Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
589 Open 7,716 Closed
589 Open 7,716 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 : add ggml_top_k Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#17365 opened Nov 18, 2025 by ggerganov • Draft
4 tasks
server: split server.cpp code into server/common/task/queue examples server
#17362 opened Nov 18, 2025 by ngxson Loading…
3
mtmd: add Eagle2-VL vision and projector support examples python python script changes
#17360 opened Nov 18, 2025 by YaelGitAccount Loading…
1
convert : use self.block_count everywhere instead of reading hparams python python script changes
#17359 opened Nov 18, 2025 by CISC Loading…
1
vulkan: force full subgroups for flash attention to fix intel subgroup crash ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#17356 opened Nov 18, 2025 by 0cc4m Loading…
1
2
ggml-hexagon: fix swiglu failure at test-backend-ops ggml changes relating to the ggml tensor library for machine learning
#17344 opened Nov 18, 2025 by chraac • Draft
4
Throughput improvement for small batch sizes ggml changes relating to the ggml tensor library for machine learning
#17342 opened Nov 18, 2025 by uttampc1 Loading…
vulkan: Disable skip-neg-inf logic for Intel ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#17335 opened Nov 17, 2025 by jeffbolznv Loading…
1
CANN: Refactor evaluate_and_capture_cann_graph Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#17333 opened Nov 17, 2025 by rauletorresc Loading…
4
Fix too relaxed check on CUDA "fast copy" (can_be_transposed) condition ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17332 opened Nov 17, 2025 by pwilkin Loading…
22
Fix locale-dependent float printing in GGUF metadata
#17331 opened Nov 17, 2025 by ssam18 Loading…
1
1
Fix grammar README: Update non-terminal naming rules
#17330 opened Nov 17, 2025 by ssam18 Loading…
1
1
cuda : support non-contiguous i32 to i32 copy ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17326 opened Nov 17, 2025 by CISC Loading…
3
arg: slightly reduce compilation time
#17324 opened Nov 17, 2025 by ngxson Loading…
3
Fix transposed SOLVE_TRI result ggml changes relating to the ggml tensor library for machine learning
#17323 opened Nov 17, 2025 by pwilkin Loading…
2
vulkan: implement ADD1, ARANGE, FILL, SOFTPLUS, STEP, ROUND, CEIL, FLOOR, TRUNC documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#17319 opened Nov 17, 2025 by giuseppe Loading…
9
ggml-cpu: extend support for RVV floating-point kernels ggml changes relating to the ggml tensor library for machine learning
#17318 opened Nov 17, 2025 by taimur-10x Loading…
ggml-cpu:add RISC-V RVV (Zvfh) optimization for FP16 vector scaling ggml changes relating to the ggml tensor library for machine learning
#17314 opened Nov 17, 2025 by ixgbe Loading…
3
vulkan: support larger argsort ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#17313 opened Nov 17, 2025 by jeffbolznv Loading…
ggml-cpu: Don't pass -mpowerpc64 when -mcpu already implies it ggml changes relating to the ggml tensor library for machine learning
#17308 opened Nov 16, 2025 by JeremyRand Loading…
1
Fix json schema with '\' in literals
#17307 opened Nov 16, 2025 by i-v-s Loading…
1
3
[model] Add support for Plamo3 model Model specific python python script changes
#17304 opened Nov 16, 2025 by mmnga Loading…
5
release: fix duplicate libs, store symbolic links devops improvements to build systems and github actions
#17299 opened Nov 16, 2025 by taronaeo Loading…
1
5
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#17276 opened Nov 14, 2025 by slaren Loading…
4
Per-conversation system message with UI displaying, edition & branching examples server
#17275 opened Nov 14, 2025 by allozaur • Draft
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.