Eval bug: ggml_metal_encode_node: error: unsupported op 'IM2COL'

[beginor]

Name and Version

llama-cli --version
version: 4329 (89d604f)
built with Apple clang version 16.0.0 (clang-1600.0.26.6) for arm64-apple-darwin24.2.0

Operating systems

Mac

GGML backends

Metal

Hardware

MacBookPro M1 Max

Models

• model Qwen2-VL-72B-Instruct-Q4_K_M.gguf
• mmproj mmproj-Qwen2-VL-72B-Instruct-f32.gguf

Problem description & steps to reproduce

Just run:

llama-qwen2vl-cli -m models/qwen2-vl-72b-instruct-q4_k_m.gguf --mmproj models/qwen2-vl-72b-instruct.f32.mmproj.gguf --image demos/images/06.png --temp 0 -p "describe the image in detail."

First Bad Commit

No response

Relevant log output

llama-qwen2vl-cli -m models/qwen2-vl-72b-instruct-q4_k_m.gguf --mmproj models/qwen2-vl-72b-instruct.f32.mmproj.gguf --image demos/images/06.png --temp 0 -p "describe the image in detail." -ngl 0  
build: 4329 (89d604f2) with Apple clang version 16.0.0 (clang-1600.0.26.6) for arm64-apple-darwin24.2.0
llama_load_model_from_file: using device Metal (Apple M1 Max) - 57343 MiB free
llama_model_loader: loaded meta data with 39 key-value pairs and 963 tensors from models/qwen2-vl-72b-instruct-q4_k_m.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              = qwen2vl
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2 VL 72B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen2-VL
llama_model_loader: - kv   5:                         general.size_label str              = 72B
llama_model_loader: - kv   6:                            general.license str              = other
llama_model_loader: - kv   7:                       general.license.name str              = tongyi-qianwen
llama_model_loader: - kv   8:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2-VL-...
llama_model_loader: - kv   9:                   general.base_model.count u32              = 1
llama_model_loader: - kv  10:                  general.base_model.0.name str              = Qwen2 VL 72B
llama_model_loader: - kv  11:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  12:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2-VL-72B
llama_model_loader: - kv  13:                               general.tags arr[str,2]       = ["multimodal", "image-text-to-text"]
llama_model_loader: - kv  14:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  15:                        qwen2vl.block_count u32              = 80
llama_model_loader: - kv  16:                     qwen2vl.context_length u32              = 32768
llama_model_loader: - kv  17:                   qwen2vl.embedding_length u32              = 8192
llama_model_loader: - kv  18:                qwen2vl.feed_forward_length u32              = 29568
llama_model_loader: - kv  19:               qwen2vl.attention.head_count u32              = 64
llama_model_loader: - kv  20:            qwen2vl.attention.head_count_kv u32              = 8
llama_model_loader: - kv  21:                     qwen2vl.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  22:   qwen2vl.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  23:                          general.file_type u32              = 15
llama_model_loader: - kv  24:            qwen2vl.rope.dimension_sections arr[i32,4]       = [16, 24, 24, 0]
llama_model_loader: - kv  25:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  26:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  27:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  28:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  29:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  30:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  31:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  32:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  33:                    tokenizer.chat_template str              = {% set image_count = namespace(value=...
llama_model_loader: - kv  34:               general.quantization_version u32              = 2
llama_model_loader: - kv  35:                      quantize.imatrix.file str              = /models_out/Qwen2-VL-72B-Instruct-GGU...
llama_model_loader: - kv  36:                   quantize.imatrix.dataset str              = /training_dir/calibration_datav3.txt
llama_model_loader: - kv  37:             quantize.imatrix.entries_count i32              = 560
llama_model_loader: - kv  38:              quantize.imatrix.chunks_count i32              = 128
llama_model_loader: - type  f32:  401 tensors
llama_model_loader: - type q5_0:   40 tensors
llama_model_loader: - type q8_0:   40 tensors
llama_model_loader: - type q4_K:  401 tensors
llama_model_loader: - type q5_K:   40 tensors
llama_model_loader: - type q6_K:   41 tensors
llm_load_vocab: special tokens cache size = 14
llm_load_vocab: token to piece cache size = 0.9309 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = qwen2vl
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 152064
llm_load_print_meta: n_merges         = 151387
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 8192
llm_load_print_meta: n_layer          = 80
llm_load_print_meta: n_head           = 64
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            = 8
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-06
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             = 29568
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        = 8
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 32768
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       = 70B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 72.71 B
llm_load_print_meta: model size       = 44.15 GiB (5.22 BPW) 
llm_load_print_meta: general.name     = Qwen2 VL 72B Instruct
llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token        = 151645 '<|im_end|>'
llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
llm_load_print_meta: LF token         = 148848 'ÄĬ'
llm_load_print_meta: EOG token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token        = 151645 '<|im_end|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: offloading 0 repeating layers to GPU
llm_load_tensors: offloaded 0/81 layers to GPU
llm_load_tensors:   CPU_Mapped model buffer size = 45213.44 MiB
...................................................................................................
clip_model_load: model name:   Qwen2-VL-72B-Instruct
clip_model_load: description:  image encoder for Qwen2VL
clip_model_load: GGUF version: 3
clip_model_load: alignment:    32
clip_model_load: n_tensors:    521
clip_model_load: n_kv:         20
clip_model_load: ftype:        f32

clip_model_load: loaded meta data with 20 key-value pairs and 521 tensors from models/qwen2-vl-72b-instruct.f32.mmproj.gguf
clip_model_load: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
clip_model_load: - kv   0:                       general.architecture str              = clip
clip_model_load: - kv   1:                        general.description str              = image encoder for Qwen2VL
clip_model_load: - kv   2:                          general.file_type u32              = 0
clip_model_load: - kv   3:                      clip.has_text_encoder bool             = false
clip_model_load: - kv   4:                    clip.has_vision_encoder bool             = true
clip_model_load: - kv   5:                    clip.has_qwen2vl_merger bool             = true
clip_model_load: - kv   6:                        clip.projector_type str              = qwen2vl_merger
clip_model_load: - kv   7:                              clip.use_silu bool             = false
clip_model_load: - kv   8:                              clip.use_gelu bool             = false
clip_model_load: - kv   9:                     clip.vision.patch_size u32              = 14
clip_model_load: - kv  10:                     clip.vision.image_size u32              = 560
clip_model_load: - kv  11:               clip.vision.embedding_length u32              = 1280
clip_model_load: - kv  12:                 clip.vision.projection_dim u32              = 8192
clip_model_load: - kv  13:           clip.vision.attention.head_count u32              = 16
clip_model_load: - kv  14:   clip.vision.attention.layer_norm_epsilon f32              = 0.000001
clip_model_load: - kv  15:                    clip.vision.block_count u32              = 32
clip_model_load: - kv  16:            clip.vision.feed_forward_length u32              = 0
clip_model_load: - kv  17:                               general.name str              = Qwen2-VL-72B-Instruct
clip_model_load: - kv  18:                     clip.vision.image_mean arr[f32,3]       = [0.481455, 0.457828, 0.408211]
clip_model_load: - kv  19:                      clip.vision.image_std arr[f32,3]       = [0.268630, 0.261303, 0.275777]
clip_model_load: - type  f32:  521 tensors
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1 Max
ggml_metal_init: picking default device: Apple M1 Max
ggml_metal_init: using embedded metal library
ggml_metal_init: GPU name:   Apple M1 Max
ggml_metal_init: GPU family: MTLGPUFamilyApple7  (1007)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3  (5001)
ggml_metal_init: simdgroup reduction   = true
ggml_metal_init: simdgroup matrix mul. = true
ggml_metal_init: has bfloat            = true
ggml_metal_init: use bfloat            = false
ggml_metal_init: hasUnifiedMemory      = true
ggml_metal_init: recommendedMaxWorkingSetSize  = 60129.54 MB
ggml_metal_init: skipping kernel_get_rows_bf16                     (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32                   (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_1row              (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_l4                (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_bf16                  (not supported)
ggml_metal_init: skipping kernel_mul_mv_id_bf16_f32                (not supported)
ggml_metal_init: skipping kernel_mul_mm_bf16_f32                   (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_bf16_f32                (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h64           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h80           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h96           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h112          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h128          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h256          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h128      (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h256      (not supported)
ggml_metal_init: skipping kernel_cpy_f32_bf16                      (not supported)
ggml_metal_init: skipping kernel_cpy_bf16_f32                      (not supported)
ggml_metal_init: skipping kernel_cpy_bf16_bf16                     (not supported)
clip_model_load: CLIP using Metal backend
clip_model_load: text_encoder:   0
clip_model_load: vision_encoder: 1
clip_model_load: llava_projector:  0
clip_model_load: minicpmv_projector:  0
clip_model_load: model size:     2667.83 MB
clip_model_load: metadata size:  0.18 MB
clip_model_load: params backend buffer size =  2667.83 MB (521 tensors)
key clip.vision.image_grid_pinpoints not found in file
key clip.vision.mm_patch_merge_type not found in file
key clip.vision.image_crop_resolution not found in file
clip_model_load: compute allocated memory: 198.93 MB
llama_new_context_with_model: n_seq_max     = 1
llama_new_context_with_model: n_ctx         = 4096
llama_new_context_with_model: n_ctx_per_seq = 4096
llama_new_context_with_model: n_batch       = 2048
llama_new_context_with_model: n_ubatch      = 512
llama_new_context_with_model: flash_attn    = 0
llama_new_context_with_model: freq_base     = 1000000.0
llama_new_context_with_model: freq_scale    = 1
llama_new_context_with_model: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1 Max
ggml_metal_init: picking default device: Apple M1 Max
ggml_metal_init: using embedded metal library
ggml_metal_init: GPU name:   Apple M1 Max
ggml_metal_init: GPU family: MTLGPUFamilyApple7  (1007)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3  (5001)
ggml_metal_init: simdgroup reduction   = true
ggml_metal_init: simdgroup matrix mul. = true
ggml_metal_init: has bfloat            = true
ggml_metal_init: use bfloat            = false
ggml_metal_init: hasUnifiedMemory      = true
ggml_metal_init: recommendedMaxWorkingSetSize  = 60129.54 MB
ggml_metal_init: skipping kernel_get_rows_bf16                     (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32                   (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_1row              (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_l4                (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_bf16                  (not supported)
ggml_metal_init: skipping kernel_mul_mv_id_bf16_f32                (not supported)
ggml_metal_init: skipping kernel_mul_mm_bf16_f32                   (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_bf16_f32                (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h64           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h80           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h96           (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h112          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h128          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h256          (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h128      (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h256      (not supported)
ggml_metal_init: skipping kernel_cpy_f32_bf16                      (not supported)
ggml_metal_init: skipping kernel_cpy_bf16_f32                      (not supported)
ggml_metal_init: skipping kernel_cpy_bf16_bf16                     (not supported)
llama_kv_cache_init:        CPU KV buffer size =  1280.00 MiB
llama_new_context_with_model: KV self size  = 1280.00 MiB, K (f16):  640.00 MiB, V (f16):  640.00 MiB
llama_new_context_with_model:        CPU  output buffer size =     0.58 MiB
llama_new_context_with_model:        CPU compute buffer size =   584.01 MiB
llama_new_context_with_model: graph nodes  = 2806
llama_new_context_with_model: graph splits = 1282 (with bs=512), 1 (with bs=1)
/Users/zhang/Developer/llama.cpp/ggml/src/ggml-metal/ggml-metal.m:1263: unsupported op
ggml_metal_encode_node: error: unsupported op 'IM2COL'
zsh: abort      llama-qwen2vl-cli -m models/qwen2-vl-72b-instruct-q4_k_m.gguf --mmproj     0

[bunnyfu]

+1 Same error on Macbook Pro M3 Max when trying to run Qwen2-VL-72b