forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 11
Pull requests: ravi9/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
OpenVINO Backend: Support common MTMD ops, fix input tensor creation bugs
#323
opened Sep 20, 2026 by
mostafafaheem
Collaborator
Loading…
ggml-openvino : enable conv ops and more comprehensive conv fusion
#322
opened Sep 19, 2026 by
mostafafaheem
Collaborator
Loading…
OpenVINO Backend: Upgrade graph cache to use n_leaves, node_idx, src_idx, and node type
#321
opened Sep 17, 2026 by
mostafafaheem
Collaborator
Loading…
Optimize NPU performance with KV cache slicing and requantization
#318
opened Sep 15, 2026 by
zhaixuejun1993
Collaborator
Loading…
Enhance NPU optimizations with KV cache slicing and buffer management
#314
opened Sep 8, 2026 by
zhaixuejun1993
Collaborator
Loading…
ggml-openvino : make op support a property of the registry
#307
opened Sep 2, 2026 by
cavusmustafa
Collaborator
•
Draft
ggml-openvino : fix 2D/3D view input shape inference
#303
opened Aug 27, 2026 by
mostafafaheem
Collaborator
•
Draft
[Draft] Refactor OpenVINO backend for better modularity and documentation
#279
opened Aug 11, 2026 by
zhaixuejun1993
Collaborator
Loading…
Refactor OpenVINO backend: isolate op support, manage buffers, and document API
#278
opened Aug 10, 2026 by
zhaixuejun1993
Collaborator
Loading…
OpenVINO: PRD-compliant device enumeration and memory reporting for --list-devices
#256
opened Jul 16, 2026 by
haarika-madaka
Loading…
Refactor OpenVINO backend: move and clean up parameter handling
#240
opened Jul 3, 2026 by
zhaixuejun1993
Collaborator
Loading…
ProTip!
no:milestone will show everything without a milestone.