llama.cpp
OpenVINO: Update OV to 2026.3.1, whisper.cpp support, Qwen3.5 on NPU, and new ops
#27843
Merged
Merged
OpenVINO: Update OV to 2026.3.1, whisper.cpp support, Qwen3.5 on NPU, and new ops #27843
ggerganov
merged
21 commits into
ggml-org:master
from
ravi9:pr-2026-08-27
OpenVINO Backend: Fuse IM2COL + MatMul convolution into OpenVINO conv…
ad1dda27
ci:ggml-ov: Skip recurrent state rollback tests
f5f746a1
ci:ggml-ov: Skip recurrent state rollback tests
3a0eb607
Update OPENVINO.md
7f0030b2
ggml-openvino : add env-var gated op support debugging
9c93a24b
Fix ggml_rope_set_offset case
64586f72
OpenVINO backend: Support Whisper.cpp
684b6077
Fix code style
5c94b944
openvino : enable qwen35 on NPU
eaa99815
Update to OpenVINO 2026.3.1
fdefe96d
ggml-openvino: forward NPU compilation mode parameters
28993524
ggml-openvino : support RELU, POOL_2D, QUICK_GEGLU, and ROLL ops
da7d97a3
reorder op table
50137937
exclude GPU/NPU failing POOL_2D case
2adeb1a2
move op type detection to compute_op_case
fdcca71b
Relax rope supported cases
81020ca3
Fix pool case
a1e39670
Update openvino doc, gpu driver in ov docker
66b851b4
openvino: remove unused static remote context branch
feafb091
openvino: parallelize static model build
40d3fdd5
Apply editorconfig
40d8bde2
taronaeo
approved these changes
on 2026-08-28
CISC
approved these changes
on 2026-08-28
Login to write a write a comment.
Login via GitHub