Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
644 Open 8,499 Closed
644 Open 8,499 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

model: qwen3next: no concat-in-loop model Model specific
#18759 opened Jan 11, 2026 by ngxson • Draft
1
vocab: add tokenizer support for jina-embeddings-v2-base-zh python python script changes
#18756 opened Jan 11, 2026 by o7si Loading…
Kimi-Linear support (backend agnostic + MLA KV cache) ggml changes relating to the ggml tensor library for machine learning model Model specific python python script changes
#18755 opened Jan 11, 2026 by ymcki Loading…
1
security: make it clear about subtopics in server
#18754 opened Jan 11, 2026 by ngxson Loading…
1
tests : refactor test-backend-sampler devops improvements to build systems and github actions testing Everything test related
#18753 opened Jan 11, 2026 by ggerganov Loading…
fix: OOB reads in UGM tokenizer (precompiled_charsmap handling)
#18750 opened Jan 11, 2026 by hourhl Loading…
Vulkan: Optimize Matmul parameters for AMD GPUs with Coopmat support ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18749 opened Jan 11, 2026 by 0cc4m Loading…
ggml, llama : add CPU paged attention for memory-efficient KV cache examples ggml changes relating to the ggml tensor library for machine learning model Model specific testing Everything test related
#18747 opened Jan 11, 2026 by pestopoppa Loading…
5 tasks done
2
fix: use actual tensor embedding dimension instead of model parameter
#18745 opened Jan 10, 2026 by chrismuzyn Loading…
1
1
server: add missing rerank and chat presets (#10932)
#18742 opened Jan 10, 2026 by ingyukoh Loading…
POC: group gate_exps and up_exps + fix mxfp4 alignment for PP boost model Model specific python python script changes
#18740 opened Jan 10, 2026 by am17an • Draft
llama: add canaries to Markdown files
#18735 opened Jan 10, 2026 by JohannesGaessler Loading…
8
feat: add support for WeDLM architecture python python script changes
#18731 opened Jan 10, 2026 by feedseawave Loading…
5 tasks done
6
lookup, lookahead: fix crash when n_ctx not specified examples
#18729 opened Jan 10, 2026 by pestopoppa Loading…
1
llama: fix pooled embedding readback sizing/stride and state I/O
#18723 opened Jan 9, 2026 by retr0reg Loading…
1
model: Add VAETKI support examples model Model specific python python script changes
#18719 opened Jan 9, 2026 by dororodoroddo Loading…
5 tasks done
33
ggml: new backend for Virglrenderer API Remoting acceleration (v2) build Compilation issues ggml changes relating to the ggml tensor library for machine learning python python script changes
#18718 opened Jan 9, 2026 by kpouget Loading…
@taronaeo
8
Support parsing JSON into grammar for schemas with no type and no properties
#18711 opened Jan 9, 2026 by markrietveld • Draft
1
1
vulkan: Check maxStorageBufferRange in supports_op ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#18709 opened Jan 9, 2026 by jeffbolznv Loading…
fix text spacing in print_info
#18708 opened Jan 9, 2026 by ddh0 Loading…
6
ggml-metal: Clean up files used for embedded build Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#18705 opened Jan 9, 2026 by DaAwesomeP Loading…
[WIP] ggml-opencl: op args init refactoring ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#18701 opened Jan 8, 2026 by chraac • Draft
Improving inference speed for the repack buffer type on NUMA architectures ggml changes relating to the ggml tensor library for machine learning
#18698 opened Jan 8, 2026 by zzjianhui Loading…
debug : include LLAMA_POOLING_TYPE_UNSPECIFIED in pooling check examples
#18692 opened Jan 8, 2026 by danbev Loading…
2
ggml-cuda: extend concat support for more types ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#18690 opened Jan 8, 2026 by Lourdle Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.