Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
665 Open 8,602 Closed
665 Open 8,602 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

server: fix json_schema response_format handling
#18963 opened Jan 20, 2026 by khasinski Loading…
3 tasks done
1
1
cli : fix reasoning responses in CLI
#18961 opened Jan 20, 2026 by ngxson Loading…
3
CUDA: use mmvq for mul-mat-id for small batch sizes
#18958 opened Jan 20, 2026 by am17an Loading…
common, server : use the same User-Agent by default examples server
#18957 opened Jan 20, 2026 by angt Loading…
jinja : implement mixed type object keys jinja parser Issues related to the jinja parser testing Everything test related
#18955 opened Jan 20, 2026 by CISC Loading…
27
model-conversion : add tensor-info.py utility examples python python script changes
#18954 opened Jan 20, 2026 by danbev Loading…
CUDA: add gqa_ratio 4 for GLM 4.7 flash ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#18953 opened Jan 20, 2026 by am17an Loading…
1
5
quant : manual overrides of tensor types take precedence
#18952 opened Jan 20, 2026 by ggerganov Loading…
1
vulkan: Enable topk_moe fusion for GLM-4.7-Flash ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18947 opened Jan 20, 2026 by jeffbolznv Loading…
vulkan: Remove transfer_ctx, do everything in compute_ctx. ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18945 opened Jan 20, 2026 by jeffbolznv Loading…
1
5
vulkan: support flash attention GQA/split_k with small batches ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#18938 opened Jan 19, 2026 by jeffbolznv Loading…
chore: Update outdated GitHub Actions versions devops improvements to build systems and github actions
#18935 opened Jan 19, 2026 by pgoslatara Loading…
4
ggml-cuda: enable cuda-graphs for n-cpu-moe ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes script Script related
#18934 opened Jan 19, 2026 by am17an Loading…
7
ggml-rpc: Add graceful error handling for graph compute operations ggml changes relating to the ggml tensor library for machine learning
#18933 opened Jan 19, 2026 by mfahsold Loading…
2
2
ggml-cpu: add RISC-V Vector support for SSM scan (f32) in Mamba-2 ggml changes relating to the ggml tensor library for machine learning
#18926 opened Jan 19, 2026 by ixgbe Loading…
common: add reranking server configuration preset
#18923 opened Jan 18, 2026 by ingyukoh Loading…
metal : support virtual devices Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#18919 opened Jan 18, 2026 by ggerganov Loading…
vulkan: Use mul_mat_vec_id for small values of n ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18918 opened Jan 18, 2026 by jeffbolznv Loading…
fix: Use tabular-nums for chat message statistics examples server
#18915 opened Jan 18, 2026 by nathanlesage Loading…
4
introduce legacy-torch flag for backward compatibility on older Intel… python python script changes
#18908 opened Jan 18, 2026 by csabakecskemeti Loading…
1
graph : utilize ggml_build_forward_select() to avoid reallocations devops improvements to build systems and github actions model Model specific
#18898 opened Jan 17, 2026 by ggerganov Loading…
3
HIP: add mmf for CDNA ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18896 opened Jan 17, 2026 by zhang-hui-yulo Loading…
2 of 3 tasks
2
llama: fix integer type consistency in split helpers
#18894 opened Jan 17, 2026 by MaheshJakkala Loading…
1
examples: llama evaluation tool for mmlu, aime, gsm8k examples python python script changes
#18892 opened Jan 17, 2026 by gatbontonpc • Draft
11
fit-params : Handle n_ctx 0 for models that entirely fit with n_ctx_train
#18890 opened Jan 17, 2026 by 65a Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.