llama.cpp
llama.cpp copied to clipboard
Published
20 hours ago •
ggml-org
ggml-org
Misc. bug: Segmentation fault when importing model to opencl buffer
Name and Version
version: 4737 (5137da7b) built with cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0 for aarch64-linux-gnu
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
llama-cli
Command line
llama-cli -m /home/aidlux/QualcommLLM/models/Qwen2.5_0.5b.gguf -ngl 1
Problem description & steps to reproduce
The program llama-cli caused a Segmentation falt when initialize model on opencl device. I tried to findout what the problem is with clion debug mode. Here is the call stack and some value:
The program runs correctly when running model on CPU. But when I run with param "-ngl 1" trying to load a layer on GPU, it raised a sagmentation falt.
I compiled llama.cpp on my QCS6490 device whith Adreno643L GPU, setting GGML_OPENCL=ON.
Because of the limit on my device, I tried to reset max buffer size to adapt my device in ggml/src/ggml-opencl/ggml-opencl.cpp: line800-803 as below:
// Allocate intermediate buffers and images
size_t max_A_q_d_bytes = 268435456;//311164928;
size_t max_A_s_d_bytes = 268435456;//38895616;
size_t max_B_d_bytes = 268435456;//45088768;
below is clinfo about my device:
Number of platforms 1
Platform Name QUALCOMM Snapdragon(TM)
Platform Vendor QUALCOMM
Platform Version OpenCL 3.0 QUALCOMM build: commit unknown
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd
Platform Host timer resolution 0ns
Platform Extensions function suffix QCOM
Platform Name QUALCOMM Snapdragon(TM)
Number of devices 1
Device Name QUALCOMM Adreno(TM) 643
Device Vendor QUALCOMM
Device Vendor ID 0x5143
Device Version OpenCL 2.0 Adreno(TM) 643
Driver Version OpenCL 3.0 QUALCOMM build: commit unknown Compiler E031.42.02.00
Device OpenCL C Version OpenCL C 2.0 Adreno(TM) 643
Device Type GPU
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 2
Max clock frequency 1MHz
Device Partition (core)
Max number of sub-devices 1
Supported partition types None
Supported affinity domains (n/a)
Max work item dimensions 3
Max work item sizes 1024x1024x1024
Max work group size 1024
Preferred work group size multiple 128
Preferred / native vector sizes
char 1 / 1
short 1 / 1
int 1 / 1
long 1 / 0
half 1 / 1 (cl_khr_fp16)
float 1 / 1
double 0 / 0 (n/a)
Half-precision Floating-point support (cl_khr_fp16)
Denormals No
Infinity and NANs Yes
Round to nearest Yes
Round to zero No
Round to infinity Yes
IEEE754-2008 fused multiply-add No
Support is emulated in software No
Single-precision Floating-point support (core)
Denormals No
Infinity and NANs Yes
Round to nearest Yes
Round to zero No
Round to infinity Yes
IEEE754-2008 fused multiply-add No
Support is emulated in software No
Correctly-rounded divide and sqrt operations No
Double-precision Floating-point support (n/a)
Address bits 64, Little-Endian
Global memory size 1073741824 (1024MiB)
Error Correction support No
Max memory allocation 268435456 (256MiB)
Unified memory for Host and Device Yes
Shared Virtual Memory (SVM) capabilities (core)
Coarse-grained buffer sharing Yes
Fine-grained buffer sharing Yes
Fine-grained system sharing No
Atomics Yes
Minimum alignment for any data type 128 bytes
Alignment of base address 1024 bits (128 bytes)
Page size (QCOM) 4096 bytes
External memory padding (QCOM) 0 bytes
Preferred alignment for atomics
SVM 128 bytes
Global 0 bytes
Local 0 bytes
Max size for global variable 65536 (64KiB)
Preferred total size of global vars 1048576 (1024KiB)
Global Memory cache type Read/Write
Global Memory cache size 262144 (256KiB)
Global Memory cache line size 64 bytes
Image support Yes
Max number of samplers per kernel 16
Max size for 1D images from buffer 134217728 pixels
Max 1D or 2D image array size 2048 images
Base address alignment for 2D image buffers 64 bytes
Pitch alignment for 2D image buffers 64 pixels
Max 2D image size 16384x16384 pixels
Max 3D image size 16384x16384x2048 pixels
Max number of read image args 128
Max number of write image args 64
Max number of read/write image args 64
Max number of pipe args 16
Max active pipe reservations 4096
Max pipe packet size 1024
Local memory type Local
Local memory size 32768 (32KiB)
Max number of constant args 8
Max constant buffer size 65536 (64KiB)
Max size of kernel argument 1024
Queue properties (on host)
Out-of-order execution Yes
Profiling Yes
Queue properties (on device)
Out-of-order execution Yes
Profiling Yes
Preferred size 655376 (640KiB)
Max size 655376 (640KiB)
Max queues on device 1
Max events on device 1024
Prefer user sync for interop No
Profiling timer resolution 1000ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
printf() buffer size 1048576 (1024KiB)
Built-in kernels (n/a)
Device Extensions cl_img_egl_image cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_egl_event cl_khr_egl_image cl_khr_fp16 cl_khr_gl_sharing cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_image2d_from_buffer cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_mipmap_image cl_khr_srgb_image_writes cl_khr_subgroups cl_qcom_accelerated_image_ops cl_qcom_compressed_image cl_qcom_compressed_yuv_image_read cl_qcom_create_buffer_from_image cl_qcom_dot_product8 cl_qcom_ext_host_ptr cl_qcom_ext_host_ptr_iocoherent cl_qcom_extract_image_plane cl_qcom_ion_host_ptr cl_qcom_other_image cl_qcom_perf_hint cl_qcom_priority_hint cl_qcom_protected_context cl_qcom_reqd_sub_group_size cl_qcom_subgroup_shuffle cl_qcom_vector_image_ops
NULL platform behavior
clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) QUALCOMM Snapdragon(TM)
clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [QCOM]
clCreateContext(NULL, ...) [default] Success [QCOM]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)
Platform Name QUALCOMM Snapdragon(TM)
Device Name QUALCOMM Adreno(TM) 643
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1)
Platform Name QUALCOMM Snapdragon(TM)
Device Name QUALCOMM Adreno(TM) 643
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) Invalid device type for platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1)
Platform Name QUALCOMM Snapdragon(TM)
Device Name QUALCOMM Adreno(TM) 643
ICD loader properties
ICD loader Name OpenCL ICD Loader
ICD loader Vendor OCL Icd free software
ICD loader Version 2.2.11
ICD loader Profile OpenCL 2.1
NOTE: your OpenCL library only supports OpenCL 2.1,
but some installed platforms support OpenCL 3.0.
Programs using 3.0 features may crash
or behave unexpectedly
First Bad Commit
No response
Relevant log output
Program output with command "llama-cli -m ~/QualcommLLM/models/Qwen2.5_0.5b.gguf -ngl 1":
ggml_opencl: selecting platform: 'QUALCOMM Snapdragon(TM)'
ggml_opencl: selecting device: 'QUALCOMM Adreno(TM) 643'
ggml_opencl: Unsupported Adreno GPU: , using wave size 128, may not work as expected
ggml_opencl: device OpenCL version: OpenCL 2.0 Adreno(TM) 643
ggml_opencl: OpenCL driver: OpenCL 3.0 QUALCOMM build: commit unknown Compiler E031.42.02.00
ggml_opencl: vector subgroup broadcast support: false
ggml_opencl: device FP16 support: true
ggml_opencl: mem base addr align: 1024
ggml_opencl: max mem alloc size: 256 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)
register_backend: registered backend OpenCL (1 devices)
register_device: registered device GPUOpenCL (QUALCOMM Adreno(TM) 643)
register_backend: registered backend CPU (1 devices)
register_device: registered device CPU (CPU)
load_backend: failed to find ggml_backend_init in /home/aidlux/QualcommLLM/dev/llm/llama.cpp/cmake-build-debug/bin/libggml-opencl.so
load_backend: failed to find ggml_backend_init in /home/aidlux/QualcommLLM/dev/llm/llama.cpp/cmake-build-debug/bin/libggml-cpu.so
build: 4737 (5137da7b) with cc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0 for aarch64-linux-gnu (debug)
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_load_from_file_impl: using device GPUOpenCL (QUALCOMM Adreno(TM) 643) - 0 MiB free
llama_model_loader: loaded meta data with 34 key-value pairs and 290 tensors from /home/aidlux/QualcommLLM/models/Qwen2.5_0.5b.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 = qwen2
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen2.5 0.5B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Qwen2.5
llama_model_loader: - kv 5: general.size_label str = 0.5B
llama_model_loader: - kv 6: general.license str = apache-2.0
llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-0...
llama_model_loader: - kv 8: general.base_model.count u32 = 1
llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 0.5B
llama_model_loader: - kv 10: general.base_model.0.organization str = Qwen
llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-0.5B
llama_model_loader: - kv 12: general.tags arr[str,2] = ["chat", "text-generation"]
llama_model_loader: - kv 13: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 14: qwen2.block_count u32 = 24
llama_model_loader: - kv 15: qwen2.context_length u32 = 32768
llama_model_loader: - kv 16: qwen2.embedding_length u32 = 896
llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 4864
llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 14
llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 2
llama_model_loader: - kv 20: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 21: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 22: general.file_type u32 = 1
llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 24: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 32: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 33: general.quantization_version u32 = 2
llama_model_loader: - type f32: 121 tensors
llama_model_loader: - type f16: 169 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = F16
print_info: file size = 942.43 MiB (16.00 BPW)
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch = qwen2
print_info: vocab_only = 0
print_info: n_ctx_train = 32768
print_info: n_embd = 896
print_info: n_layer = 24
print_info: n_head = 14
print_info: n_head_kv = 2
print_info: n_rot = 64
print_info: n_swa = 0
print_info: n_embd_head_k = 64
print_info: n_embd_head_v = 64
print_info: n_gqa = 7
print_info: n_embd_k_gqa = 128
print_info: n_embd_v_gqa = 128
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: n_ff = 4864
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 = 1
print_info: n_ctx_orig_yarn = 32768
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 = 1B
print_info: model params = 494.03 M
print_info: general.name = Qwen2.5 0.5B Instruct
print_info: vocab type = BPE
print_info: n_vocab = 151936
print_info: n_merges = 151387
print_info: BOS token = 151643 '<|endoftext|>'
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151643 '<|endoftext|>'
print_info: LF token = 198 'Ċ'
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
print_info: FIM MID token = 151660 '<|fim_middle|>'
print_info: FIM PAD token = 151662 '<|fim_pad|>'
print_info: FIM REP token = 151663 '<|repo_name|>'
print_info: FIM SEP token = 151664 '<|file_sep|>'
print_info: EOG token = 151643 '<|endoftext|>'
print_info: EOG token = 151645 '<|im_end|>'
print_info: EOG token = 151662 '<|fim_pad|>'
print_info: EOG token = 151663 '<|repo_name|>'
print_info: EOG token = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 1 repeating layers to GPU
load_tensors: offloaded 1/25 layers to GPU
load_tensors: CPU_Mapped model buffer size = 942.43 MiB
load_tensors: OpenCL model buffer size = 28.45 MiB
..........................................................................
llama_init_from_model: n_seq_max = 1
llama_init_from_model: n_ctx = 4096
llama_init_from_model: n_ctx_per_seq = 4096
llama_init_from_model: n_batch = 2048
llama_init_from_model: n_ubatch = 512
llama_init_from_model: flash_attn = 0
llama_init_from_model: freq_base = 1000000.0
llama_init_from_model: freq_scale = 1
llama_init_from_model: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 4096, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 24, can_shift = 1
llama_kv_cache_init: CPU KV buffer size = 46.00 MiB
Segmentation fault
