Skip to content

cmake : add install() for impl libraries#23511

Merged
ggerganov merged 6 commits into
masterfrom
gg/cmake-fix-builds
May 22, 2026
Merged

cmake : add install() for impl libraries#23511
ggerganov merged 6 commits into
masterfrom
gg/cmake-fix-builds

Conversation

@ggerganov
Copy link
Copy Markdown
Member

@ggerganov ggerganov commented May 22, 2026 •
edited
Loading

Overview

cont #23462

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f (#23462). Without this, cmake --install fails to copy
the shared libraries, causing runtime errors like:

llama-server: error while loading shared libraries: libllama-server-impl.so: cannot open shared object file

Fixes #23494

Additional information

Addresses #23494 (comment)

Requirements

  • I have read and agree with the contributing guidelines
  • AI usage disclosure: YES. llama.cpp + pi + Qwen3.6-27B-MTP:Q8_0

ggerganov added 5 commits May 22, 2026 10:12
@ggerganov
pi : update
43ded77
@ggerganov
ci : fix ios build
ef1355a
@ggerganov
ci : fix andoroid
b487fe0
@ggerganov
ci : fix apple builds
1e69258
@ggerganov
cmake : add install() for impl libraries
f7ad7d8 
Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: #23494 (comment)

Assisted-by: llama.cpp:local pi
@ggerganov
Copy link
Copy Markdown
Member Author

ggerganov commented May 22, 2026

Running the CI here: https://github.com/ggerganov/tmp2/actions

@CISC
Copy link
Copy Markdown
Member

CISC commented May 22, 2026

build-info.h problem still present:
https://github.com/ggml-org/llama.cpp/actions/runs/26274420858/job/77335160714?pr=23511

@ggerganov
Copy link
Copy Markdown
Member Author

ggerganov commented May 22, 2026

YOLO merge?

danbev
danbev approved these changes May 22, 2026
View reviewed changes
Copy link
Copy Markdown
Member

@danbev danbev left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Verified locally.

@ggerganov ggerganov marked this pull request as ready for review May 22, 2026 08:45
@ggerganov ggerganov requested review from a team and ngxson as code owners May 22, 2026 08:45
@ggerganov ggerganov merged commit bbce619 into master May 22, 2026
7 of 46 checks passed
@ggerganov ggerganov deleted the gg/cmake-fix-builds branch May 22, 2026 08:46
@CISC
Copy link
Copy Markdown
Member

CISC commented May 22, 2026

LGTM https://github.com/ggerganov/tmp2/actions/runs/26277028330/job/77343681637

@Green-Sky
Copy link
Copy Markdown
Collaborator

Green-Sky commented May 22, 2026

Was about to complain 😄

@CISC CISC linked an issue May 22, 2026 that may be closed by this pull request
builddir/_deps/llama-src/app/llama.cpp:1:10: fatal error: build-info.h: No such file or directory #23497
Closed
@github-actions github-actions Bot added android Issues specific to Android examples devops improvements to build systems and github actions server labels May 22, 2026
@CISC CISC removed a link to an issue May 22, 2026
builddir/_deps/llama-src/app/llama.cpp:1:10: fatal error: build-info.h: No such file or directory #23497
Closed
@CISC CISC linked an issue May 22, 2026 that may be closed by this pull request
Misc. bug: server-cuda-b9282 image: /app/llama-server: error while loading shared libraries: libllama-common.so.0: cannot open shared object file: No such file or directory #23517
Closed
Alex7MV pushed a commit to Alex7MV/claude_llama.cpp that referenced this pull request May 22, 2026
@ggerganov @Alex7MV
cmake : add install() for impl libraries + fix apple builds (ggml-org…
9ba988e 
…#23511)

* pi : update

* ci : fix ios build

* ci : fix andoroid

* ci : fix apple builds

* cmake : add install() for impl libraries

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: ggml-org#23494 (comment)

Assisted-by: llama.cpp:local pi

* ci : fix xcframework build
ProTekk pushed a commit to ProTekk/buun-llama-cpp that referenced this pull request May 22, 2026
@ggerganov @ProTekk
cmake : add install() for impl libraries + fix apple builds (ggml-org…
8d7ed22 
…#23511)

* pi : update

* ci : fix ios build

* ci : fix andoroid

* ci : fix apple builds

* cmake : add install() for impl libraries

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: ggml-org#23494 (comment)

Assisted-by: llama.cpp:local pi

* ci : fix xcframework build
@THEman6989 THEman6989 mentioned this pull request May 22, 2026
Merged
gabe-l-hart added a commit to gabe-l-hart/llama.cpp that referenced this pull request May 22, 2026
@gabe-l-hart
Merge remote-tracking branch 'origin/master' into Granite4Vision
75452c3 
* origin/master:
server: only parse empty msg if continuing an assistant msg (ggml-org#23506)
perplexity : fix integer overflow (ggml-org#23496)
SYCL: improve MoE prefill throughput (ggml-org#23142)
sycl : Level Zero detection in ggml_sycl_init (ggml-org#23097)
SYCL : gated_delta_net K>1 (ggml-org#23174)
SYCL: add BF16 to DMMV kernel path (~4x tg speedup on Intel Arc) (ggml-org#21580)
docs: Update documentation with Granite 4.0/4.1 (ggml-org#23404)
ggml-zendnn : add Q8_0 quantization support (ggml-org#23414)
cmake : build router app only during standalone builds (ggml-org#23521)
vocab : fix HybridDNA tokenizer (ggml-org#23466)
cmake : add install() for impl libraries + fix apple builds (ggml-org#23511)
CUDA: fix PDL CC check for JIT compilation (ggml-org#23471)
cmake : remove STATIC from impl libraries, enable LLAMA_BUILD_APP by default (ggml-org#23462)
Update WebGPU support and add link to blog/demo (ggml-org#23483)
vulkan: fuse snake activation (mul, sin, sqr, mul, add) (ggml-org#22855)
@sasa7812
Copy link
Copy Markdown

sasa7812 commented May 22, 2026

Let's delete the broken images, people keep downloading them and keep opening duplicate bugs about missing libraries. Ideally, triggering image rebuild would be great

baramofme pushed a commit to baramofme/llama-cpp-turboquant that referenced this pull request May 23, 2026
@ggerganov @baramofme
cmake : add install() for impl libraries + fix apple builds (ggml-org…
3a30540 
…#23511)

* pi : update

* ci : fix ios build

* ci : fix andoroid

* ci : fix apple builds

* cmake : add install() for impl libraries

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: ggml-org#23494 (comment)

Assisted-by: llama.cpp:local pi

* ci : fix xcframework build
srossitto79 pushed a commit to srossitto79/llama.cpp that referenced this pull request May 23, 2026
@ggerganov @srossitto79
cmake : add install() for impl libraries + fix apple builds (ggml-org…
8829518 
…#23511)

* pi : update

* ci : fix ios build

* ci : fix andoroid

* ci : fix apple builds

* cmake : add install() for impl libraries

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: ggml-org#23494 (comment)

Assisted-by: llama.cpp:local pi

* ci : fix xcframework build
testeddoughnut pushed a commit to testeddoughnut/llama.cpp that referenced this pull request May 25, 2026
@ggerganov @testeddoughnut
cmake : add install() for impl libraries + fix apple builds (ggml-org…
05b6ac5 
…#23511)

* pi : update

* ci : fix ios build

* ci : fix andoroid

* ci : fix apple builds

* cmake : add install() for impl libraries

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: ggml-org#23494 (comment)

Assisted-by: llama.cpp:local pi

* ci : fix xcframework build
Alex7MV pushed a commit to Alex7MV/claude_llama.cpp that referenced this pull request May 27, 2026
@ggerganov @Alex7MV
cmake : add install() for impl libraries + fix apple builds (ggml-org…
c3b84e1 
…#23511)

* pi : update

* ci : fix ios build

* ci : fix andoroid

* ci : fix apple builds

* cmake : add install() for impl libraries

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: ggml-org#23494 (comment)

Assisted-by: llama.cpp:local pi

* ci : fix xcframework build
fewtarius pushed a commit to fewtarius/llama.cpp that referenced this pull request May 30, 2026
@ggerganov
cmake : add install() for impl libraries + fix apple builds (ggml-org…
f891496 
…#23511)

* pi : update

* ci : fix ios build

* ci : fix andoroid

* ci : fix apple builds

* cmake : add install() for impl libraries

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit 276a721. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: ggml-org#23494 (comment)

Assisted-by: llama.cpp:local pi

* ci : fix xcframework build
turbo-tan pushed a commit to turbo-tan/llama.cpp-tq3 that referenced this pull request Jun 2, 2026
@ggerganov @charpdev
cmake : add install() for impl libraries + fix apple builds (ggml-org…
cf0243e 
…#23511)

* pi : update

* ci : fix ios build

* ci : fix andoroid

* ci : fix apple builds

* cmake : add install() for impl libraries

Add install(TARGETS <target> LIBRARY) for all -impl libraries that were
changed from STATIC to shared (controlled by BUILD_SHARED_LIBS) in
commit bb28c1f. Without this, cmake --install fails to copy the shared
libraries, causing runtime errors like:

  llama-server: error while loading shared libraries: libllama-server-impl.so

Ref: ggml-org#23494 (comment)

Assisted-by: llama.cpp:local pi

* ci : fix xcframework build
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@danbev danbev danbev approved these changes

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

Assignees

No one assigned

Labels

android Issues specific to Android devops improvements to build systems and github actions examples server

Projects

None yet

Milestone

No milestone

5 participants

@ggerganov @CISC @Green-Sky @sasa7812 @danbev