Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
Clear current search query, filters, and sorts
622 Open 8,149 Closed
622 Open 8,149 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

arg: allow -kvu flag for llama-perplexity
#18117 by TrevorS was merged Dec 17, 2025 Loading…
model: fix LFM2 missing tensors
#18105 by ngxson was merged Dec 16, 2025 Loading…
1
llama-fit-params: force disable mlock
#18103 by JohannesGaessler was merged Dec 16, 2025 Loading…
1
llama-fit-params: lower ctx size for multi GPU
#18101 by JohannesGaessler was merged Dec 16, 2025 Loading…
1
2
gguf-py: allow converting multi-tensor models from read-only locations python python script changes
#18100 by ykhrustalev was merged Dec 17, 2025 Loading…
llama-fit-params: fix underflow for dense models
#18095 by JohannesGaessler was merged Dec 16, 2025 Loading…
1
ggml : use WARP_SIZE/2 for argmax reduction offset ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18092 by Aadeshveer was merged Dec 17, 2025 Loading…
2
llama-fit-params: QoL impr. for prints/errors examples
#18089 by JohannesGaessler was merged Dec 16, 2025 Loading…
3
model-conversion : remove -fa option in model card template [no ci] examples
#18088 by danbev was merged Dec 16, 2025 Loading…
1
model-conversion : add note about verifying previous models examples
#18082 by danbev was merged Dec 16, 2025 Loading…
security : add collaborator guidance
#18081 by ggerganov was merged Dec 16, 2025 Loading…
model-conversion : use CONVERTED_EMBEDDING_MODEL for embedding_verify_logits examples
#18079 by danbev was merged Dec 16, 2025 Loading…
llama: Include algorithm header needed for C++23
#18078 by cpeterso was merged Dec 16, 2025 Loading…
NVIDIA Nemotron 3 parsing testing Everything test related
#18077 by aldehir was merged Dec 16, 2025 Loading…
3
Update README.md incorrect argument examples server
#18073 by 2114L3 was merged Dec 16, 2025 Loading…
3
ci : separate webui from server devops improvements to build systems and github actions
#18072 by CISC was merged Dec 16, 2025 Loading…
5
llama: fix early stop in params_fit if ctx is set
#18070 by JohannesGaessler was merged Dec 16, 2025 Loading…
1
9
convert : move rope_parameters to TextModel class python python script changes
#18061 by CISC was merged Dec 15, 2025 Loading…
4
llama : add support for NVIDIA Nemotron 3 Nano model Model specific python python script changes
#18058 by danbev was merged Dec 16, 2025 Loading…
24
server: Fix router proxying to child processes when --host is specified examples server
#18054 by wbtek was closed Dec 17, 2025 Loading…
14
arch: refactor LLM_TENSOR_NAMES documentation Improvements or additions to documentation refactoring Refactoring
#18051 by ngxson was merged Dec 16, 2025 Loading…
cmake: CLI should explicitly depend on mtmd headers now examples
#18045 by 65a was closed Dec 15, 2025 • Draft
2
model: support GLM4V vision encoder examples model Model specific python python script changes
#18042 by ngxson was merged Dec 16, 2025 Loading…
1
17
preset: handle negated arg, reverse the meaning if needed
#18041 by ngxson was merged Dec 14, 2025 Loading…
1
model: add KORMo model model Model specific python python script changes
#18032 by HelloKS was merged Dec 15, 2025 Loading…
10
ProTip! Mix and match filters to narrow down what you’re looking for.