Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,121 Open 11,299 Closed
1,121 Open 11,299 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

[SYCL] add to support pool_1d, move pool_1d/2d code to pool.cpp/hpp 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
#24584 opened Jun 13, 2026 by arthw Contributor Loading…
ci : add sycl to check-release devops improvements to build systems and github actions
#24583 opened Jun 13, 2026 by CISC Member Loading…
vulkan: support all backend tests for SQR/SQRT/SIN/COS/CLAMP/LEAKY_RELU/NORM ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#24582 opened Jun 13, 2026 by jeffbolznv Contributor Loading…
3
vulkan: Support gated_delta_net with S_v=16 ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#24581 opened Jun 13, 2026 by jeffbolznv Contributor Loading…
vulkan: support more CONCAT types ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend
#24579 opened Jun 13, 2026 by jeffbolznv Contributor Loading…
[SYCL]fix reorder function crash:GGML_ASSERT(block_num_y % num_subgroups ==0) examples ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#24578 opened Jun 13, 2026 by arthw Contributor Loading…
ui: (demo) access server remotely via webrtc examples server/ui
#24577 opened Jun 13, 2026 by ngxson Collaborator • Draft
1
ggml: optimize concat op by replacing per-element memcpy with row-level memcpy ggml changes relating to the ggml tensor library for machine learning
#24575 opened Jun 13, 2026 by sirohikartik Contributor Loading…
1
CI: Replace flake8-no-print with flake8-debug and pin repos to hashes
#24572 opened Jun 13, 2026 by jpodivin Contributor Loading…
Fix #24505 and #18231 build Compilation issues
#24570 opened Jun 13, 2026 by OPS-NeoRetro Loading…
1
CUDA: Add conv3d. ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#24569 opened Jun 13, 2026 by Sero1000 Loading…
1
EXPERIMENT: meta: key external view cache by backend context ggml changes relating to the ggml tensor library for machine learning
#24566 opened Jun 13, 2026 by nycdubliner • Draft
1
[fattn-tune] Add Blackwell MMA config ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#24565 opened Jun 13, 2026 by yaohengxu Contributor Loading…
[SYCL] Enhance set_rows to support q1_0, mxfp4, nvfp4 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
#24564 opened Jun 13, 2026 by arthw Contributor Loading…
CUDA: don't route RDNA3.5 flash attention to the rocWMMA kernel ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#24562 opened Jun 13, 2026 by liminfei-amd Loading…
1 task done
2
CUDA/HIP: chunked MFMA prefill kernel for GATED_DELTA_NET (CDNA) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#24561 opened Jun 13, 2026 by jadenmach2 Contributor Loading…
1
ggml-alloc : check realloc result in alloc_tensor_range ggml changes relating to the ggml tensor library for machine learning
#24559 opened Jun 13, 2026 by ricku777-bear Loading…
1
2
Fix 24486: TP: allows the usage of 8,9,10 gpus for stepfun
#24554 opened Jun 13, 2026 by krampenschiesser Loading…
1
llama: copy tensor_split at model load instead of retaining caller pointer, resolving segfault
#24552 opened Jun 13, 2026 by dragonfyre13 Loading…
llama : disable graph reuse when contexts share memory under SPLIT_MODE_TENSOR
#24549 opened Jun 12, 2026 by nycdubliner Loading…
2 tasks done
1
5
Reduce RSS during BF16 GGUF export python python script changes
#24548 opened Jun 12, 2026 by i386 Loading…
ggml-cuda: use universal launch bounds for MoE MMVQ kernel ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#24547 opened Jun 12, 2026 by batot1 Loading…
1
CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#24546 opened Jun 12, 2026 by ravel7524 Contributor Loading…
docs: add eagle3 to speculative doc documentation Improvements or additions to documentation
#24540 opened Jun 12, 2026 by LiaXLiang Loading…
spec: add spec metrics mean acceptance length and acceptance rate per position examples server
#24536 opened Jun 12, 2026 by ruixiang63 Contributor Loading…
@ggerganov
1
ProTip! no:milestone will show everything without a milestone.