jan
jan copied to clipboard
Published
20 hours ago •
janhq
janhq
bug: LLAMA_CPP_PROCESS_ERROR The model process encountered an unexpected error.
Version: v0.7.3
b6929/win-avx2-cuda-cu12.0-x64
Describe the Bug
loading model makes this error model does not load.
b6929/win-avx2-cuda-cu11.7-x64 working fine.
GPU 2x 3090 24GB Win11
I guess same one on the Mac M3.
LLAMA_CPP_PROCESS_ERROR: The model process encountered an unexpected error.
Details:
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.008 sec
ggml_metal_device_init: GPU name: Apple M3 Ultra
ggml_metal_device_init: GPU family: MTLGPUFamilyApple9 (1009)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_device_init: simdgroup reduction = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory = true
ggml_metal_device_init: has bfloat = true
ggml_metal_device_init: use residency sets = true
ggml_metal_device_init: use shared buffers = true
ggml_metal_device_init: recommendedMaxWorkingSetSize = 498216.21 MB
main: setting n_parallel = 4 and kv_unified = true
build: 1 (29ef746) with Apple clang version 14.0.0 (clang-1400.0.29.202) for arm64-apple-darwin21.6.0
system info: n_threads = 24, n_threads_batch = 24, total_threads = 32
system_info: n_threads = 24 (n_threads_batch = 24) / 32 | Metal : EMBED_LIBRARY = 1 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | MATMUL_INT8 = 1 | DOTPROD = 1 | ACCELERATE = 1 | REPACK = 1 |
Web UI is disabled
main: binding port with default address family
main: HTTP server is listening, hostname: 127.0.0.1, port: 3459, http threads: 31
main: loading model
srv load_model: loading model '/Users/me/Library/Application Support/Jan/data/llamacpp/models/Jan-v2-VL-high/model.gguf'
llama_model_load_from_file_impl: using device Metal (Apple M3 Ultra) (unknown id) - 475135 MiB free
llama_model_loader: loaded meta data with 30 key-value pairs and 399 tensors from /Users/me/Library/Application Support/Jan/data/llamacpp/models/Jan-v2-VL-high/model.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 = qwen3vl
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Jan-v2-VL-high
llama_model_loader: - kv 3: general.version str = 10
llama_model_loader: - kv 4: general.basename str = checkpoint
llama_model_loader: - kv 5: general.size_label str = 8.2B
llama_model_loader: - kv 6: qwen3vl.block_count u32 = 36
llama_model_loader: - kv 7: qwen3vl.context_length u32 = 262144
llama_model_loader: - kv 8: qwen3vl.embedding_length u32 = 4096
llama_model_loader: - kv 9: qwen3vl.feed_forward_length u32 = 12288
llama_model_loader: - kv 10: qwen3vl.attention.head_count u32 = 32
llama_model_loader: - kv 11: qwen3vl.attention.head_count_kv u32 = 8
llama_model_loader: - kv 12: qwen3vl.rope.freq_base f32 = 5000000.000000
llama_model_loader: - kv 13: qwen3vl.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 14: qwen3vl.attention.key_length u32 = 128
llama_model_loader: - kv 15: qwen3vl.attention.value_length u32 = 128
llama_model_loader: - kv 16: general.file_type u32 = 32
llama_model_loader: - kv 17: qwen3vl.rope.dimension_sections arr[i32,4] = [24, 20, 20, 0]
llama_model_loader: - kv 18: qwen3vl.n_deepstack_layers u32 = 3
llama_model_loader: - kv 19: general.quantization_version u32 = 2
llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 21: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 25: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 26: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 27: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 28: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 29: tokenizer.chat_template str = {%- set image_count = namespace(value...
llama_model_loader: - type f32: 145 tensors
llama_model_loader: - type bf16: 254 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = BF16
print_info: file size = 15.26 GiB (16.00 BPW)
load: printing all EOG tokens:
load: - 151643 ('<|endoftext|>')
load: - 151645 ('<|im_end|>')
load: - 151662 ('<|fim_pad|>')
load: - 151663 ('<|repo_name|>')
load: - 151664 ('<|file_sep|>')
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen3vl
print_info: vocab_only = 0
print_info: n_ctx_train = 262144
print_info: n_embd = 16384
print_info: n_layer = 36
print_info: n_head = 32
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 4
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 = 0.0e+00
print_info: n_ff = 12288
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: n_expert_groups = 0
print_info: n_group_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 40
print_info: rope scaling = linear
print_info: freq_base_train = 5000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 262144
print_info: rope_finetuned = unknown
print_info: mrope sections = [24, 20, 20, 0]
print_info: model type = 8B
print_info: model params = 8.19 B
print_info: general.name = Jan-v2-VL-high
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 36 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 37/37 layers to GPU
load_tensors: CPU_Mapped model buffer size = 1187.00 MiB
load_tensors: Metal_Mapped model buffer size = 15623.18 MiB
.......................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 4
llama_context: n_ctx = 8192
llama_context: n_ctx_seq = 8192
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = auto
llama_context: kv_unified = true
llama_context: freq_base = 5000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_seq (8192) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M3 Ultra
ggml_metal_init: picking default device: Apple M3 Ultra
ggml_metal_init: use bfloat = true
ggml_metal_init: use fusion = true
ggml_metal_init: use concurrency = true
ggml_metal_init: use graph optimize = true
llama_context: CPU output buffer size = 2.32 MiB
llama_kv_cache: Metal KV buffer size = 1152.00 MiB
llama_kv_cache: size = 1152.00 MiB ( 8192 cells, 36 layers, 4/1 seqs), K (f16): 576.00 MiB, V (f16): 576.00 MiB
llama_context: Flash Attention was auto, set to enabled
llama_context: Metal compute buffer size = 304.75 MiB
llama_context: CPU compute buffer size = 24.02 MiB
llama_context: graph nodes = 1267
llama_context: graph splits = 2
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 8192
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
ggml_metal_library_compile_pipeline: error: failed to compile pipeline: base = 'kernel_mul_mv_bf16_f32_4', name = 'kernel_mul_mv_bf16_f32_4_nsg=4'
ggml_metal_library_compile_pipeline: error: Error Domain=MTLLibraryErrorDomain Code=5 "Function kernel_mul_mv_bf16_f32_4 was not found in the library" UserInfo={NSLocalizedDescription=Function kernel_mul_mv_bf16_f32_4 was not found in the library}
ggml_metal_library_compile_pipeline: error: failed to compile pipeline: base = 'kernel_mul_mv_bf16_f32_4', name = 'kernel_mul_mv_bf16_f32_4_nsg=4'
Sounds like llama.cpp. Metal kernel compile failed.
