Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
139 commits
Select commit Hold shift + click to select a range
65a3ebb
sycl: Batched mulmat rework for oneDNN dispatch (#14617)
ShanoToni Jul 14, 2025
0f4c6ec
SYCL: use 1D kernel for set_rows (#14618)
qnixsynapse Jul 14, 2025
494c589
scripts: benchmark for HTTP server throughput (#14668)
JohannesGaessler Jul 14, 2025
9c9e4fc
llama-context: add ability to get logits (#14672)
am17an Jul 14, 2025
55c509d
ggml : refactor llamafile_sgemm PPC code (#14673)
shalinib-ibm Jul 14, 2025
bdca383
sycl: Hotfix for non dnnl codepath (#14677)
ShanoToni Jul 14, 2025
cbc68be
cuda: fix build warnings in set-rows.cu (unused variable) (#14687)
yeahdongcn Jul 15, 2025
68e37a6
model : add PLaMo-2 support (#14560)
mitmul Jul 15, 2025
10a0351
vulkan: add RTE variants for glu/add/sub/mul/div (#14653)
jeffbolznv Jul 15, 2025
ba1ceb3
vulkan: fix noncontig check for mat_mul_id splitting (#14683)
jeffbolznv Jul 15, 2025
4a4f426
model : add Kimi-K2 support (#14654)
gabriellarson Jul 15, 2025
c81f419
gguf-py : dump bpw per layer and model in markdown mode (#14703)
EAddario Jul 15, 2025
79e0b68
llama: add LLAMA_API to deprecated llama_kv_self_seq_div (#14708)
Min-Hua Jul 16, 2025
cf91f21
convert : add pre-computed hashes first to prevent order mishaps (#14…
CISC Jul 16, 2025
4b91d6f
convert : only check for tokenizer folder if we need it (#14704)
CISC Jul 16, 2025
5cae766
scripts: synthetic prompt mode for server-bench.py (#14695)
JohannesGaessler Jul 16, 2025
538cc77
server : fix handling of the ignore_eos flag (#14710)
ggerganov Jul 16, 2025
e4841d2
llama : fix parallel processing for plamo2 (#14716)
mitmul Jul 16, 2025
6ffd4e9
server : pre-calculate EOG logit biases (#14721)
ggerganov Jul 16, 2025
6497834
ggml : add asserts (#14720)
ggerganov Jul 16, 2025
ab14019
Support diffusion models: Add Dream 7B (#14644)
am17an Jul 16, 2025
225e7a1
llama : add high-throughput mode (#14363)
ggerganov Jul 16, 2025
b0f0ecc
model : support output bias for qwen2 (#14711)
tempstudio Jul 16, 2025
21c0217
ggml: Add initial WebGPU backend (#14521)
reeselevine Jul 16, 2025
496957e
llama : fix parameter order for hybrid memory initialization (#14725)
dinerburger Jul 16, 2025
19e5943
convert : make hf token optional (#14717)
CISC Jul 16, 2025
1ba45d4
ci : disable failing vulkan crossbuilds (#14723)
CISC Jul 16, 2025
ad57d3e
batch : fix uninitialized has_cpl flag (#14733)
ggerganov Jul 17, 2025
d9b6910
kv-cache : opt mask set input (#14600)
ggerganov Jul 17, 2025
086cf81
llama : fix parallel processing for lfm2 (#14705)
tdakhran Jul 17, 2025
01612b7
llama : reuse compute graphs (#14482)
ggerganov Jul 17, 2025
d6fb3f6
kv-cache : fix k-shift for multiple streams (#14742)
ggerganov Jul 17, 2025
cb887f1
model: add Ernie 4.5 MoE support (#14658)
pwilkin Jul 17, 2025
760b448
nix : use optionalAttrs for env mkDerivation attrset argument (#14726)
amozeo Jul 17, 2025
670e136
convert : fix Ernie4.5 MoE without shared experts (#14746)
pwilkin Jul 17, 2025
349ea79
use max work group size for device to replace the magic number (#14732)
NeoZhangJianyu Jul 18, 2025
09651d0
graph : Pass the graph placeholder message in debug mode (#14748)
Nexesenex Jul 18, 2025
8f974bc
graph : refactor context to not pass gf explicitly (#14629)
ggerganov Jul 18, 2025
f9a31ee
CUDA: set_rows + cpy.cu refactor (#14712)
am17an Jul 18, 2025
e0cb5c5
model : add EXAONE 4.0 support (#14630)
lgai-exaone Jul 18, 2025
eacdeb5
model : fix build after merge conflict (#14754)
ggerganov Jul 18, 2025
d498af3
graph : avoid huge warm-up graphs for MoE models (#14753)
ggerganov Jul 18, 2025
021cc28
cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (#14741)
ORippler Jul 18, 2025
2adf8d8
parallel : add option for different RNG seeds (#14757)
ggerganov Jul 18, 2025
9fb1042
graph : fix graph reuse reset of params (#14760)
ggerganov Jul 18, 2025
bf9087f
metal : fuse add, mul + add tests (#14596)
ggerganov Jul 18, 2025
b172309
sync : ggml
ggerganov Jul 19, 2025
f0d4d17
Documentation: Update build.md's Vulkan section (#14736)
rspOverflow Jul 19, 2025
83f5872
Vulkan: Fix fprintf format-security warning (#14770)
0cc4m Jul 19, 2025
d4b91ea
vulkan: Add logging for bf16 features to ggml_vk_print_gpu_info (#132…
Peter0x44 Jul 19, 2025
9008328
imatrix : use GGUF to store importance matrices (#9400)
compilade Jul 19, 2025
a979ca2
ggml: adds CONV_2D op and direct GEMM Vulkan implementation (#14316)
etasnadi Jul 19, 2025
36c1532
Contrib: add 0cc4m as codeowner for Vulkan backend (#14775)
0cc4m Jul 19, 2025
938b785
Clang-format: local files first + fix BinPacking (#14779)
am17an Jul 20, 2025
b526ad2
Documentation: Further revisions to the Vulkan section in build.md (#…
rspOverflow Jul 20, 2025
2be60cb
docs : fix link for tools/perplexity in README.md (#14780)
am17an Jul 20, 2025
b4efd77
server : add parse_special option to /tokenize endpoint (#14783)
IsaacDynamo Jul 21, 2025
c82d48e
llama : fix `--reverse-prompt` crashing issue (#14794)
MollySophia Jul 21, 2025
c2e058f
vulkan/cuda: Fix im2col when KW!=KH (#14789)
jeffbolznv Jul 21, 2025
2ba1333
docs : fix backends table in README.md (#14796)
rgerganov Jul 21, 2025
9220426
kleidiai: add support for get_rows (#14676)
chaxu01 Jul 21, 2025
cd465d8
sycl: Fix im2col (#14797)
Rbiessy Jul 21, 2025
6c9ee3b
opencl: add conv2d kernel (#14403)
rmatif Jul 21, 2025
38d3af1
opencl: fix `im2col` when `KW!=KH` (#14803)
CISC Jul 21, 2025
48b86c4
cuda: remove linking to cublasLt (#14790)
yeahdongcn Jul 21, 2025
adef817
server : allow setting `--reverse-prompt` arg (#14799)
MollySophia Jul 22, 2025
8e6f8bc
opencl: remove unreachable `return` (#14806)
lhez Jul 22, 2025
e28c0b8
cuda : implement bf16 cpy ops and enable bf16 cont (#14763)
CISC Jul 22, 2025
c8ade30
Mtmd: add a way to select device for vision encoder (#14236)
stduhpf Jul 22, 2025
d1aa0cc
imatrix: add option to display importance score statistics for a give…
EAddario Jul 22, 2025
d4d1522
llama : add model type detection for rwkv7 7B&14B (#14816)
MollySophia Jul 22, 2025
84712b6
vulkan: fix rms_norm_mul to handle broadcasting dim0 (#14817)
jeffbolznv Jul 22, 2025
acd6cb1
ggml : model card yaml tab->2xspace (#14819)
csabakecskemeti Jul 22, 2025
8c988fa
CUDA: add fused rms norm (#14800)
am17an Jul 23, 2025
14c28df
CANN: weight format to NZ for Ascend310P3 (#14407)
tqgy6 Jul 23, 2025
6c88b3b
ggml: fix loongarch quantize_row_q8_1 error (#14827)
lixing-star Jul 23, 2025
7233358
memory : handle saving/loading null layers in recurrent memory (#14675)
l3utterfly Jul 23, 2025
18f3b5f
tests : add non-cont K,V FA tests
ggerganov Jul 18, 2025
07a19e2
CUDA: fix quantized KV cache + multiple sequences (#14822)
JohannesGaessler Jul 23, 2025
221c0e0
ci : correct label refactor->refactoring (#14832)
CISC Jul 23, 2025
b284197
CUDA: fix compilation with GGML_CUDA_F16 (#14837)
JohannesGaessler Jul 23, 2025
a86f52b
CUDA: fix overflow in FA, tune performance (#14840)
JohannesGaessler Jul 23, 2025
a12363b
convert : text-only support for GLM-4.1V-9B-Thinking (#14823)
jacekpoplawski Jul 23, 2025
4ec6291
sycl: fix undefined variable in work group size check (#14843)
djeong20 Jul 24, 2025
065908c
metal : fix fusion across different encoders (#14849)
ggerganov Jul 24, 2025
39cffdf
docs: add libcurl-dev install hint for Linux distros (#14801)
PouyaGhahramanian Jul 24, 2025
86f5623
llama : fix MiniCPM inference after Granite Four changes (#14850)
jk3456a Jul 24, 2025
cb4a63a
sycl: fixed semantics of block offset calculation (#14814)
Alcpz Jul 24, 2025
820de57
chat : fix kimi-k2 chat template (#14852)
ngxson Jul 24, 2025
e4868d1
context : perform output reorder lazily upon access after sync (#14853)
ggerganov Jul 24, 2025
5592f27
ggml-cpu : remove stdlib include from repack.cpp (ggml/1276)
danbev Jul 21, 2025
60f816a
cmake : fix usage issues (ggml/1257)
dg0yt Jul 22, 2025
2df255d
sync : ggml
ggerganov Jul 24, 2025
3f4fc97
musa: upgrade musa sdk to rc4.2.0 (#14498)
yeahdongcn Jul 24, 2025
c12bbde
sched : fix multiple evaluations of the same graph with pipeline para…
slaren Jul 25, 2025
64bf1c3
rpc : check for null buffers in get/set/copy tensor endpoints (#14868)
struct Jul 25, 2025
749e0d2
mtmd : fix 32-bit narrowing issue in export-lora and mtmd clip (#14503)
kiwi142857 Jul 25, 2025
c1dbea7
context : restore preemptive sched reset when LLAMA_SET_ROWS=0 (#14870)
ggerganov Jul 25, 2025
e2b7621
ggml : remove invalid portPos specifiers from dot files (#14838)
ORippler Jul 25, 2025
e7fecba
docs : update HOWTO‑add‑model.md for ModelBase and new model classes …
wooksong Jul 25, 2025
ce111d3
opencl: add fused `rms_norm_mul` (#14841)
lhez Jul 25, 2025
793c0d7
metal: SSM_SCAN performance (#14743)
gabe-l-hart Jul 25, 2025
c7f3169
ggml-cpu : disable GGML_NNPA by default due to instability (#14880)
taronaeo Jul 25, 2025
9b8f3c6
musa: fix build warnings (unused variable) (#14869)
yeahdongcn Jul 26, 2025
11dd5a4
CANN: Implement GLU ops (#14884)
hipudding Jul 26, 2025
66906cd
HIP: Enable Matrix cores for MMQ Kernels, Enable stream-K for CDNA 3 …
deepsek Jul 26, 2025
446595b
Docs: add instructions for adding backends (#14889)
am17an Jul 27, 2025
1dc9614
llama : fix kq_scale for the attention layers of PLaMo2 (#14892)
mitmul Jul 27, 2025
4762ad7
model : make rope_yarn_log_mul optional for deepseek2 (#14896)
gabriellarson Jul 27, 2025
f1a4e72
vulkan: skip empty set_rows to avoid invalid API usage (#14860)
jeffbolznv Jul 27, 2025
89d1029
vulkan : add fp16 support for the conv_2d kernel (#14872)
Green-Sky Jul 27, 2025
ca0ef2d
llama : clarify comment about pp and tg graphs [no ci] (#14895)
danbev Jul 27, 2025
bbfc849
SYCL: add ops doc (#14901)
qnixsynapse Jul 27, 2025
bf78f54
vulkan: add ops docs (#14900)
0cc4m Jul 27, 2025
7f97599
quantize : update README.md (#14905)
EAddario Jul 27, 2025
613c509
cmake : Indent ggml-config.cmake (ggml/1310)
dg0yt Jul 24, 2025
1f45f28
sync : ggml
ggerganov Jul 28, 2025
c35f9ea
ops : update Metal (#14912)
ggerganov Jul 28, 2025
a5771c9
ops : update BLAS (#14914)
ggerganov Jul 28, 2025
afc0e89
sycl: refactor quantization to q8_1 (#14815)
Alcpz Jul 28, 2025
6c6e397
model : add support for SmallThinker series (#14898)
wdl339 Jul 28, 2025
946b1f6
CUDA: fix pointer incrementation in FA (#14916)
JohannesGaessler Jul 28, 2025
00fa15f
mtmd : add support for Voxtral (#14862)
ngxson Jul 28, 2025
cd1fce6
SYCL: Add set_rows support for quantized types (#14883)
qnixsynapse Jul 28, 2025
db16e28
ggml-cpu : deduplicate scalar implementations (#14897)
xctan Jul 28, 2025
c556418
llama-bench : use local GPUs along with RPC servers (#14917)
rgerganov Jul 28, 2025
bda6219
test-backend-ops : extend test case filtering (#14865)
tlemo Jul 28, 2025
8ad7b3e
opencl : add ops docs (#14910)
lhez Jul 28, 2025
0a5036b
CUDA: add roll (#14919)
am17an Jul 29, 2025
bbd0f91
server-bench: make seed choice configurable (#14929)
JohannesGaessler Jul 29, 2025
138b288
cuda : add softcap fusion (#14907)
CISC Jul 29, 2025
204f2cf
CANN: Add ggml_set_rows (#14943)
hipudding Jul 29, 2025
1a67fcc
common : avoid logging partial messages (which can contain broken UTF…
kallewoof Jul 29, 2025
c7aa136
HIP: Ignore unsupported unroll transformation in fattn-vec (#14931)
IMbackK Jul 29, 2025
b77d111
HIP: add GGML_HIP_MMQ_MFMA option to allow disableing the MFMA path. …
IMbackK Jul 29, 2025
aa79524
HIP: remove the use of __HIP_PLATFORM_AMD__, explicitly support only …
IMbackK Jul 29, 2025
61550f8
CANN: update ops docs (#14935)
bachelor-dou Jul 30, 2025
a118d80
embeddings: fix extraction of CLS pooling results (#14927)
iamlemec Jul 30, 2025
30de771
Merge branch 'layla-build' into merge
l3utterfly Jul 30, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 8 additions & 5 deletions .clang-format
Original file line number Diff line number Diff line change
Expand Up @@ -22,8 +22,8 @@ AllowShortIfStatementsOnASingleLine: Never
AllowShortLambdasOnASingleLine: Inline
AllowShortLoopsOnASingleLine: false
AlwaysBreakBeforeMultilineStrings: true
BinPackArguments: true
BinPackParameters: true # OnePerLine
BinPackArguments: false
BinPackParameters: false # OnePerLine
BitFieldColonSpacing: Both
BreakBeforeBraces: Custom # Attach
BraceWrapping:
Expand Down Expand Up @@ -70,15 +70,18 @@ ExperimentalAutoDetectBinPacking: false
FixNamespaceComments: true
IncludeBlocks: Regroup
IncludeCategories:
- Regex: '^<.*\.h>'
- Regex: '".*"'
Priority: 1
SortPriority: 0
- Regex: '^<.*'
- Regex: '^<.*\.h>'
Priority: 2
SortPriority: 0
- Regex: '.*'
- Regex: '^<.*'
Priority: 3
SortPriority: 0
- Regex: '.*'
Priority: 4
SortPriority: 0
IncludeIsMainRegex: '([-_](test|unittest))?$'
IncludeIsMainSourceRegex: ''
IndentAccessModifiers: false
Expand Down
6 changes: 3 additions & 3 deletions .devops/musa.Dockerfile
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
ARG UBUNTU_VERSION=22.04
# This needs to generally match the container host's environment.
ARG MUSA_VERSION=rc4.0.1
ARG MUSA_VERSION=rc4.2.0
# Target the MUSA build image
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-mudnn-devel-ubuntu${UBUNTU_VERSION}
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64

ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-mudnn-runtime-ubuntu${UBUNTU_VERSION}
ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64

FROM ${BASE_MUSA_DEV_CONTAINER} AS build

Expand Down
3 changes: 2 additions & 1 deletion .devops/nix/package.nix
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@ let
inherit (lib)
cmakeBool
cmakeFeature
optionalAttrs
optionals
strings
;
Expand Down Expand Up @@ -197,7 +198,7 @@ effectiveStdenv.mkDerivation (finalAttrs: {
];

# Environment variables needed for ROCm
env = optionals useRocm {
env = optionalAttrs useRocm {
ROCM_PATH = "${rocmPackages.clr}";
HIP_DEVICE_LIB_PATH = "${rocmPackages.rocm-device-libs}/amdgcn/bitcode";
};
Expand Down
4 changes: 2 additions & 2 deletions .devops/rocm.Dockerfile
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
ARG UBUNTU_VERSION=24.04

# This needs to generally match the container host's environment.
ARG ROCM_VERSION=6.3
ARG AMDGPU_VERSION=6.3
ARG ROCM_VERSION=6.4
ARG AMDGPU_VERSION=6.4

# Target the CUDA build image
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
Expand Down
276 changes: 138 additions & 138 deletions .github/workflows/build-linux-cross.yml
Original file line number Diff line number Diff line change
Expand Up @@ -48,98 +48,98 @@ jobs:

cmake --build build --config Release -j $(nproc)

ubuntu-24-riscv64-vulkan-cross:
runs-on: ubuntu-24.04

steps:
- uses: actions/checkout@v4
- name: Setup Riscv
run: |
sudo dpkg --add-architecture riscv64

# Add arch-specific repositories for non-amd64 architectures
cat << EOF | sudo tee /etc/apt/sources.list.d/riscv64-ports.list
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
EOF

sudo apt-get update || true ;# Prevent failure due to missing URLs.

sudo apt-get install -y --no-install-recommends \
build-essential \
glslc \
gcc-14-riscv64-linux-gnu \
g++-14-riscv64-linux-gnu \
libvulkan-dev:riscv64

- name: Build
run: |
cmake -B build -DLLAMA_CURL=OFF \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_VULKAN=ON \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_SYSTEM_NAME=Linux \
-DCMAKE_SYSTEM_PROCESSOR=riscv64 \
-DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14 \
-DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-DCMAKE_FIND_ROOT_PATH=/usr/lib/riscv64-linux-gnu \
-DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
-DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
-DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH

cmake --build build --config Release -j $(nproc)

ubuntu-24-arm64-vulkan-cross:
runs-on: ubuntu-24.04

steps:
- uses: actions/checkout@v4
- name: Setup Arm64
run: |
sudo dpkg --add-architecture arm64

# Add arch-specific repositories for non-amd64 architectures
cat << EOF | sudo tee /etc/apt/sources.list.d/arm64-ports.list
deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
EOF

sudo apt-get update || true ;# Prevent failure due to missing URLs.

sudo apt-get install -y --no-install-recommends \
build-essential \
glslc \
crossbuild-essential-arm64 \
libvulkan-dev:arm64

- name: Build
run: |
cmake -B build -DLLAMA_CURL=OFF \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_VULKAN=ON \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_SYSTEM_NAME=Linux \
-DCMAKE_SYSTEM_PROCESSOR=aarch64 \
-DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc \
-DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++ \
-DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-DCMAKE_FIND_ROOT_PATH=/usr/lib/aarch64-linux-gnu \
-DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
-DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
-DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH

cmake --build build --config Release -j $(nproc)
# ubuntu-24-riscv64-vulkan-cross:
# runs-on: ubuntu-24.04

# steps:
# - uses: actions/checkout@v4
# - name: Setup Riscv
# run: |
# sudo dpkg --add-architecture riscv64

# # Add arch-specific repositories for non-amd64 architectures
# cat << EOF | sudo tee /etc/apt/sources.list.d/riscv64-ports.list
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
# deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
# EOF

# sudo apt-get update || true ;# Prevent failure due to missing URLs.

# sudo apt-get install -y --no-install-recommends \
# build-essential \
# glslc \
# gcc-14-riscv64-linux-gnu \
# g++-14-riscv64-linux-gnu \
# libvulkan-dev:riscv64

# - name: Build
# run: |
# cmake -B build -DLLAMA_CURL=OFF \
# -DCMAKE_BUILD_TYPE=Release \
# -DGGML_VULKAN=ON \
# -DGGML_OPENMP=OFF \
# -DLLAMA_BUILD_EXAMPLES=ON \
# -DLLAMA_BUILD_TOOLS=ON \
# -DLLAMA_BUILD_TESTS=OFF \
# -DCMAKE_SYSTEM_NAME=Linux \
# -DCMAKE_SYSTEM_PROCESSOR=riscv64 \
# -DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
# -DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14 \
# -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
# -DCMAKE_FIND_ROOT_PATH=/usr/lib/riscv64-linux-gnu \
# -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
# -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
# -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH

# cmake --build build --config Release -j $(nproc)

# ubuntu-24-arm64-vulkan-cross:
# runs-on: ubuntu-24.04

# steps:
# - uses: actions/checkout@v4
# - name: Setup Arm64
# run: |
# sudo dpkg --add-architecture arm64

# # Add arch-specific repositories for non-amd64 architectures
# cat << EOF | sudo tee /etc/apt/sources.list.d/arm64-ports.list
# deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
# deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
# deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
# deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
# EOF

# sudo apt-get update || true ;# Prevent failure due to missing URLs.

# sudo apt-get install -y --no-install-recommends \
# build-essential \
# glslc \
# crossbuild-essential-arm64 \
# libvulkan-dev:arm64

# - name: Build
# run: |
# cmake -B build -DLLAMA_CURL=OFF \
# -DCMAKE_BUILD_TYPE=Release \
# -DGGML_VULKAN=ON \
# -DGGML_OPENMP=OFF \
# -DLLAMA_BUILD_EXAMPLES=ON \
# -DLLAMA_BUILD_TOOLS=ON \
# -DLLAMA_BUILD_TESTS=OFF \
# -DCMAKE_SYSTEM_NAME=Linux \
# -DCMAKE_SYSTEM_PROCESSOR=aarch64 \
# -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc \
# -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++ \
# -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
# -DCMAKE_FIND_ROOT_PATH=/usr/lib/aarch64-linux-gnu \
# -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
# -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
# -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH

# cmake --build build --config Release -j $(nproc)

ubuntu-24-ppc64el-cpu-cross:
runs-on: ubuntu-24.04
Expand Down Expand Up @@ -185,52 +185,52 @@ jobs:

cmake --build build --config Release -j $(nproc)

ubuntu-24-ppc64el-vulkan-cross:
runs-on: ubuntu-24.04

steps:
- uses: actions/checkout@v4
- name: Setup PowerPC64le
run: |
sudo dpkg --add-architecture ppc64el

# Add arch-specific repositories for non-amd64 architectures
cat << EOF | sudo tee /etc/apt/sources.list.d/ppc64el-ports.list
deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
EOF

sudo apt-get update || true ;# Prevent failure due to missing URLs.

sudo apt-get install -y --no-install-recommends \
build-essential \
glslc \
gcc-14-powerpc64le-linux-gnu \
g++-14-powerpc64le-linux-gnu \
libvulkan-dev:ppc64el

- name: Build
run: |
cmake -B build -DLLAMA_CURL=OFF \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_VULKAN=ON \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_SYSTEM_NAME=Linux \
-DCMAKE_SYSTEM_PROCESSOR=ppc64 \
-DCMAKE_C_COMPILER=powerpc64le-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=powerpc64le-linux-gnu-g++-14 \
-DCMAKE_POSITION_INDEPENDENT_CODE=ON \
-DCMAKE_FIND_ROOT_PATH=/usr/lib/powerpc64le-linux-gnu \
-DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
-DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
-DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH

cmake --build build --config Release -j $(nproc)
# ubuntu-24-ppc64el-vulkan-cross:
# runs-on: ubuntu-24.04

# steps:
# - uses: actions/checkout@v4
# - name: Setup PowerPC64le
# run: |
# sudo dpkg --add-architecture ppc64el

# # Add arch-specific repositories for non-amd64 architectures
# cat << EOF | sudo tee /etc/apt/sources.list.d/ppc64el-ports.list
# deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
# deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
# deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
# deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
# EOF

# sudo apt-get update || true ;# Prevent failure due to missing URLs.

# sudo apt-get install -y --no-install-recommends \
# build-essential \
# glslc \
# gcc-14-powerpc64le-linux-gnu \
# g++-14-powerpc64le-linux-gnu \
# libvulkan-dev:ppc64el

# - name: Build
# run: |
# cmake -B build -DLLAMA_CURL=OFF \
# -DCMAKE_BUILD_TYPE=Release \
# -DGGML_VULKAN=ON \
# -DGGML_OPENMP=OFF \
# -DLLAMA_BUILD_EXAMPLES=ON \
# -DLLAMA_BUILD_TOOLS=ON \
# -DLLAMA_BUILD_TESTS=OFF \
# -DCMAKE_SYSTEM_NAME=Linux \
# -DCMAKE_SYSTEM_PROCESSOR=ppc64 \
# -DCMAKE_C_COMPILER=powerpc64le-linux-gnu-gcc-14 \
# -DCMAKE_CXX_COMPILER=powerpc64le-linux-gnu-g++-14 \
# -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
# -DCMAKE_FIND_ROOT_PATH=/usr/lib/powerpc64le-linux-gnu \
# -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
# -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
# -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH

# cmake --build build --config Release -j $(nproc)

debian-13-loongarch64-cpu-cross:
runs-on: ubuntu-24.04
Expand Down
Loading
Loading