Skip to content

Eval bug: Segmentation fault when running gemma3-cli on Android #13000

New issue
New issue
Closed
Closed
Eval bug: Segmentation fault when running gemma3-cli on Android#13000
Labels
bug-unconfirmedstale
@Russyyds

Description

@Russyyds
Russyyds
opened on Apr 18, 2025

Name and Version

version: 5128 (3ec8878)
built with Android (11349228, +pgo, +bolt, +lto, -mlgo, based on r487747e) clang version 17.0.2 (https://android.googlesource.com/toolchain/llvm-project d9f89f4d16663d5012e5c09495f3b30ece3d2362) for x86_64-unknown-linux-gnu

Operating systems

Other? (Please let us know in description)

GGML backends

CPU

Hardware

Android
selecting device: 'QUALCOMM Adreno(TM) 750 (OpenCL 3.0 Adreno(TM) 750)'
OpenCL driver: OpenCL 3.0 QUALCOMM build: commit unknown Compiler E031.45.02.05

Models

google/gemma-3-4b-it-qat-q4_0-gguf

Problem description & steps to reproduce

I tried running gemma3-4b model on my android device, I came across sgement fault. Here is the step to reproduce the bug.

  1. Build the binaries:
# build command
PROJECT_DIR=$(pwd)
THIRD_PARTY_DIR=${PROJECT_DIR}/third_party

if [ ! -d $THIRD_PARTY_DIR ]; then
  mkdir $THIRD_PARTY_DIR
fi

cd $THIRD_PARTY_DIR
if [ ! -d OpenCL-Headers ]; then
  echo "Directory OpenCL-Headers already exists, remove it."
  git clone https://github.com/KhronosGroup/OpenCL-Headers
fi
cd OpenCL-Headers && \
cp -r CL $ANDROID_NDK/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include

cd ..
if [ ! -d OpenCL-ICD-Loader ]; then
    git clone https://github.com/KhronosGroup/OpenCL-ICD-Loader
fi

cd OpenCL-ICD-Loader
if [ -d build_ndk ]; then
  echo "Directory build_ndk already exists, remove it."
  rm -rf build_ndk
fi

mkdir build_ndk
cd build_ndk && \
cmake .. -G Ninja -DCMAKE_BUILD_TYPE=Release \
  -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake \
  -DOPENCL_ICD_LOADER_HEADERS_DIR=$ANDROID_NDK/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/include \
  -DANDROID_ABI=arm64-v8a \
  -DANDROID_PLATFORM=24 \
  -DANDROID_STL=c++_shared && \
ninja && \
cp libOpenCL.so $ANDROID_NDK/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/lib/aarch64-linux-android

cd ${PROJECT_DIR}
if [ -d build_android ]; then
  echo "Directory build_android already exists, remove it."
  rm -rf build_android
fi
mkdir build_android
cd build_android

cmake .. -G Ninja \
  -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake \
  -DANDROID_ABI=arm64-v8a \
  -DANDROID_PLATFORM=android-28 \
  -DBUILD_SHARED_LIBS=OFF \
  -DGGML_OPENCL=ON \
  -DGGML_OPENMP=OFF \
  -DLLAMA_CURL=OFF

ninja -j 16

2. push bins and model to device:

# push bin and model
adb push .\build\bin\ /data/local/tmp
adb push .\gemma-3-4b-it-qat-q4_0-gguf\ /data/local/tmp

3. execute the progam:

adb shell
cd /data/local/tmp/bin
chmod +x llama-gemma3-cli
llama-gemma3-cli -m ../gemma-3-4b-it-qat-q4_0-gguf/gemma-3-4b-it-q4_0.gguf \
                --mmproj ../gemma-3-4b-it-qat-q4_0-gguf/mmproj-model-f16-4B.gguf \
                -p "Describe this image in detail" \
                --image path/to/image

4. error output:

ggml_opencl: selecting platform: 'QUALCOMM Snapdragon(TM)'
ggml_opencl: selecting device: 'QUALCOMM Adreno(TM) 750 (OpenCL 3.0 Adreno(TM) 750)'
ggml_opencl: OpenCL driver: OpenCL 3.0 QUALCOMM build: commit unknown Compiler E031.45.02.05
ggml_opencl: vector subgroup broadcast support: false
ggml_opencl: device FP16 support: true
ggml_opencl: mem base addr align: 128
ggml_opencl: max mem alloc size: 1024 MB
ggml_opencl: SVM coarse grain buffer support: true
ggml_opencl: SVM fine grain buffer support: true
ggml_opencl: SVM fine grain system support: false
ggml_opencl: SVM atomics support: true
ggml_opencl: flattening quantized weights representation as struct of arrays (GGML_OPENCL_SOA_Q)
....
....
....
load_hparams: model size:         490604.59 MiB
load_hparams: metadata size:      0.15 MiB
ggml_backend_opencl_buffer_type_alloc_buffer: failed to allocate 1128.81 MiB
ggml_gallocr_reserve_n: failed to allocate OpenCL buffer of size 1183645696
main: ../gemma-3-4b-it-qat-q4_0-gguf/gemma-3-4b-it-q4_0.gguf
encoding image...
Segmentation fault

Does anyone met the same bug? Any help would be appreciate~

Thanks

First Bad Commit

No response

Relevant log output

Full log output:

ggml_opencl: selecting platform: 'QUALCOMM Snapdragon(TM)'
ggml_opencl: selecting device: 'QUALCOMM Adreno(TM) 750 (OpenCL 3.0 Adreno(TM) 750)'
ggml_opencl: OpenCL driver: OpenCL 3.0 QUALCOMM build: commit unknown Compiler E031.45.02.05
ggml_opencl: vector subgroup broadcast support: false
ggml_opencl: device FP16 support: true
ggml_opencl: mem base addr align: 128
ggml_opencl: max mem alloc size: 1024 MB
ggml_opencl: SVM coarse grain buffer support: true
ggml_opencl: SVM fine grain buffer support: true
ggml_opencl: SVM fine grain system support: false
ggml_opencl: SVM atomics support: true
ggml_opencl: flattening quantized weights representation as struct of arrays (GGML_OPENCL_SOA_Q)
ggml_opencl: using kernels optimized for Adreno (GGML_OPENCL_USE_ADRENO_KERNELS)
build: 5128 (3ec88782) with Android (11349228, +pgo, +bolt, +lto, -mlgo, based on r487747e) clang version 17.0.2 (https://android.googlesource.com/toolchain/llvm-project d9f89f4d16663d5012e5c09495f3b30ece3d2362) for x86_64-unknown-linux-gnu
llama_model_load_from_file_impl: using device GPUOpenCL (QUALCOMM Adreno(TM) 750) - 0 MiB free
llama_model_loader: loaded meta data with 39 key-value pairs and 444 tensors from ../gemma-3-4b-it-qat-q4_0-gguf/gemma-3-4b-it-q4_0.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = gemma3
llama_model_loader: - kv   1:                      gemma3.context_length u32              = 131072
llama_model_loader: - kv   2:                         gemma3.block_count u32              = 34
llama_model_loader: - kv   3:                    gemma3.embedding_length u32              = 2560
llama_model_loader: - kv   4:                 gemma3.feed_forward_length u32              = 10240
llama_model_loader: - kv   5:                gemma3.attention.head_count u32              = 8
llama_model_loader: - kv   6:             gemma3.attention.head_count_kv u32              = 4
llama_model_loader: - kv   7:                gemma3.attention.key_length u32              = 256
llama_model_loader: - kv   8:              gemma3.attention.value_length u32              = 256
llama_model_loader: - kv   9:    gemma3.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  10:                   gemma3.rope.scaling.type str              = linear
llama_model_loader: - kv  11:                 gemma3.rope.scaling.factor f32              = 8.000000
llama_model_loader: - kv  12:                      gemma3.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  13:            gemma3.attention.sliding_window u32              = 1024
llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32              = 2
llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32              = 1
llama_model_loader: - kv  17:            tokenizer.ggml.padding_token_id u32              = 0
llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32              = 3
llama_model_loader: - kv  19:                      tokenizer.ggml.tokens arr[str,262144]  = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv  20:                      tokenizer.ggml.scores arr[f32,262144]  = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,262144]  = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  22:               general.quantization_version u32              = 2
llama_model_loader: - kv  23:                          general.file_type u32              = 2
llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {{ bos_token }} {%- if messages[0]['r...
llama_model_loader: - kv  25:                 gemma3.mm.tokens_per_image u32              = 256
llama_model_loader: - kv  26:         gemma3.vision.attention.head_count u32              = 16
llama_model_loader: - kv  27: gemma3.vision.attention.layer_norm_epsilon f32              = 0.000001
llama_model_loader: - kv  28:                  gemma3.vision.block_count u32              = 27
llama_model_loader: - kv  29:             gemma3.vision.embedding_length u32              = 1152
llama_model_loader: - kv  30:          gemma3.vision.feed_forward_length u32              = 4304
llama_model_loader: - kv  31:                   gemma3.vision.image_size u32              = 896
llama_model_loader: - kv  32:                 gemma3.vision.num_channels u32              = 3
llama_model_loader: - kv  33:                   gemma3.vision.patch_size u32              = 14
llama_model_loader: - kv  34:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  35:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  36:           tokenizer.ggml.add_padding_token bool             = false
llama_model_loader: - kv  37:           tokenizer.ggml.add_unknown_token bool             = false
llama_model_loader: - kv  38:                         tokenizer.ggml.pre str              = default
llama_model_loader: - type  f32:  205 tensors
llama_model_loader: - type  f16:    1 tensors
llama_model_loader: - type q4_0:  238 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_0
print_info: file size   = 2.93 GiB (6.49 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 8
load: token to piece cache size = 1.9446 MB
print_info: arch             = gemma3
print_info: vocab_only       = 0
print_info: n_ctx_train      = 131072
print_info: n_embd           = 2560
print_info: n_layer          = 34
print_info: n_head           = 8
print_info: n_head_kv        = 4
print_info: n_rot            = 256
print_info: n_swa            = 1024
print_info: n_swa_pattern    = 6
print_info: n_embd_head_k    = 256
print_info: n_embd_head_v    = 256
print_info: n_gqa            = 2
print_info: n_embd_k_gqa     = 1024
print_info: n_embd_v_gqa     = 1024
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-06
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 6.2e-02
print_info: n_ff             = 10240
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 0.125
print_info: n_ctx_orig_yarn  = 131072
print_info: rope_finetuned   = unknown
print_info: ssm_d_conv       = 0
print_info: ssm_d_inner      = 0
print_info: ssm_d_state      = 0
print_info: ssm_dt_rank      = 0
print_info: ssm_dt_b_c_rms   = 0
print_info: model type       = 4B
print_info: model params     = 3.88 B
print_info: general.name     = n/a
print_info: vocab type       = SPM
print_info: n_vocab          = 262144
print_info: n_merges         = 0
print_info: BOS token        = 2 '<bos>'
print_info: EOS token        = 1 '<eos>'
print_info: EOT token        = 106 '<end_of_turn>'
print_info: UNK token        = 3 '<unk>'
print_info: PAD token        = 0 '<pad>'
print_info: LF token         = 248 '<0x0A>'
print_info: EOG token        = 1 '<eos>'
print_info: EOG token        = 106 '<end_of_turn>'
print_info: max token length = 93
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 0 repeating layers to GPU
load_tensors: offloaded 0/35 layers to GPU
load_tensors:   CPU_Mapped model buffer size =  3002.65 MiB
...........................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch       = 2048
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 0.125
llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context:        CPU  output buffer size =     1.00 MiB
init: kv_size = 4096, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 34, can_shift = 1
init:        CPU KV buffer size =   544.00 MiB
llama_context: KV self size  =  544.00 MiB, K (f16):  272.00 MiB, V (f16):  272.00 MiB
llama_context:        CPU compute buffer size =   517.00 MiB
llama_context: graph nodes  = 1435
llama_context: graph splits = 1
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
clip_ctx: CLIP using OpenCL backend
clip_model_loader: model name:
clip_model_loader: description:
clip_model_loader: GGUF version: 3
clip_model_loader: alignment:    32
clip_model_loader: n_tensors:    439
clip_model_loader: n_kv:         16

load_hparams: text_encoder:       0
load_hparams: vision_encoder:     1
load_hparams: llava_projector:    0
load_hparams: minicpmv_projector: 0
load_hparams: minicpmv_version:   2
load_hparams: glm_projector:      0
load_hparams: model size:         490604.59 MiB
load_hparams: metadata size:      0.15 MiB
ggml_backend_opencl_buffer_type_alloc_buffer: failed to allocate 1128.81 MiB
ggml_gallocr_reserve_n: failed to allocate OpenCL buffer of size 1183645696
main: ../gemma-3-4b-it-qat-q4_0-gguf/gemma-3-4b-it-q4_0.gguf
encoding image...
Segmentation fault

Metadata

Metadata

Assignees

No one assigned

    Labels

    bug-unconfirmedstale

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions