Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
742 Open 9,129 Closed
742 Open 9,129 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-cpu: optimise s390x multiply extend instructions ggml changes relating to the ggml tensor library for machine learning
#20032 opened Mar 2, 2026 by taronaeo Loading…
cann: support flash attention for head dim not multiple of 16 Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#20031 opened Mar 2, 2026 by noemotiovon Loading…
1
gguf-py: add type validation to GGUFWriter.add_key_value python python script changes
#20023 opened Mar 1, 2026 by Scottcjn Loading…
1
json-schema: handle typeless schema nodes as any-value testing Everything test related
#20021 opened Mar 1, 2026 by Scottcjn Loading…
1
gguf: add big-endian magic "FUGG" for explicit endianness detection ggml changes relating to the ggml tensor library for machine learning python python script changes testing Everything test related
#20019 opened Mar 1, 2026 by Scottcjn Loading…
1
2
vulkan: add UMA zero-copy async transfers and fix event_record deferred memcpy handling ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#20018 opened Mar 1, 2026 by neilopet Loading…
3
vulkan: add sparse OOM fallback for large UMA allocations and chunked staging fallback ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#20017 opened Mar 1, 2026 by neilopet Loading…
1
feat: add --cache-only flag to skip model re-download
#20010 opened Mar 1, 2026 by lonnie08 Loading…
1
server: add Qwen3-Reranker instruction support examples python python script changes server
#20009 opened Mar 1, 2026 by schwebke Loading…
2
webui: add PWA support examples server
#19995 opened Feb 28, 2026 by matous-volf Loading…
common : fix common_chat_peg_parse for incomplete utf-8 sequence tail testing Everything test related
#19992 opened Feb 28, 2026 by akreal Loading…
build: fix various compiler warnings on Windows MinGW examples testing Everything test related
#19990 opened Feb 28, 2026 by jonathanjacksonswe Loading…
vulkan: tune MMVQ for Intel Windows ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#19988 opened Feb 28, 2026 by 0cc4m Loading…
3
ggml : add GGML_OP_ADD1 for metal Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#19987 opened Feb 28, 2026 by aisk Loading…
1
cli : add command and file auto-completion examples
#19985 opened Feb 28, 2026 by CISC Loading…
Re-enable manual LoRA adapter free
#19983 opened Feb 28, 2026 by PopFlamingo Loading…
Add file existence and type checks for imatrix examples
#19974 opened Feb 28, 2026 by geoffmunn Loading…
feat: add --threads-all option to llama-bench examples
#19971 opened Feb 28, 2026 by hobostay Loading…
4 tasks done
1
server: batch checkpoints to support kvcache context truncation examples server
#19970 opened Feb 28, 2026 by aagit Loading…
3
Fix logic for retrieving schema items in json_schema_to_grammar.py examples python python script changes
#19968 opened Feb 28, 2026 by RayXu14 Loading…
2
ggml webgpu: fix workgroup dispatch limit for large batch sizes ggml changes relating to the ggml tensor library for machine learning
#19965 opened Feb 28, 2026 by abhijitramesh Loading…
3
Use fp32 in cuBLAS V100 to avoid overflows, env variables to override cuBLAS compute type documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#19959 opened Feb 27, 2026 by wallentri88 Loading…
1
tools : enable kvu in perplexity for hellaswag, winogrande, multiple-choice examples
#19954 opened Feb 27, 2026 by angt Loading…
scripts : improve get-wikitext-2.sh script Script related
#19952 opened Feb 27, 2026 by angt Loading…
7
[New quant] Q3_PT 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
#19941 opened Feb 26, 2026 by pwilkin • Draft
43
ProTip! Mix and match filters to narrow down what you’re looking for.