Skip to content

Update build.md#37

Open
I-N-T-E-L wants to merge 241 commits intoravi9:dev_backend_openvinofrom
I-N-T-E-L:patch-1
Open

Update build.md#37
I-N-T-E-L wants to merge 241 commits intoravi9:dev_backend_openvinofrom
I-N-T-E-L:patch-1

Conversation

@I-N-T-E-L
Copy link

@I-N-T-E-L I-N-T-E-L commented Jan 24, 2026

Generalizing OV folder path

YangleiZouIntel and others added 30 commits January 15, 2026 10:05
@YangleiZouIntel @cavusmustafa
Add ggml-openvino base files
fe5720e
@zhanmyz @cavusmustafa
add openvino as optional backend for Llama.cpp ggml
5294402
@zhanmyz @cavusmustafa
* Configure the device(default CPU) that uses OpenVINO to compile th…
9b9d51d 
…e model

 * Add OpenVINO ADD operator to Llama.cpp. The output is somewhat abnormal and needs further debugging.
@zhanmyz @cavusmustafa
Solve the issue of abnormal model output caused by using OpenVINO ADD…
faa4a7d 
… operator
@zhanmyz @cavusmustafa
Add OpenVINO MUL operator to GGML of Llama.cpp.
adc2c70
@zhanmyz @cavusmustafa
Add compile options
0a81aa1
@zhanmyz @cavusmustafa
add OpenVINO frontend convert process steps
77d6814
@zhanmyz @cavusmustafa
add get openvino available ops function
ee31dc1
@yumengbo @cavusmustafa
Add PoC of integration of openvino frontend. Main changes: ggml-ov-fr…
171c468 
…ontend-utils, GraphIterator, Decoder
@yumengbo @cavusmustafa
Implement GgmlOvDecoder. Add dump functions.
34e826a
@yumengbo @cavusmustafa
Convert subgraph with add, sub, mul, div op to ov model and do infer …
9b7b63d 
…on openvino device
@yumengbo @cavusmustafa
Add GGML_OV_FRONTEND option. Add readme.
31bd816
@yumengbo @cavusmustafa
Change output for infer request to set output tensor. Support scale, …
5b46dc2 
…view op.
@zhanmyz @cavusmustafa
add GET_ROWS operator of OpenVINO to GGML of llama.cpp
49804f4
@zhanmyz @cavusmustafa
Update build.md and add operation mapping(GGML to OpenVINO)
80c330a
@zhanmyz @cavusmustafa
add the rms_norm operator implemented using OpenVINO to the GGML back…
8c5a609 
…end of llama.cpp
@yumengbo @cavusmustafa
Fix issue for output memory copy of infer request
e95f29c
@yumengbo @cavusmustafa
Change to implementation following pytorch frontend
b100f89
@yumengbo @cavusmustafa
Add support for UNARY SILU op . Fix pytorch impl bugs.
590f587
@yumengbo @cavusmustafa
Support Softmax op
d218c61
@yumengbo @cavusmustafa
Support Softmax op
8aba03b
@yumengbo @cavusmustafa
Support ROPE op.
2353c73
@zhanmyz @cavusmustafa
Add support for RMS_NORM OP
0f7d07d
@zhanmyz @cavusmustafa
Add MUL_MAT,CPY,CONT as operators implemented in OpenVINO for GGML ba…
2b04bd4 
…ckend
@zhanmyz @cavusmustafa
Move CPY from GGML OV Backend to OV Frontend
cb2729b
@zhanmyz @cavusmustafa
add implementation of MUL_MAT, CPY, CONT of GGML ops using OV ops
8484769
@zhanmyz @cavusmustafa
add implementation of CPY when the output tensor is non-contiguous
57582fd
@zhanmyz @cavusmustafa
add tmp source code files
afb8594
@zhanmyz @cavusmustafa
Execute singel CONT operator is OK
081b526
@zhanmyz @cavusmustafa
Execute CONT & VIEW operators in OV Frontend is OK
901f734
wine99 and others added 24 commits January 15, 2026 11:39
@wine99 @cavusmustafa
Support -ctk f32
0d6f253
@cavusmustafa
Initial stateful graph support
5f30eac
@cavusmustafa @ynimmaga
Update ggml/src/ggml-openvino/ggml-decoder.cpp
d2fc152 
Co-authored-by: Yamini Nimmagadda <yamini.nimmagadda@intel.com>
@cavusmustafa
code cleanup
981ec65
@cavusmustafa
npu perf fix
a40a5df
@cavusmustafa
requant to f16 for Q6 embed on NPU
a81b202
@cavusmustafa
Update ggml/src/ggml-openvino/ggml-decoder.cpp
a92ecee
@cavusmustafa
Update ggml/src/ggml-openvino/ggml-openvino-extra.cpp
599335c
@ynimmaga @cavusmustafa
Create OPENVINO.md in llama.cpp backend docs
416556a
@ynimmaga @cavusmustafa
Update OPENVINO.md
25e6525
@ynimmaga @cavusmustafa
Update OPENVINO.md
9ba3247
@ynimmaga @cavusmustafa
Update OPENVINO.md
61552e4
@ynimmaga @cavusmustafa
Update build.md
63eed0d
@ynimmaga @cavusmustafa
Update OPENVINO.md
f44c60e
@ynimmaga @cavusmustafa
Update OPENVINO.md
e9ed5c4
@ynimmaga @cavusmustafa
Update OPENVINO.md
d3649c1
@cavusmustafa
kq_mask naming fix
d7dccf8
@cavusmustafa
Syntax correction for workflows build file
aa4bc90
@wine99
Change ov backend buffer is_host to false
9a15c8b
@cavusmustafa
Merge pull request ravi9#34 from ravi9/fix-backend-buffer-is-host
be2d4b6 
Change ov backend buffer is_host to false
@wine99
Fix llama-bench -p -n where p<=256
e0c377f
@wine99
Fix --direct-io 0
ff9bb1a
@wine99
Don't put kvcache on GPU in stateful mode
cd067dc
@I-N-T-E-L
Update build.md
fc282f4 
Generalizing OV folder path
@github-actions github-actions bot added the documentation Improvements or additions to documentation label Jan 24, 2026
@wine99 wine99 force-pushed the dev_backend_openvino branch from 6d71ded to 900dd76 Compare February 11, 2026 02:16
@ggerganov ggerganov force-pushed the dev_backend_openvino branch from 76e4057 to e73b4d4 Compare March 13, 2026 10:44
@wine99 wine99 force-pushed the dev_backend_openvino branch from 996b739 to b6c83aa Compare March 17, 2026 02:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@cavusmustafa cavusmustafa Awaiting requested review from cavusmustafa cavusmustafa is a code owner

@wine99 wine99 Awaiting requested review from wine99 wine99 is a code owner

Assignees

No one assigned

Labels

documentation Improvements or additions to documentation

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

10 participants

@I-N-T-E-L @YangleiZouIntel @zhanmyz @yumengbo @wine99 @virajwad @ravi9 @cavusmustafa @zhaixuejun1993 @ynimmaga