Skip to content

Pull requests: PrismML-Eng/llama.cpp

New pull request New
6 Open 52 Closed
6 Open 52 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

ggml-cpu: enable Q2_0 VNNI kernel on AVX-VNNI-only CPUs ggml
#76 opened Jul 15, 2026 by gondoi Loading…
cuda: speed up Q1_0 extraction with byte permutes CUDA ggml
#73 opened Jul 15, 2026 by bri-prism Loading…
3 of 4 tasks
5
perf(ggml-cpu): enable Q2_0 fast path on AVX-VNNI CPUs (3.2x on Intel 12th-14th gen) ggml
#72 opened Jul 15, 2026 by thtro Loading…
3
Q2_0 group 64: CUDA backend Apple Metal conversion CUDA documentation Improvements or additions to documentation ggml Hexagon jinja parser model OpenCL server/ui server SYCL testing Vulkan
#43 opened Jun 10, 2026 by khosravipasha Collaborator • Draft
5
Bit-interleaved Q1_0 8x32 repack kernels for x86 AVX2 ggml
#29 opened May 2, 2026 by pl752 • Draft
33
opencl: Q1_0 support first attempt ggml OpenCL
#25 opened Apr 15, 2026 by khosravipasha Collaborator • Draft
6
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.