Bug: llava.cpp Segmentation fault (core dumped) starting in faf69d4237c9ae4d7f572b4674d1002463e8acd3 #9436
Description
What happened?
I am getting Segmentation fault (core dumped) when running llama-llava-cli and llama-minicpmv-cli starting in faf69d4. After reviewing faf69d4, I think the problem is related to these lines in the llama.cpp that try to access tokens when only image emb are given
for (uint32_t i = 0; i < n_tokens_all; ++i) {
if (batch_all.token[i] < 0 || (uint32_t)batch_all.token[i] >= lctx.model.vocab.n_vocab) {
LLAMA_LOG_ERROR("%s: invalid token[%d] = %d", __func__, i, batch_all.token[i]);
return -1;
}
}Name and Version
/llama.cpp$ ./llama-cli --version22.04) 11.4.0 for x86_64-linux-gnu
version: 3731 (0996c55)
built with cc (Ubuntu 11.4.0-1ubuntu1
What operating system are you seeing the problem on?
Linux
Relevant log output
~/llama.cpp$ ./llama-llava-cli -m ../.cache/huggingface/hub/models--cjpais--llava-1.6-mistral-7b-gguf/snapshots/6019df415777605a8364e2668aa08b7e354bf0ba/llava-v1.6-mistral-7b.Q4_K_M.gguf --mmproj ../.cache/huggingface/hub/models--cjpais--llava-1.6-mistral-7b-gguf/snapshots/6019df415777605a8364e2668aa08b7e354bf0ba/mmproj-model-f16.gguf --image 458623.jpg -p "What is this image?" -c 8192 -ngl 33
Log start
llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from ../.cache/huggingface/hub/models--cjpais--llava-1.6-mistral-7b-gguf/snapshots/6019df415777605a8364e2668aa08b7e354bf0ba/llava-v1.6-mistral-7b.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 = llama
llama_model_loader: - kv 1: general.name str = 1.6
llama_model_loader: - kv 2: llama.context_length u32 = 32768
llama_model_loader: - kv 3: llama.embedding_length u32 = 4096
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 7: llama.attention.head_count u32 = 32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: llama.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 11: general.file_type u32 = 15
llama_model_loader: - kv 12: tokenizer.ggml.model str = llama
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 22: tokenizer.chat_template str = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv 23: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
llm_load_vocab: special tokens cache size = 3
llm_load_vocab: token to piece cache size = 0.1637 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_layer = 32
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 = 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 = 7B
llm_load_print_meta: model ftype = Q4_K - Medium
llm_load_print_meta: model params = 7.24 B
llm_load_print_meta: model size = 4.07 GiB (4.83 BPW)
llm_load_print_meta: general.name = 1.6
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_print_meta: max token length = 48
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4070 Laptop GPU, compute capability 8.9, VMM: yes
llm_load_tensors: ggml ctx size = 0.27 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors: CPU buffer size = 70.31 MiB
llm_load_tensors: CUDA0 buffer size = 4095.05 MiB
................................................................................................
clip_model_load: model name: vit-large336-custom
clip_model_load: description: image encoder for LLaVA
clip_model_load: GGUF version: 3
clip_model_load: alignment: 32
clip_model_load: n_tensors: 378
clip_model_load: n_kv: 25
clip_model_load: ftype: f16
clip_model_load: loaded meta data with 25 key-value pairs and 378 tensors from ../.cache/huggingface/hub/models--cjpais--llava-1.6-mistral-7b-gguf/snapshots/6019df415777605a8364e2668aa08b7e354bf0ba/mmproj-model-f16.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: clip.has_text_encoder bool = false
clip_model_load: - kv 2: clip.has_vision_encoder bool = true
clip_model_load: - kv 3: clip.has_llava_projector bool = true
clip_model_load: - kv 4: general.file_type u32 = 1
clip_model_load: - kv 5: general.name str = vit-large336-custom
clip_model_load: - kv 6: general.description str = image encoder for LLaVA
clip_model_load: - kv 7: clip.projector_type str = mlp
clip_model_load: - kv 8: clip.vision.image_size u32 = 336
clip_model_load: - kv 9: clip.vision.patch_size u32 = 14
clip_model_load: - kv 10: clip.vision.embedding_length u32 = 1024
clip_model_load: - kv 11: clip.vision.feed_forward_length u32 = 4096
clip_model_load: - kv 12: clip.vision.projection_dim u32 = 768
clip_model_load: - kv 13: clip.vision.attention.head_count u32 = 16
clip_model_load: - kv 14: clip.vision.attention.layer_norm_epsilon f32 = 0.000010
clip_model_load: - kv 15: clip.vision.block_count u32 = 23
clip_model_load: - kv 16: clip.vision.image_grid_pinpoints arr[i32,10] = [336, 672, 672, 336, 672, 672, 1008, ...
clip_model_load: - kv 17: clip.vision.image_crop_resolution u32 = 224
clip_model_load: - kv 18: clip.vision.image_aspect_ratio str = anyres
clip_model_load: - kv 19: clip.vision.image_split_resolution u32 = 224
clip_model_load: - kv 20: clip.vision.mm_patch_merge_type str = spatial_unpad
clip_model_load: - kv 21: clip.vision.mm_projector_type str = mlp2x_gelu
clip_model_load: - kv 22: clip.vision.image_mean arr[f32,3] = [0.481455, 0.457828, 0.408211]
clip_model_load: - kv 23: clip.vision.image_std arr[f32,3] = [0.268630, 0.261303, 0.275777]
clip_model_load: - kv 24: clip.use_gelu bool = false
clip_model_load: - type f32: 236 tensors
clip_model_load: - type f16: 142 tensors
clip_model_load: CLIP using CUDA backend
clip_model_load: text_encoder: 0
clip_model_load: vision_encoder: 1
clip_model_load: llava_projector: 1
clip_model_load: minicpmv_projector: 0
clip_model_load: model size: 595.50 MB
clip_model_load: metadata size: 0.13 MB
clip_model_load: params backend buffer size = 595.50 MB (378 tensors)
clip_model_load: compute allocated memory: 32.89 MB
llama_new_context_with_model: n_ctx = 8192
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_kv_cache_init: CUDA0 KV buffer size = 1024.00 MiB
llama_new_context_with_model: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.12 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 560.00 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 24.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 2
encode_image_with_clip: 5 segments encoded in 256.86 ms
encode_image_with_clip: image embedding created: 2880 tokens
encode_image_with_clip: image encoded in 293.57 ms by CLIP ( 0.10 ms per image patch)
Segmentation fault (core dumped)
~/llama.cpp$ ./llama-minicpmv-cli -m ../.cache/huggingface/hub/models--openbmb--MiniCPM-V-2_6-gguf/snapshots/69b9eaaebde4d5e2fafa1adb6a4169c349244cf6/ggml-model-Q4_K_M.gguf --mmproj ../.cache/huggingface/hub/models--openbmb--MiniCPM-V-2_6-gguf/snapshots/69b9eaaebde4d5e2fafa1adb6a4169c349244cf6/mmproj-model-f16.gguf --image 458623.jpg -p "What is this image?" -c 8192 -ngl 33
Log start
clip_model_load: description: image encoder for MiniCPM-V
clip_model_load: GGUF version: 3
clip_model_load: alignment: 32
clip_model_load: n_tensors: 455
clip_model_load: n_kv: 19
clip_model_load: ftype: f16
clip_model_load: loaded meta data with 19 key-value pairs and 455 tensors from ../.cache/huggingface/hub/models--openbmb--MiniCPM-V-2_6-gguf/snapshots/69b9eaaebde4d5e2fafa1adb6a4169c349244cf6/mmproj-model-f16.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: clip.has_text_encoder bool = false
clip_model_load: - kv 2: clip.has_vision_encoder bool = true
clip_model_load: - kv 3: clip.has_minicpmv_projector bool = true
clip_model_load: - kv 4: general.file_type u32 = 1
clip_model_load: - kv 5: general.description str = image encoder for MiniCPM-V
clip_model_load: - kv 6: clip.projector_type str = resampler
clip_model_load: - kv 7: clip.minicpmv_version i32 = 3
clip_model_load: - kv 8: clip.vision.image_size u32 = 448
clip_model_load: - kv 9: clip.vision.patch_size u32 = 14
clip_model_load: - kv 10: clip.vision.embedding_length u32 = 1152
clip_model_load: - kv 11: clip.vision.feed_forward_length u32 = 4304
clip_model_load: - kv 12: clip.vision.projection_dim u32 = 0
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 = 26
clip_model_load: - kv 16: clip.vision.image_mean arr[f32,3] = [0.500000, 0.500000, 0.500000]
clip_model_load: - kv 17: clip.vision.image_std arr[f32,3] = [0.500000, 0.500000, 0.500000]
clip_model_load: - kv 18: clip.use_gelu bool = true
clip_model_load: - type f32: 285 tensors
clip_model_load: - type f16: 170 tensors
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4070 Laptop GPU, compute capability 8.9, VMM: yes
clip_model_load: CLIP using CUDA backend
clip_model_load: text_encoder: 0
clip_model_load: vision_encoder: 1
clip_model_load: llava_projector: 0
clip_model_load: minicpmv_projector: 1
clip_model_load: model size: 996.02 MB
clip_model_load: metadata size: 0.16 MB
clip_model_load: params backend buffer size = 996.02 MB (455 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_image_build_graph: 448 448
clip_model_load: compute allocated memory: 102.80 MB
uhd_slice_image: multiple 9
uhd_slice_image: image_size: 1594 1080; source_image size: 546 364
uhd_slice_image: image_size: 1594 1080; best_grid: 4 2
uhd_slice_image: refine_image_size: 1512 1036; refine_size: 1512 1036
clip_image_preprocess: 546 364
clip_image_preprocess: 378 518
clip_image_preprocess: 378 518
clip_image_preprocess: 378 518
clip_image_preprocess: 378 518
clip_image_preprocess: 378 518
clip_image_preprocess: 378 518
clip_image_preprocess: 378 518
clip_image_preprocess: 378 518
clip_image_build_graph: 546 364
encode_image_with_clip: step 1 of 9 encoded in 162.32 ms
clip_image_build_graph: 378 518
encode_image_with_clip: step 2 of 9 encoded in 137.34 ms
clip_image_build_graph: 378 518
encode_image_with_clip: step 3 of 9 encoded in 116.51 ms
clip_image_build_graph: 378 518
encode_image_with_clip: step 4 of 9 encoded in 114.31 ms
clip_image_build_graph: 378 518
encode_image_with_clip: step 5 of 9 encoded in 113.83 ms
clip_image_build_graph: 378 518
encode_image_with_clip: step 6 of 9 encoded in 117.35 ms
clip_image_build_graph: 378 518
encode_image_with_clip: step 7 of 9 encoded in 114.32 ms
clip_image_build_graph: 378 518
encode_image_with_clip: step 8 of 9 encoded in 114.95 ms
clip_image_build_graph: 378 518
encode_image_with_clip: step 9 of 9 encoded in 115.67 ms
encode_image_with_clip: all 9 segments encoded in 1106.94 ms
encode_image_with_clip: load_image_size 1594 1080
encode_image_with_clip: image embedding created: 576 tokens
encode_image_with_clip: image encoded in 1109.53 ms by CLIP ( 1.93 ms per image patch)
llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from ../.cache/huggingface/hub/models--openbmb--MiniCPM-V-2_6-gguf/snapshots/69b9eaaebde4d5e2fafa1adb6a4169c349244cf6/ggml-model-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 = qwen2
llama_model_loader: - kv 1: general.name str = model
llama_model_loader: - kv 2: qwen2.block_count u32 = 28
llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584
llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944
llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28
llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4
llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 10: general.file_type u32 = 15
llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644
llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244
llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo...
llama_model_loader: - kv 21: general.quantization_version u32 = 2
llama_model_loader: - type f32: 141 tensors
llama_model_loader: - type q4_K: 169 tensors
llama_model_loader: - type q6_K: 29 tensors
llm_load_vocab: special tokens cache size = 25
llm_load_vocab: token to piece cache size = 0.9309 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = qwen2
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 151666
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 = 3584
llm_load_print_meta: n_layer = 28
llm_load_print_meta: n_head = 28
llm_load_print_meta: n_head_kv = 4
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 = 7
llm_load_print_meta: n_embd_k_gqa = 512
llm_load_print_meta: n_embd_v_gqa = 512
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 = 18944
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 = 2
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 = ?B
llm_load_print_meta: model ftype = Q4_K - Medium
llm_load_print_meta: model params = 7.61 B
llm_load_print_meta: model size = 4.35 GiB (4.91 BPW)
llm_load_print_meta: general.name = model
llm_load_print_meta: BOS token = 151644 '<|im_start|>'
llm_load_print_meta: EOS token = 151645 '<|im_end|>'
llm_load_print_meta: UNK token = 128244 '<unk>'
llm_load_print_meta: PAD token = 0 '!'
llm_load_print_meta: LF token = 148848 'ÄĬ'
llm_load_print_meta: EOT token = 151645 '<|im_end|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: ggml ctx size = 0.30 MiB
llm_load_tensors: offloading 28 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 29/29 layers to GPU
llm_load_tensors: CPU buffer size = 291.59 MiB
llm_load_tensors: CUDA0 buffer size = 4166.97 MiB
....................................................................................
llama_new_context_with_model: n_ctx = 8192
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_kv_cache_init: CUDA0 KV buffer size = 448.00 MiB
llama_new_context_with_model: KV self size = 448.00 MiB, K (f16): 224.00 MiB, V (f16): 224.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.58 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 492.00 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 23.01 MiB
llama_new_context_with_model: graph nodes = 986
llama_new_context_with_model: graph splits = 2
minicpmv_init: llava init in 10.14 ms.
process_image: image token past: 0
Segmentation fault (core dumped)