Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
609 Open 7,844 Closed
609 Open 7,844 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

common : add minimalist multi-thread progress bar
#17602 opened Nov 29, 2025 by angt Loading…
cuda : add error checking for cudaMemcpyAsync in argsort (#12836) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17599 opened Nov 29, 2025 by Mahekk357 Loading…
1
Load Sliding Window Attention (SWA) pattern from GGUF metadata
#17597 opened Nov 29, 2025 by taylorchu Loading…
1
server: move server-context to its own cpp|h examples server
#17595 opened Nov 29, 2025 by ngxson Loading…
4
clip: fix nb calculation for qwen3-vl examples
#17594 opened Nov 29, 2025 by ngxson Loading…
2
Feature/kimi linear support ggml changes relating to the ggml tensor library for machine learning model Model specific Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#17592 opened Nov 29, 2025 by cacaview Loading…
34
update LLAMA_ARG_KV_SPLIT --> LLAMA_ARG_KV_UNIFIED to match CLI argument
#17588 opened Nov 29, 2025 by ddh0 Loading…
Override SSM_A op for Qwen3 Next to reduce splits model Model specific
#17587 opened Nov 29, 2025 by pwilkin Loading…
9
Improve Qwen3-Next Speed model Model specific
#17585 opened Nov 29, 2025 by lovedheart • Draft
1
Add support for CUMSUM and TRI for CUDA. ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17584 opened Nov 28, 2025 by pwilkin Loading…
7
cmake: fix macOS build with -DGGML_BACKEND_DL=ON ggml changes relating to the ggml tensor library for machine learning
#17581 opened Nov 28, 2025 by giladgd Loading…
Add safetensors support
#17580 opened Nov 28, 2025 by ericcurtin • Draft
1
Add PagedAttention support (experimental, CUDA only) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17579 opened Nov 28, 2025 by ericcurtin Loading…
4
model: LFM2-VL fixes examples ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#17577 opened Nov 28, 2025 by tdakhran Loading…
13
HIP: enable WMMA-MMQ INT kernels for RDNA 3 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#17576 opened Nov 28, 2025 by jiachengjason • Draft
mtmd: support dots.ocr examples python python script changes
#17575 opened Nov 28, 2025 by ngxson • Draft
1
[SYCL] enhance argsort for UT ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#17573 opened Nov 28, 2025 by NeoZhangJianyu Loading…
2
Server: Change Invalid Schema from Server Error (500) to User Error (400) examples python python script changes server testing Everything test related
#17572 opened Nov 28, 2025 by chadvoegele Loading…
7
ggml-hexagon: fix rope failure at test-backend-ops ggml changes relating to the ggml tensor library for machine learning
#17565 opened Nov 28, 2025 by chraac Loading…
1
CANN: The Ger operator of OUT_PROD is not supported on the 310p device Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#17563 opened Nov 28, 2025 by TianHao324 Loading…
2
Fix unreadable user markdown colors and truncate long texts in deletion dialogs examples server
#17555 opened Nov 27, 2025 by ServeurpersoCom Loading…
New llama-run examples server
#17554 opened Nov 27, 2025 by ericcurtin Loading…
16
cmake : add option to build and link LibreSSL
#17552 opened Nov 27, 2025 by angt Loading…
2
ggml-cpu: Add operator-level execution time profiling ggml changes relating to the ggml tensor library for machine learning
#17544 opened Nov 27, 2025 by kimminsu38oo Loading…
CANN: add support for partial RoPE and Vision mode Ascend NPU issues specific to Ascend NPUs ggml changes relating to the ggml tensor library for machine learning
#17543 opened Nov 27, 2025 by noemotiovon Loading…
40
ProTip! Filter pull requests by the default branch with base:master.