Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
943 Open 10,354 Closed
943 Open 10,354 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

Support jina-reranker-v3 cross-encoder architecture python python script changes testing Everything test related
#22576 opened May 1, 2026 by Dampish0 • Draft
1
server: support input_image in function_call_output (#20663) examples server
#22575 opened May 1, 2026 by Empressia Loading…
hexagon: enable non-contiguous row tensor support for unary ops ggml changes relating to the ggml tensor library for machine learning Hexagon
#22574 opened May 1, 2026 by aparmp-quic Contributor Loading…
llama-quant : fix --tensor-type when default qtype is overriden
#22572 opened May 1, 2026 by ddh0 Contributor Loading…
1
Swap out F16 for BF16 in Q8_1 activations to avoid overflowing values ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22571 opened May 1, 2026 by bartowski1182 Contributor • Draft
[Draft] feat: implement paged KV cache and attention examples ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#22569 opened Apr 30, 2026 by matiaslin Contributor • Draft
5
ggml-cpu: fix msvc c2440 cast error for m512bh and m256bh in sgemm.cpp ggml changes relating to the ggml tensor library for machine learning
#22568 opened Apr 30, 2026 by nanodan52 Loading…
devops: SYCL: upgraded the default compute-runtime version devops improvements to build systems and github actions
#22567 opened Apr 30, 2026 by WizardlyBump17 Contributor Loading…
fix: consistent memory breakdown for models loaded with no_alloc testing Everything test related
#22566 opened Apr 30, 2026 by giladgd Contributor Loading…
2
cmake: fix MATH_LIBRARY check on Windows MSVC ggml changes relating to the ggml tensor library for machine learning
#22564 opened Apr 30, 2026 by ServeurpersoCom Contributor Loading…
3
chat: preserve media markers for typed-content templates
#22563 opened Apr 30, 2026 by AlexonOliveiraRH Loading…
1
server : avoid checkpoint data host copies examples server
#22558 opened Apr 30, 2026 by ggerganov Member Loading…
ggml-virtgpu: fix transitive dependency in headers ggml changes relating to the ggml tensor library for machine learning
#22557 opened Apr 30, 2026 by Juste-Leo2 Loading…
2
kleidiai : update to v1.24.0 and use release archive ggml changes relating to the ggml tensor library for machine learning
#22549 opened Apr 30, 2026 by chaxu01 Collaborator Loading…
spec : allow for multiple spec types (chains of speculators) examples server
#22546 opened Apr 30, 2026 by petersid2022 Contributor Loading…
server: support Vertex AI compatible API examples python python script changes server
#22545 opened Apr 30, 2026 by ngxson Contributor • Draft
11
docs : update speculative decoding parameters after refactor (#22397) documentation Improvements or additions to documentation
#22539 opened Apr 30, 2026 by ggerganov Member • Draft
1
server : validate --tools CLI argument against known tool names examples server
#22538 opened Apr 30, 2026 by ggerganov Member • Draft
1 task done
server : fix image blocks in tool_result being dropped during Anthropic→OpenAI conversion examples python python script changes server
#22536 opened Apr 30, 2026 by quei4r Loading…
2 tasks done
4
fix: CUDA device PCI bus ID de-dupe OOMing (ignoring other 3 gpus entirely) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22533 opened Apr 29, 2026 by lucyknada Loading…
2
[Model] Support MiniCPM-V 4.6 documentation Improvements or additions to documentation examples python python script changes
#22529 opened Apr 29, 2026 by tc-mb Contributor Loading…
20
sycl: Add optional USM system allocations documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22526 opened Apr 29, 2026 by ifdu Loading…
1
ggml-cpu: optimize ggml_gemm_q4_K_8x8_q8_K interleaving/staging for AVX-512 (and AVX2) ggml changes relating to the ggml tensor library for machine learning
#22525 opened Apr 29, 2026 by HyeongiJeon Loading…
Programmatic Dependent Launch (PDL) for more performance on newer NVIDIA GPUs (Hopper+) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22522 opened Apr 29, 2026 by aendk Contributor • Draft
7
mtmd : add Nemotron 3 Nano Omni support (parakeet) examples python python script changes
#22520 opened Apr 29, 2026 by danbev Member • Draft
11
ProTip! Adding no:label will show everything without a label.