Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
128 commits
Select commit Hold shift + click to select a range
9c0ac88
ui: Prioritize favorite models in model selection (#24766)
mahdiou Jun 22, 2026
dec5ca5
server : Add id to tool call responses api (#24882)
boondocklabs Jun 22, 2026
23ee879
opencl: q8_0 gemv precision improvement (#24923)
shawngu-quic Jun 23, 2026
73618f2
server: improve user message detection and create checkpoints at ever…
aldehir Jun 23, 2026
035cd8f
codeowners: add yomaytk to ggml-webgpu (#24930)
yomaytk Jun 23, 2026
7c90850
ggml-webgpu: improve MTP inference by using mat-vec path for small ba…
yomaytk Jun 23, 2026
a3900a6
model: Granite Speech Plus (#24818)
gabe-l-hart Jun 23, 2026
c926ad0
vulkan: link ggml-cpu when GGML_VULKAN_CHECK_RESULTS / RUN_TESTS are …
Detensable Jun 23, 2026
75ad0b2
server: fix remote preset handling, add test (#24938)
ngxson Jun 23, 2026
0eb874d
vulkan: make mul_mm ALIGNED a spec constant (#24689)
jeffbolznv Jun 23, 2026
c560636
vulkan: support CONV_3D (#24612)
jeffbolznv Jun 23, 2026
92e854a
vulkan: Support GET_ROWS_BACK (#24883)
jeffbolznv Jun 23, 2026
72a9269
vulkan: support all backend tests for SQR/SQRT/SIN/COS/CLAMP/LEAKY_RE…
jeffbolznv Jun 23, 2026
be4a6a6
server : check draft context creation error (#24922)
Kononnable Jun 23, 2026
ac4105d
vulkan: Apply bias before softmax in FA, to avoid overflow (#24909)
jeffbolznv Jun 24, 2026
88636e1
model : Add LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M (#24913)
tdakhran Jun 24, 2026
ef9c13d
ui: New Logo + Navigation cleanup & Mobile UI/UX improvements (#24897)
allozaur Jun 24, 2026
00139b6
ui: loading bar below the model picker (#24931)
ServeurpersoCom Jun 24, 2026
1191758
vulkan: fail the build when a shader fails to compile (#24450)
liminfei-amd Jun 24, 2026
51eae8c
vulkan: allow reducing the graph submission batches to avoid timeouts…
wbruna Jun 24, 2026
fb40104
common: remove unused json-partial (#24968)
ngxson Jun 24, 2026
894bb27
mtmd: model: unlimited-ocr: converter + parity test (#24969)
sfallah Jun 24, 2026
8be759e
hexagon: MUL_MAT and MUL_MAT_ID rework : 32x32 tiled weight repack, k…
max-krasnyansky Jun 24, 2026
09cedfd
chat: harden caps check (#24973)
pwilkin Jun 25, 2026
fdb2c11
opencl: support non-contig rows in norm (#24965)
lhez Jun 25, 2026
9c10954
sycl : fix the failed UT cases of conv_3d (#24900)
arthw Jun 25, 2026
e9fb3b3
sycl : support --split-mode tensor (#24152)
Spruill-1 Jun 25, 2026
b3ce5ce
quant : fix quantizing moe with mtp (#24986)
CISC Jun 25, 2026
e12a012
build: include libmtmd in Apple XCFramework (#21935)
theabecaster Jun 25, 2026
fdbd6ab
tests : synchronize contexts at end of test-thread-safety (#24935)
krystophny Jun 25, 2026
3e61ea0
ui: fix always-show-sidebar-on-desktop setting after navigation refac…
ServeurpersoCom Jun 25, 2026
f728ada
ggml : address integer overflows in binary ops CUDA implementation (#…
fairydreaming Jun 25, 2026
683b04c
app : add the llama download subcommand (#24982)
angt Jun 25, 2026
e8ecce5
docs : Eagle3 qwen3 draft model support (#24977)
kashif Jun 25, 2026
60bc886
common: refactor model handling (#24980)
ngxson Jun 25, 2026
099bf06
misc: update lables (#24920)
ngxson Jun 25, 2026
e9d1b76
server: use status code 403 for disabled features (#24970)
ngxson Jun 25, 2026
c7cddef
misc: fix labeler (#25012)
ngxson Jun 25, 2026
1ec44d1
CUDA: Various fixes to `cpy.cu` (#25000)
ORippler Jun 25, 2026
9d5d882
model : Add label for LFM2.5-230M (#25008)
tdakhran Jun 25, 2026
beac530
xcframework : disable mtmd video on i/tv/visionos (#25018)
CISC Jun 25, 2026
5c7c22c
opencl: flush profiling batch at shutdown for incomplete batches (#25…
shaofeiqi Jun 26, 2026
960d628
mamba2: remove hardcoded 2x expansion factor and invalid d_inner % d_…
limloop Jun 26, 2026
f818065
CUDA: batch out_prod broadcast (dps2>1) path with cublasSgemmBatched …
leonardHONG Jun 26, 2026
b11f7c1
mtmd: add more validations (#25013)
ngxson Jun 26, 2026
e7e3f35
sycl : clamp softmax input to avoid underflow (#24941)
Jassieluo Jun 26, 2026
1a87dcd
server + ui: SSE Replay Buffer (#23226)
ServeurpersoCom Jun 26, 2026
c16c35b
ggml-cpu: fix SVE leftover path in ggml_vec_dot_f32 (#24699)
tdakhran Jun 26, 2026
2f18fe1
CUDA: add cublasSgemmBatched mapping for HIP/MUSA vendor headers (#25…
leonardHONG Jun 26, 2026
9df0680
vulkan: Workaround compiler bug in conv2d coopmat2 path (#24924)
jeffbolznv Jun 26, 2026
ded1561
ui: fix accessibility for hover-gated interactive elements assisted b…
sanjayahari Jun 26, 2026
5a6a0dd
vulkan: add INTEL_XE1 arch enum and enable coopmat1 on Intel Xe-LPG P…
fish-jiang Jun 26, 2026
487a6cc
vulkan: opt mul_mat_vecq for mi50 (#22933)
chraac Jun 26, 2026
96183e9
ggml : bump version to 0.15.3 (ggml/1550)
ggerganov Jun 26, 2026
e7ea94a
sync : ggml
ggerganov Jun 26, 2026
5397c36
openvino: Update to OV 2026.2.1, self-contained release packages, ope…
ravi9 Jun 26, 2026
024930c
arg: fix handling --spec-draft-hf and --hf-repo-v (#25043)
ngxson Jun 26, 2026
5d8ccdf
devops : add llama in all docker images (#25035)
angt Jun 26, 2026
3fc4e10
sched : reintroduce less synchronizations during split compute (#20793)
aendk Jun 26, 2026
050ee92
app : allow --version, --licenses & --help (#25054)
angt Jun 26, 2026
83d385b
tests : fix test-chat-template --no-common option (#25075)
CISC Jun 27, 2026
0275c0f
ci : add windows-openvino to check-release (#25022)
CISC Jun 27, 2026
c299a92
binaries : Improve rpc-server and export-graph-ops names. (#25045)
ckastner Jun 27, 2026
0b6529d
vulkan: fix step operator for 0 input (#25036)
0cc4m Jun 27, 2026
9bebfcb
sycl : fix failed ut cases of norm (#25044)
arthw Jun 27, 2026
0ed235e
[CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy (#25057)
gaugarg-nv Jun 27, 2026
ebd048f
opencl: flash attention improvement (#25069)
wanghqc Jun 27, 2026
27c8bb4
logs : reduce v2 (#25078)
ggerganov Jun 28, 2026
c1a1c8e
common : allow --offline in llama download (#25091)
angt Jun 28, 2026
d1b3425
spec : add DFlash support (#22105)
ruixiang63 Jun 28, 2026
f68a788
jinja: add --dump-prog for debugging (#25086)
ngxson Jun 28, 2026
c818263
chat : implement minicpm5 parser (#24889)
aldehir Jun 28, 2026
fa72bc6
dflash: refactor draft model conversion (#25110)
ruixiang63 Jun 28, 2026
7cb8576
ui: fix stop and reasoning skip in single-model mode (#25084)
ServeurpersoCom Jun 28, 2026
dbdaece
Revert "ui: fix accessibility for hover-gated interactive elements as…
allozaur Jun 28, 2026
b3fed31
jinja, chat: add --reasoning-preserve flag (#25105)
ngxson Jun 28, 2026
277a105
common : remove unused regex-partial (#25118)
o7si Jun 29, 2026
6cb18b2
tools/ui: restore Tailwind scanning in ignored worktrees (#24879)
seryogakovalyov Jun 29, 2026
8c146a8
DeepSeek V4 (#24162)
am17an Jun 29, 2026
25a1d63
vulkan: use flops instead of weight tensor size for submission heuris…
0cc4m Jun 29, 2026
6f4f53f
common : dedup preset and cached model entries in /v1/models (#25131)
angt Jun 29, 2026
86b9470
Revert "sched : reintroduce less synchronizations during split comput…
ORippler Jun 30, 2026
6c5de1c
ggml-webgpu: add support for NVFP4 (#25143)
yomaytk Jun 30, 2026
d9df110
HIP: use hipBLAS for dense prefill on gfx900, keep MMQ for MoE (#24588)
DEV-DUFORD Jun 30, 2026
f708a5b
vulkan: roll bk loop in matmul for asahi linux (#24663)
xingjianll Jun 30, 2026
e495d1e
CUDA: fix Gemma E4B MTP FlashAttention (#25148)
JohannesGaessler Jun 30, 2026
931eb37
CUDA: fix get_rows_back for tables with more than 65535 rows (grid-y …
mattjallo Jun 30, 2026
799fcc0
common,server: handle bracketed IPv6 literals in URL authority (#25140)
ServeurpersoCom Jun 30, 2026
4f31eed
model : register t_layer_inp for qwen3next (#25141)
jschmied Jun 30, 2026
0eca4d4
cuda : prevent integer truncation and overflow errors when using KQ m…
fairydreaming Jun 30, 2026
fd1a057
opencl: initial q1_0 support (#25160)
lhez Jul 1, 2026
7af4279
ui: Remove PWA navigate fallback to prevent caching API endpoint requ…
allozaur Jul 1, 2026
9d88e7c
ui Prevent tool messages from incorrectly appending to other conversa…
allozaur Jul 1, 2026
6dbc117
ggml-cpu: add AVX2 optimization for nvfp4 dot product and use UE4M3 L…
ragz4125 Jul 1, 2026
b820cc8
CUDA: consistent use of __restrict__ + PDL for FA (#25185)
JohannesGaessler Jul 1, 2026
13e6738
hexagon: flash attention rework (optimizations, accuracy improvements…
max-krasnyansky Jul 1, 2026
a6647b1
common : use hf primary split as model path (#25194)
angt Jul 1, 2026
4fc4ec5
opencl: allow loading precompiled binary kernels from library (#23042)
lhez Jul 1, 2026
fdb1db8
llama : add llama_model_ftype_name() (#25134)
angt Jul 2, 2026
c8ae9a7
vendor : update cpp-httplib to 0.49.0 (#25218)
cabelo Jul 3, 2026
5a460de
Remove redundant CUDA copies after gated_delta_net. (#23940)
gaugarg-nv Jul 3, 2026
9487528
ui: Add MCP Servers Opt-In for first time visitors (#25239)
allozaur Jul 3, 2026
b5315e1
server + ui: ping silent SSE streams every 1s and kick only after 3s …
ServeurpersoCom Jul 3, 2026
067de93
ui: align persisted config with strict server schema and enable think…
ServeurpersoCom Jul 3, 2026
75a48a9
cuda: enable topk-moe fusion for 288 experts (#25267)
pwilkin Jul 3, 2026
152d337
spec: support spec-draft-p-min in DFlash (#25246)
ruixiang63 Jul 3, 2026
f113e02
ui: strip path and weight extension from model id in single model mod…
ServeurpersoCom Jul 3, 2026
d4cff11
ui: Improve performance when streaming (#25225)
ntowle Jul 3, 2026
2d97363
chat: trim messages sent to StepFun parser (fixes long reasoning loop…
pwilkin Jul 3, 2026
ef2d770
ggml : fix broken CPU concat implementation for quantized types (#25247)
fairydreaming Jul 4, 2026
6658925
ui: add sync blocks so display/behavior settings can be set via --ui-…
ServeurpersoCom Jul 4, 2026
a410713
llama : add guard for K/V rotation input when buffer is unallocated (…
liminfei-amd Jul 4, 2026
78d2f52
cuda : concat implementation for quantized types (#25303)
fairydreaming Jul 5, 2026
7a63fde
ggml: Update VMM Pool allocation ggml-cuda.cu - Turing P2P access fix…
VexxieCode Jul 5, 2026
4b2a0cd
ggml : fix tensor-parallel + -ncmoe crash on MoE models (#25028)
liminfei-amd Jul 5, 2026
3e5036f
abort if we see a multi buffer (#25276)
netrunnereve Jul 5, 2026
2da6686
Fix stale tensor-split params for draft models (#24814)
RedToasty Jul 5, 2026
72874f5
ggml-cuda: optimize conv_transpose_1d indexing (#25310)
adavyas Jul 6, 2026
898b088
ui: fake 200 for proxy DELETE req (#25298)
ngxson Jul 6, 2026
d06ddd3
ggml-hip: enable -ffast-math for HIP builds (#23862)
a-huk Jul 6, 2026
4871961
scripts : use HF_TOKEN when downloading UI assets (#25280)
angt Jul 6, 2026
d80e878
ui: restore Ctrl+B sidebar toggle shortcut (#25307)
ServeurpersoCom Jul 6, 2026
86961ef
vulkan: fix 32-bit integer overflow in CEIL_DIV (#25245)
hokanosekai Jul 6, 2026
3b4fca1
ggml-cpu: Enable tiled matmul on AIX (#25199)
shalinib-ibm Jul 6, 2026
20a04b2
ggml-cpu: use UE4M3 LUT in ARM NVFP4 dot product (#25331)
ragz4125 Jul 6, 2026
bfdf581
server: temporary skip model downloading API test (#25355)
ngxson Jul 6, 2026
cb295bf
CUDA: extend K-type validation to V-types for flash attention (#24403)
sanmai Jul 6, 2026
9abce74
server: fix deadlock in load_models() when erasing a finished downloa…
ServeurpersoCom Jul 6, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
4 changes: 2 additions & 2 deletions .devops/cann.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -145,7 +145,7 @@ ENTRYPOINT ["/app/tools.sh"]
# ==============================================================================
FROM base AS light

COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

ENTRYPOINT [ "/app/llama-cli" ]

Expand All @@ -156,7 +156,7 @@ FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama-server /app
COPY --from=build /app/full/llama /app/full/llama-server /app

HEALTHCHECK --interval=5m CMD [ "curl", "-f", "http://localhost:8080/health" ]

Expand Down
4 changes: 2 additions & 2 deletions .devops/cpu.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light

COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

WORKDIR /app

Expand All @@ -115,7 +115,7 @@ FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama-server /app
COPY --from=build /app/full/llama /app/full/llama-server /app

WORKDIR /app

Expand Down
4 changes: 2 additions & 2 deletions .devops/cuda.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light

COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

WORKDIR /app

Expand All @@ -124,7 +124,7 @@ FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama-server /app
COPY --from=build /app/full/llama /app/full/llama-server /app

WORKDIR /app

Expand Down
4 changes: 2 additions & 2 deletions .devops/intel.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -141,7 +141,7 @@ ENTRYPOINT ["/app/tools.sh"]
FROM base AS light

COPY --from=build /app/lib/ /app
COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

WORKDIR /app

Expand All @@ -153,7 +153,7 @@ FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/lib/ /app
COPY --from=build /app/full/llama-server /app
COPY --from=build /app/full/llama /app/full/llama-server /app

WORKDIR /app

Expand Down
4 changes: 2 additions & 2 deletions .devops/musa.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light

COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

WORKDIR /app

Expand All @@ -126,7 +126,7 @@ FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama-server /app
COPY --from=build /app/full/llama /app/full/llama-server /app

WORKDIR /app

Expand Down
16 changes: 8 additions & 8 deletions .devops/openvino.Dockerfile
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
ARG OPENVINO_VERSION_MAJOR=2026.2
ARG OPENVINO_VERSION_FULL=2026.2.0.21903.52ddc073857
ARG OPENVINO_VERSION_MAJOR=2026.2.1
ARG OPENVINO_VERSION_FULL=2026.2.1.21919.ede283a88e3
ARG UBUNTU_VERSION=24.04

# Intel GPU driver versions. https://github.com/intel/compute-runtime/releases
ARG IGC_VERSION=v2.34.4
ARG IGC_VERSION_FULL=2_2.34.4+21428
ARG COMPUTE_RUNTIME_VERSION=26.18.38308.1
ARG COMPUTE_RUNTIME_VERSION_FULL=26.18.38308.1-0
ARG IGC_VERSION=v2.36.3
ARG IGC_VERSION_FULL=2_2.36.3+21719
ARG COMPUTE_RUNTIME_VERSION=26.22.38646.4
ARG COMPUTE_RUNTIME_VERSION_FULL=26.22.38646.4-0
ARG IGDGMM_VERSION=22.10.0

# Intel NPU driver versions. https://github.com/intel/linux-npu-driver/releases
Expand Down Expand Up @@ -214,7 +214,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light

COPY --from=build /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/

WORKDIR /app

Expand All @@ -225,7 +225,7 @@ FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app/

WORKDIR /app

Expand Down
4 changes: 2 additions & 2 deletions .devops/rocm.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light

COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

WORKDIR /app

Expand All @@ -138,7 +138,7 @@ FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama-server /app
COPY --from=build /app/full/llama /app/full/llama-server /app

WORKDIR /app

Expand Down
4 changes: 2 additions & 2 deletions .devops/s390x.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -124,7 +124,7 @@ WORKDIR /llama.cpp/bin

# Copy llama.cpp binaries and libraries
COPY --from=collector /llama.cpp/bin/*.so /llama.cpp/bin
COPY --from=collector /llama.cpp/bin/llama-cli /llama.cpp/bin/llama-completion /llama.cpp/bin
COPY --from=collector /llama.cpp/bin/llama /llama.cpp/bin/llama-cli /llama.cpp/bin/llama-completion /llama.cpp/bin

ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ]

Expand All @@ -138,7 +138,7 @@ WORKDIR /llama.cpp/bin

# Copy llama.cpp binaries and libraries
COPY --from=collector /llama.cpp/bin/*.so /llama.cpp/bin
COPY --from=collector /llama.cpp/bin/llama-server /llama.cpp/bin
COPY --from=collector /llama.cpp/bin/llama /llama.cpp/bin/llama-server /llama.cpp/bin

EXPOSE 8080

Expand Down
4 changes: 2 additions & 2 deletions .devops/vulkan.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light

COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

WORKDIR /app

Expand All @@ -118,7 +118,7 @@ FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama-server /app
COPY --from=build /app/full/llama /app/full/llama-server /app

WORKDIR /app

Expand Down
4 changes: 2 additions & 2 deletions .devops/zendnn.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light

COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

WORKDIR /app

Expand All @@ -108,7 +108,7 @@ FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama-server /app
COPY --from=build /app/full/llama /app/full/llama-server /app

WORKDIR /app

Expand Down
45 changes: 26 additions & 19 deletions .github/labeler.yml
Original file line number Diff line number Diff line change
Expand Up @@ -35,8 +35,20 @@ AMD ZenDNN:
documentation:
- changed-files:
- any-glob-to-any-file:
- "**/*.md"
- docs/**
- media/**
examples:
- all:
- changed-files:
- any-glob-to-any-file:
- app/**
- examples/**
- tools/**
- all-globs-to-all-files:
- '!tools/server/**'
- '!tools/mtmd/**'
- '!tools/ui/**'
testing:
- changed-files:
- any-glob-to-any-file:
Expand All @@ -47,28 +59,12 @@ build:
- cmake/**
- CMakeLists.txt
- CMakePresets.json
examples:
- changed-files:
- any-glob-to-any-file:
- examples/**
- tools/**
devops:
- changed-files:
- any-glob-to-any-file:
- .devops/**
- .github/**
- ci/**
python:
- changed-files:
- any-glob-to-any-file:
- "**/*.py"
- requirements/**
- gguf-py/**
- .flake8
script:
- changed-files:
- any-glob-to-any-file:
- scripts/**
android:
- changed-files:
- any-glob-to-any-file:
Expand All @@ -81,9 +77,20 @@ server:
- changed-files:
- any-glob-to-any-file:
- tools/server/**



mtmd:
- changed-files:
- any-glob-to-any-file:
- tools/mtmd/**
conversion:
- changed-files:
- any-glob-to-any-file:
- conversion/**
- convert_*.py
- gguf-py/**
vendor:
- changed-files:
- any-glob-to-any-file:
- vendor/**
ggml:
- changed-files:
- any-glob-to-any-file:
Expand Down
8 changes: 4 additions & 4 deletions .github/workflows/build-cache.yml
Original file line number Diff line number Diff line change
Expand Up @@ -68,8 +68,8 @@ jobs:

env:
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2"
OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"

steps:
- name: Clone
Expand All @@ -96,8 +96,8 @@ jobs:

env:
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2"
OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"

steps:
- name: Clone
Expand Down
8 changes: 4 additions & 4 deletions .github/workflows/build-openvino.yml
Original file line number Diff line number Diff line change
Expand Up @@ -39,8 +39,8 @@ jobs:

env:
# Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2"
OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"

steps:
- name: Clone
Expand Down Expand Up @@ -96,8 +96,8 @@ jobs:

env:
# Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2"
OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"

steps:
- name: Clone
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/build-self-hosted.yml
Original file line number Diff line number Diff line change
Expand Up @@ -266,8 +266,8 @@ jobs:

env:
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2"
OPENVINO_VERSION_FULL: "2026.2.0.21903.52ddc073857"
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"

steps:
- name: Clone
Expand Down
Loading
Loading