Error of running llama3.2-vision with the ipex-llm's built-in ollama.

[1ngram433]

I followed the steps in #https://github.com/intel-analytics/ipex-llm/blob/main/docs/mddocs/Quickstart/ollama_quickstart.md to set up ollama. I can successfully run llama3.2 and qwen. However, when I use ollama run llama3.2-vision, I get an error:
GGML_ASSERT(ggml_nelements(a) == ne0ne1ne2) failed
time=2025-01-15T10:43:34.636+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
time=2025-01-15T10:43:34.887+08:00 level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: GGML_ASSERT(ggml_nelements(a) == ne0ne1ne2) failed"

[1ngram433]

The following is the complete and detailed error message:

time=2025-01-15T10:43:29.059+08:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
time=2025-01-15T10:43:29.059+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-01-15T10:43:29.059+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12
time=2025-01-15T10:43:29.097+08:00 level=INFO source=server.go:105 msg="system memory" total="31.9 GiB" free="24.4 GiB" free_swap="25.2 GiB"
time=2025-01-15T10:43:29.097+08:00 level=INFO source=memory.go:356 msg="offload to device" projector.weights="1.8 GiB" projector.graph="2.8 GiB" layers.requested=-1 layers.model=41 layers.offload=0 layers.split="" memory.available="[24.4 GiB]" memory.gpu_overhead="0 B" memory.required.full="10.9 GiB" memory.required.partial="0 B" memory.required.kv="656.2 MiB" memory.required.allocations="[10.9 GiB]" memory.weights.total="5.5 GiB" memory.weights.repeating="5.1 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="258.5 MiB" memory.graph.partial="669.5 MiB"
time=2025-01-15T10:43:29.111+08:00 level=INFO source=server.go:401 msg="starting llama server" cmd="C:\\Users\\1ngram4\\llama-cpp\\dist\\windows-amd64\\lib\\ollama\\runners\\ipex_llm\\ollama_llama_server.exe --model C:\\Users\\1ngram4\\.ollama\\models\\blobs\\sha256-11f274007f093fefeec994a5dbbb33d0733a4feb87f7ab66dcd7c1069fef0068 --ctx-size 2048 --batch-size 512 --n-gpu-layers 999 --mmproj C:\\Users\\1ngram4\\.ollama\\models\\blobs\\sha256-ece5e659647a20a5c28ab9eea1c12a1ad430bc0f2a27021d00ad103b3bf5206f --threads 6 --no-mmap --parallel 1 --port 51907"
time=2025-01-15T10:43:29.116+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-01-15T10:43:29.116+08:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding"
time=2025-01-15T10:43:29.117+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
time=2025-01-15T10:43:29.151+08:00 level=INFO source=runner.go:963 msg="starting go runner"
time=2025-01-15T10:43:29.159+08:00 level=INFO source=runner.go:964 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(clang)" threads=6
time=2025-01-15T10:43:29.160+08:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:51907"
llama_model_loader: loaded meta data with 27 key-value pairs and 396 tensors from C:\Users\1ngram4\.ollama\models\blobs\sha256-11f274007f093fefeec994a5dbbb33d0733a4feb87f7ab66dcd7c1069fef0068 (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              = mllama
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Model
llama_model_loader: - kv   3:                         general.size_label str              = 10B
llama_model_loader: - kv   4:                         mllama.block_count u32              = 40
llama_model_loader: - kv   5:                      mllama.context_length u32              = 131072
llama_model_loader: - kv   6:                    mllama.embedding_length u32              = 4096
llama_model_loader: - kv   7:                 mllama.feed_forward_length u32              = 14336
llama_model_loader: - kv   8:                mllama.attention.head_count u32              = 32
llama_model_loader: - kv   9:             mllama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  10:                      mllama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  11:    mllama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  12:                          general.file_type u32              = 15
llama_model_loader: - kv  13:                          mllama.vocab_size u32              = 128256
llama_model_loader: - kv  14:                mllama.rope.dimension_count u32              = 128
llama_model_loader: - kv  15:    mllama.attention.cross_attention_layers arr[i32,8]       = [3, 8, 13, 18, 23, 28, 33, 38]
llama_model_loader: - kv  16:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  17:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  18:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  19:                      tokenizer.ggml.tokens arr[str,128257]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  20:                  tokenizer.ggml.token_type arr[i32,128257]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  21:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  22:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  23:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  24:            tokenizer.ggml.padding_token_id u32              = 128004
llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv  26:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  114 tensors
llama_model_loader: - type q4_K:  245 tensors
llama_model_loader: - type q6_K:   37 tensors
time=2025-01-15T10:43:29.368+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 257
llm_load_vocab: token to piece cache size = 0.7999 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = mllama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 131072
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_layer          = 40
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 4
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 14336
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 131072
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 11B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 9.78 B
llm_load_print_meta: model size       = 5.55 GiB (4.87 BPW)
llm_load_print_meta: general.name     = Model
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
llm_load_print_meta: PAD token        = 128004 '<|finetune_right_pad_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llama_model_load: vocab mismatch 128256 !- 128257 ...
ggml_sycl_init: GGML_SYCL_FORCE_MMQ:   no
ggml_sycl_init: SYCL_USE_XMX: yes
ggml_sycl_init: found 1 SYCL devices:
llm_load_tensors: ggml ctx size =    0.36 MiB
llm_load_tensors: offloading 40 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 41/41 layers to GPU
llm_load_tensors:      SYCL0 buffer size =  5397.51 MiB
llm_load_tensors:  SYCL_Host buffer size =   281.83 MiB
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 500000.0
llama_new_context_with_model: freq_scale = 1
[SYCL] call ggml_check_sycl
ggml_check_sycl: GGML_SYCL_DEBUG: 0
ggml_check_sycl: GGML_SYCL_F16: no
found 1 SYCL devices:
|  |                   |                                       |       |Max    |        |Max  |Global |
    |
|  |                   |                                       |       |compute|Max work|sub  |mem    |
    |
|ID|        Device Type|                                   Name|Version|units  |group   |group|size   |       Driver version|
|--|-------------------|---------------------------------------|-------|-------|--------|-----|-------|---------------------|
| 0| [level_zero:gpu:0]|                Intel Arc A750 Graphics|    1.6|    448|    1024|   32|  8319M|            1.3.31441|
llama_kv_cache_init:      SYCL0 KV buffer size =   656.25 MiB
llama_new_context_with_model: KV self size  =  656.25 MiB, K (f16):  328.12 MiB, V (f16):  328.12 MiB
llama_new_context_with_model:  SYCL_Host  output buffer size =     0.50 MiB
llama_new_context_with_model:      SYCL0 compute buffer size =   258.50 MiB
llama_new_context_with_model:  SYCL_Host compute buffer size =    12.01 MiB
llama_new_context_with_model: graph nodes  = 902
llama_new_context_with_model: graph splits = 2
mllama_model_load: model name:   Llama-3.2-11B-Vision-Instruct
mllama_model_load: description:  vision encoder for Mllama
mllama_model_load: GGUF version: 3
mllama_model_load: alignment:    32
mllama_model_load: n_tensors:    512
mllama_model_load: n_kv:         17
mllama_model_load: ftype:        f16
mllama_model_load:
mllama_model_load: vision using CPU backend
D:\actions-runner\release-cpp-oneapi_2024_2\_work\llm.cpp\llm.cpp\ollama-llama-cpp\ggml\src\ggml.c:5964: GGML_ASSERT(ggml_nelements(a) == ne0*ne1*ne2) failed
time=2025-01-15T10:43:34.636+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
time=2025-01-15T10:43:34.887+08:00 level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: GGML_ASSERT(ggml_nelements(a) == ne0*ne1*ne2) failed"
[GIN] 2025/01/15 - 10:43:34 | 500 |    5.8456854s |       127.0.0.1 | POST     "/api/generate"

[sgwhat]

Hi @1ngram433, what's your ollama version? And could you pls provide the specific information of your device?

[1ngram433]

Thank you, my ollama version is 0.5.1-ipexllm-20250114, and ipex-llm version is 2.2.0b20250114

AMD Ryzen 5 5500
GPU Intel Arc 750 Graphics
RAM 32GB

[sgwhat]

Well, I cannot reproduce your issue. I suspect it is related to the use of an AMD CPU on your device.