forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 8
Pull requests: ravi9/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Enable architecture test for qwen3vl in OpenVINO backend
ggml
OpenVINO
#173
opened May 19, 2026 by
zhaixuejun1993
Collaborator
Loading…
update stateful_kv_size correctly in mismatch case
ggml
OpenVINO
#170
opened May 19, 2026 by
wine99
Collaborator
Loading…
Enable RMS_NORM and VIEW in OpenVINO backend, remove op_case 2 for rope
ggml
OpenVINO
#153
opened May 7, 2026 by
zhaixuejun1993
Collaborator
Loading…
Enable OpenVINO backend fallback to CPU backend
ggml
OpenVINO
#130
opened Apr 13, 2026 by
zhaixuejun1993
Collaborator
Loading…
workarround for llama-embedding accuracy issue
#67
opened Mar 11, 2026 by
zhaixuejun1993
Collaborator
Loading…
Xuejun/0310 gpt oss success
devops
documentation
Improvements or additions to documentation
OpenVINO
#61
opened Mar 10, 2026 by
zhaixuejun1993
Collaborator
Loading…
ggml-openvino: Add graph capture API support for GGUFReaderV2
devops
documentation
Improvements or additions to documentation
jinja parser
Nvidia GPU
OpenVINO
Vulkan
#55
opened Mar 5, 2026 by
shahkarnav115-beep
Loading…
Add ov falback to CPU machinisim & verified with OV without ROPE support
#42
opened Feb 9, 2026 by
zhaixuejun1993
Collaborator
Loading…
Stateful fix for shape errors after rebase
#35
opened Jan 22, 2026 by
cavusmustafa
Collaborator
•
Draft
OpenVINO BK fallback to Llama.CPP CPU BK
#27
opened Dec 5, 2025 by
zhaixuejun1993
Collaborator
Loading…
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.