-2d with large output size ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#17685 opened Dec 2, 2025 by Acly Loading…
1
vulkan: enable mmvq for q2_k on NVIDIA ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#17675 opened Dec 2, 2025 by jeffbolznv Loading…
2
vulkan: perf_logger improvements ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#17672 opened Dec 2, 2025 by jeffbolznv Loading…
2
Add a couple of file types to the text section examples server
#17670 opened Dec 1, 2025 by pwilkin Loading…
1
5
vulkan: fix top_k bug when there are ties in the input ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#17659 opened Dec 1, 2025 by jeffbolznv Loading…
2
ggml: use 'exists( const std::filesystem::path&, std::error_code&)' instead of 'exists( const std::filesystem::path&)' to enhance robustness ggml changes relating to the ggml tensor library for machine learning
#17653 opened Dec 1, 2025 by flyinskyin2013 Loading…
8
ggml: added missing cast sections in memcpy ggml changes relating to the ggml tensor library for machine learning vibe-coded Created with heavy use of LLM assistants, requires human verification
#17651 opened Dec 1, 2025 by GermanAizek Loading…
1
ggml-cpu: remove duplicate conditional check 'iid' ggml changes relating to the ggml tensor library for machine learning
#17650 opened Dec 1, 2025 by GermanAizek Loading…
2
gguf: llama: use = default for trivial constructors and destructors ggml changes relating to the ggml tensor library for machine learning vibe-coded Created with heavy use of LLM assistants, requires human verification
#17649 opened Dec 1, 2025 by GermanAizek Loading…
2
sgemm: reuse loaded vector in AVX dot product calculation ggml changes relating to the ggml tensor library for machine learning vibe-coded Created with heavy use of LLM assistants, requires human verification
#17648 opened Dec 1, 2025 by GermanAizek Loading…
llama-vocab: replace postfix with prefix increment for iterators vibe-coded Created with heavy use of LLM assistants, requires human verification
#17646 opened Dec 1, 2025 by GermanAizek Loading…
7
vec: optimize AVX2/FMA sum-of-squares with loop unrolling and FMA ggml changes relating to the ggml tensor library for machine learning vibe-coded Created with heavy use of LLM assistants, requires human verification
#17642 opened Dec 1, 2025 by GermanAizek Loading…
ggml-quants: use _mm256_testz_si256 for mask checks in AVX2 ggml changes relating to the ggml tensor library for machine learning vibe-coded Created with heavy use of LLM assistants, requires human verification
#17641 opened Dec 1, 2025 by GermanAizek Loading…
ggml-alloc: optimize free block shifting with memmove ggml changes relating to the ggml tensor library for machine learning vibe-coded Created with heavy use of LLM assistants, requires human verification
#17640 opened Dec 1, 2025 by GermanAizek Loading…
vulkan: Replace deprecated VK_EXT_validation_features ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#17637 opened Dec 1, 2025 by rillomas Loading…
1
common : compute average token length from vocabulary
#17632 opened Dec 1, 2025 by yifant-code • Draft
llama-router, the C++ "llama-swap" for llama.cpp examples need feedback Testing and feedback with results are needed server testing Everything test related
#17629 opened Nov 30, 2025 by ServeurpersoCom • Draft
1
@ServeurpersoCom
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.