Eval bug: validateNewFunctionWithConstantArguments:305: failed assertion constantValues must not be nil.' #16564
Description
Name and Version
Using xcframework for iOS version b6750.
Operating systems
Other? (Please let us know in description)
GGML backends
Metal
Hardware
iPhone 14 Pro - iOS 26
Models
https://huggingface.co/unsloth/Qwen3-1.7B-GGUF
Problem description & steps to reproduce
The model loads correctly, but on first message sends, the app crashes. This also only happens when a debugger is running, but this wasn't always happening.
First Bad Commit
What I've changed since it last worked:
Startup now calls ggml_backend_load_all() before llama_backend_init() so every compiled backend (CPU, Metal, etc.) is registered automatically. Previously only llama_backend_init() ran.
Added Metal safe-mode infrastructure: helper noema_set_metal_safe_mode_env, retry loop over GPU/safe-mode combinations, richer logging, MoE override preparation, CPU-device null checks, and the ability to detect and auto-fallback to CPU when Metal fails. Metal safe mode defaults can be overridden via NOEMA_LLAMA_METAL_SAFE_MODE.
Expanded initializer logic to auto-locate bundled default.metallib, respect projector paths, clamp context lengths, warn on KV cache types, enforce per-sequence context minimums, and probe vision/projector support.
Introduced additional includes (cstdio, climits) and new fields (e.g., _kvOverrides vector).
Added MoE override parsing (LLAMA_MOE_EXPERTS env var) and optional GGML/MoE telemetry.
Relevant log output
[LlamaRunner] Enabling Metal safe mode (shared buffers/fusion/concurrency/residency disabled)
[LlamaRunner] Warning: default.metallib not found in bundle. Falling back to CPU if needed.
[Progress] startLoading format=gguf phase=initializing
llama_model_load_from_file_impl: using device Metal (Apple A16 GPU) (unknown id) - 4095 MiB free
[GGUFScanner] app_available_memory: 4226759544 bytes
[GGUFScanner] app_available_memory: 4222958456 bytes
llama_model_loader: loaded meta data with 32 key-value pairs and 310 tensors from /var/mobile/Containers/Data/Application/6458BBF1-3765-4209-8B01-9E5C009F9B70/Documents/LocalLLMModels/unsloth/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q3_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 = qwen3
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen3-1.7B
llama_model_loader: - kv 3: general.basename str = Qwen3-1.7B
llama_model_loader: - kv 4: general.quantized_by str = Unsloth
llama_model_loader: - kv 5: general.size_label str = 1.7B
llama_model_loader: - kv 6: general.repo_url str = https://huggingface.co/unsloth
[Progress] load animation finished progress=1.0
llama_model_loader: - kv 7: qwen3.block_count u32 = 28
llama_model_loader: - kv 8: qwen3.context_length u32 = 40960
llama_model_loader: - kv 9: qwen3.embedding_length u32 = 2048
llama_model_loader: - kv 10: qwen3.feed_forward_length u32 = 6144
llama_model_loader: - kv 11: qwen3.attention.head_count u32 = 16
llama_model_loader: - kv 12: qwen3.attention.head_count_kv u32 = 8
llama_model_loader: - kv 13: qwen3.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 14: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 15: qwen3.attention.key_length u32 = 128
llama_model_loader: - kv 16: qwen3.attention.value_length u32 = 128
llama_model_loader: - kv 17: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 18: tokenizer.ggml.pre str = qwen2
[GGUFScanner] app_available_memory: 4218616672 bytes
llama_model_loader: - kv 19: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 151654
llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 25: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 26: general.quantization_version u32 = 2
llama_model_loader: - kv 27: general.file_type u32 = 12
llama_model_loader: - kv 28: quantize.imatrix.file str = Qwen3-1.7B-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv 29: quantize.imatrix.dataset str = unsloth_calibration_Qwen3-1.7B.txt
llama_model_loader: - kv 30: quantize.imatrix.entries_count i32 = 196
llama_model_loader: - kv 31: quantize.imatrix.chunks_count i32 = 685
llama_model_loader: - type f32: 113 tensors
llama_model_loader: - type q3_K: 112 tensors
llama_model_loader: - type q4_K: 81 tensors
llama_model_loader: - type q5_K: 3 tensors
llama_model_loader: - type q6_K: 1 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q3_K - Medium
print_info: file size = 890.34 MiB (4.34 BPW)
init_tokenizer: initializing tokenizer for type 2
load: control token: 151659 '<|fim_prefix|>' is not marked as EOG
load: control token: 151656 '<|video_pad|>' is not marked as EOG
load: control token: 151655 '<|image_pad|>' is not marked as EOG
load: control token: 151653 '<|vision_end|>' is not marked as EOG
load: control token: 151652 '<|vision_start|>' is not marked as EOG
load: control token: 151651 '<|quad_end|>' is not marked as EOG
load: control token: 151649 '<|box_end|>' is not marked as EOG
load: control token: 151648 '<|box_start|>' is not marked as EOG
load: control token: 151646 '<|object_ref_start|>' is not marked as EOG
load: control token: 151644 '<|im_start|>' is not marked as EOG
load: control token: 151661 '<|fim_suffix|>' is not marked as EOG
load: control token: 151647 '<|object_ref_end|>' is not marked as EOG
load: control token: 151660 '<|fim_middle|>' is not marked as EOG
load: control token: 151654 '<|vision_pad|>' is not marked as EOG
load: control token: 151650 '<|quad_start|>' is not marked as EOG
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 = qwen3
print_info: vocab_only = 0
print_info: n_ctx_train = 40960
print_info: n_embd = 2048
print_info: n_layer = 28
print_info: n_head = 16
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 = 2
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 = 6144
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = -1
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 = 40960
print_info: rope_finetuned = unknown
print_info: model type = 1.7B
print_info: model params = 1.72 B
print_info: general.name = Qwen3-1.7B
print_info: vocab type = BPE
print_info: n_vocab = 151936
print_info: n_merges = 151387
print_info: BOS token = 11 ','
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151654 '<|vision_pad|>'
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: layer 0 assigned to device Metal, is_swa = 0
load_tensors: layer 1 assigned to device Metal, is_swa = 0
load_tensors: layer 2 assigned to device Metal, is_swa = 0
load_tensors: layer 3 assigned to device Metal, is_swa = 0
load_tensors: layer 4 assigned to device Metal, is_swa = 0
load_tensors: layer 5 assigned to device Metal, is_swa = 0
load_tensors: layer 6 assigned to device Metal, is_swa = 0
load_tensors: layer 7 assigned to device Metal, is_swa = 0
load_tensors: layer 8 assigned to device Metal, is_swa = 0
load_tensors: layer 9 assigned to device Metal, is_swa = 0
load_tensors: layer 10 assigned to device Metal, is_swa = 0
load_tensors: layer 11 assigned to device Metal, is_swa = 0
load_tensors: layer 12 assigned to device Metal, is_swa = 0
load_tensors: layer 13 assigned to device Metal, is_swa = 0
load_tensors: layer 14 assigned to device Metal, is_swa = 0
load_tensors: layer 15 assigned to device Metal, is_swa = 0
load_tensors: layer 16 assigned to device Metal, is_swa = 0
load_tensors: layer 17 assigned to device Metal, is_swa = 0
load_tensors: layer 18 assigned to device Metal, is_swa = 0
load_tensors: layer 19 assigned to device Metal, is_swa = 0
load_tensors: layer 20 assigned to device Metal, is_swa = 0
load_tensors: layer 21 assigned to device Metal, is_swa = 0
load_tensors: layer 22 assigned to device Metal, is_swa = 0
load_tensors: layer 23 assigned to device Metal, is_swa = 0
load_tensors: layer 24 assigned to device Metal, is_swa = 0
load_tensors: layer 25 assigned to device Metal, is_swa = 0
load_tensors: layer 26 assigned to device Metal, is_swa = 0
load_tensors: layer 27 assigned to device Metal, is_swa = 0
load_tensors: layer 28 assigned to device Metal, is_swa = 0
create_tensor: loading tensor token_embd.weight
create_tensor: loading tensor output_norm.weight
create_tensor: loading tensor token_embd.weight
create_tensor: loading tensor blk.0.attn_norm.weight
create_tensor: loading tensor blk.0.attn_q.weight
create_tensor: loading tensor blk.0.attn_k.weight
create_tensor: loading tensor blk.0.attn_v.weight
create_tensor: loading tensor blk.0.attn_output.weight
create_tensor: loading tensor blk.0.attn_k_norm.weight
create_tensor: loading tensor blk.0.attn_q_norm.weight
create_tensor: loading tensor blk.0.ffn_norm.weight
create_tensor: loading tensor blk.0.ffn_gate.weight
create_tensor: loading tensor blk.0.ffn_down.weight
create_tensor: loading tensor blk.0.ffn_up.weight
create_tensor: loading tensor blk.1.attn_norm.weight
create_tensor: loading tensor blk.1.attn_q.weight
create_tensor: loading tensor blk.1.attn_k.weight
create_tensor: loading tensor blk.1.attn_v.weight
create_tensor: loading tensor blk.1.attn_output.weight
create_tensor: loading tensor blk.1.attn_k_norm.weight
create_tensor: loading tensor blk.1.attn_q_norm.weight
create_tensor: loading tensor blk.1.ffn_norm.weight
create_tensor: loading tensor blk.1.ffn_gate.weight
create_tensor: loading tensor blk.1.ffn_down.weight
create_tensor: loading tensor blk.1.ffn_up.weight
create_tensor: loading tensor blk.2.attn_norm.weight
create_tensor: loading tensor blk.2.attn_q.weight
create_tensor: loading tensor blk.2.attn_k.weight
create_tensor: loading tensor blk.2.attn_v.weight
create_tensor: loading tensor blk.2.attn_output.weight
create_tensor: loading tensor blk.2.attn_k_norm.weight
create_tensor: loading tensor blk.2.attn_q_norm.weight
create_tensor: loading tensor blk.2.ffn_norm.weight
create_tensor: loading tensor blk.2.ffn_gate.weight
create_tensor: loading tensor blk.2.ffn_down.weight
create_tensor: loading tensor blk.2.ffn_up.weight
create_tensor: loading tensor blk.3.attn_norm.weight
create_tensor: loading tensor blk.3.attn_q.weight
create_tensor: loading tensor blk.3.attn_k.weight
create_tensor: loading tensor blk.3.attn_v.weight
create_tensor: loading tensor blk.3.attn_output.weight
create_tensor: loading tensor blk.3.attn_k_norm.weight
create_tensor: loading tensor blk.3.attn_q_norm.weight
create_tensor: loading tensor blk.3.ffn_norm.weight
create_tensor: loading tensor blk.3.ffn_gate.weight
create_tensor: loading tensor blk.3.ffn_down.weight
create_tensor: loading tensor blk.3.ffn_up.weight
create_tensor: loading tensor blk.4.attn_norm.weight
create_tensor: loading tensor blk.4.attn_q.weight
create_tensor: loading tensor blk.4.attn_k.weight
create_tensor: loading tensor blk.4.attn_v.weight
create_tensor: loading tensor blk.4.attn_output.weight
create_tensor: loading tensor blk.4.attn_k_norm.weight
create_tensor: loading tensor blk.4.attn_q_norm.weight
create_tensor: loading tensor blk.4.ffn_norm.weight
create_tensor: loading tensor blk.4.ffn_gate.weight
create_tensor: loading tensor blk.4.ffn_down.weight
create_tensor: loading tensor blk.4.ffn_up.weight
create_tensor: loading tensor blk.5.attn_norm.weight
create_tensor: loading tensor blk.5.attn_q.weight
create_tensor: loading tensor blk.5.attn_k.weight
create_tensor: loading tensor blk.5.attn_v.weight
create_tensor: loading tensor blk.5.attn_output.weight
create_tensor: loading tensor blk.5.attn_k_norm.weight
create_tensor: loading tensor blk.5.attn_q_norm.weight
create_tensor: loading tensor blk.5.ffn_norm.weight
create_tensor: loading tensor blk.5.ffn_gate.weight
create_tensor: loading tensor blk.5.ffn_down.weight
create_tensor: loading tensor blk.5.ffn_up.weight
create_tensor: loading tensor blk.6.attn_norm.weight
create_tensor: loading tensor blk.6.attn_q.weight
create_tensor: loading tensor blk.6.attn_k.weight
create_tensor: loading tensor blk.6.attn_v.weight
create_tensor: loading tensor blk.6.attn_output.weight
create_tensor: loading tensor blk.6.attn_k_norm.weight
create_tensor: loading tensor blk.6.attn_q_norm.weight
create_tensor: loading tensor blk.6.ffn_norm.weight
create_tensor: loading tensor blk.6.ffn_gate.weight
create_tensor: loading tensor blk.6.ffn_down.weight
create_tensor: loading tensor blk.6.ffn_up.weight
create_tensor: loading tensor blk.7.attn_norm.weight
create_tensor: loading tensor blk.7.attn_q.weight
create_tensor: loading tensor blk.7.attn_k.weight
create_tensor: loading tensor blk.7.attn_v.weight
create_tensor: loading tensor blk.7.attn_output.weight
create_tensor: loading tensor blk.7.attn_k_norm.weight
create_tensor: loading tensor blk.7.attn_q_norm.weight
create_tensor: loading tensor blk.7.ffn_norm.weight
create_tensor: loading tensor blk.7.ffn_gate.weight
create_tensor: loading tensor blk.7.ffn_down.weight
create_tensor: loading tensor blk.7.ffn_up.weight
create_tensor: loading tensor blk.8.attn_norm.weight
create_tensor: loading tensor blk.8.attn_q.weight
create_tensor: loading tensor blk.8.attn_k.weight
create_tensor: loading tensor blk.8.attn_v.weight
create_tensor: loading tensor blk.8.attn_output.weight
create_tensor: loading tensor blk.8.attn_k_norm.weight
create_tensor: loading tensor blk.8.attn_q_norm.weight
create_tensor: loading tensor blk.8.ffn_norm.weight
create_tensor: loading tensor blk.8.ffn_gate.weight
create_tensor: loading tensor blk.8.ffn_down.weight
create_tensor: loading tensor blk.8.ffn_up.weight
create_tensor: loading tensor blk.9.attn_norm.weight
create_tensor: loading tensor blk.9.attn_q.weight
create_tensor: loading tensor blk.9.attn_k.weight
create_tensor: loading tensor blk.9.attn_v.weight
create_tensor: loading tensor blk.9.attn_output.weight
create_tensor: loading tensor blk.9.attn_k_norm.weight
create_tensor: loading tensor blk.9.attn_q_norm.weight
create_tensor: loading tensor blk.9.ffn_norm.weight
create_tensor: loading tensor blk.9.ffn_gate.weight
create_tensor: loading tensor blk.9.ffn_down.weight
create_tensor: loading tensor blk.9.ffn_up.weight
create_tensor: loading tensor blk.10.attn_norm.weight
create_tensor: loading tensor blk.10.attn_q.weight
create_tensor: loading tensor blk.10.attn_k.weight
create_tensor: loading tensor blk.10.attn_v.weight
create_tensor: loading tensor blk.10.attn_output.weight
create_tensor: loading tensor blk.10.attn_k_norm.weight
create_tensor: loading tensor blk.10.attn_q_norm.weight
create_tensor: loading tensor blk.10.ffn_norm.weight
create_tensor: loading tensor blk.10.ffn_gate.weight
create_tensor: loading tensor blk.10.ffn_down.weight
create_tensor: loading tensor blk.10.ffn_up.weight
create_tensor: loading tensor blk.11.attn_norm.weight
create_tensor: loading tensor blk.11.attn_q.weight
create_tensor: loading tensor blk.11.attn_k.weight
create_tensor: loading tensor blk.11.attn_v.weight
create_tensor: loading tensor blk.11.attn_output.weight
create_tensor: loading tensor blk.11.attn_k_norm.weight
create_tensor: loading tensor blk.11.attn_q_norm.weight
create_tensor: loading tensor blk.11.ffn_norm.weight
create_tensor: loading tensor blk.11.ffn_gate.weight
create_tensor: loading tensor blk.11.ffn_down.weight
create_tensor: loading tensor blk.11.ffn_up.weight
create_tensor: loading tensor blk.12.attn_norm.weight
create_tensor: loading tensor blk.12.attn_q.weight
create_tensor: loading tensor blk.12.attn_k.weight
create_tensor: loading tensor blk.12.attn_v.weight
create_tensor: loading tensor blk.12.attn_output.weight
create_tensor: loading tensor blk.12.attn_k_norm.weight
create_tensor: loading tensor blk.12.attn_q_norm.weight
create_tensor: loading tensor blk.12.ffn_norm.weight
create_tensor: loading tensor blk.12.ffn_gate.weight
create_tensor: loading tensor blk.12.ffn_down.weight
create_tensor: loading tensor blk.12.ffn_up.weight
create_tensor: loading tensor blk.13.attn_norm.weight
create_tensor: loading tensor blk.13.attn_q.weight
create_tensor: loading tensor blk.13.attn_k.weight
create_tensor: loading tensor blk.13.attn_v.weight
create_tensor: loading tensor blk.13.attn_output.weight
create_tensor: loading tensor blk.13.attn_k_norm.weight
create_tensor: loading tensor blk.13.attn_q_norm.weight
create_tensor: loading tensor blk.13.ffn_norm.weight
create_tensor: loading tensor blk.13.ffn_gate.weight
create_tensor: loading tensor blk.13.ffn_down.weight
create_tensor: loading tensor blk.13.ffn_up.weight
create_tensor: loading tensor blk.14.attn_norm.weight
create_tensor: loading tensor blk.14.attn_q.weight
create_tensor: loading tensor blk.14.attn_k.weight
create_tensor: loading tensor blk.14.attn_v.weight
create_tensor: loading tensor blk.14.attn_output.weight
create_tensor: loading tensor blk.14.attn_k_norm.weight
create_tensor: loading tensor blk.14.attn_q_norm.weight
create_tensor: loading tensor blk.14.ffn_norm.weight
create_tensor: loading tensor blk.14.ffn_gate.weight
create_tensor: loading tensor blk.14.ffn_down.weight
create_tensor: loading tensor blk.14.ffn_up.weight
create_tensor: loading tensor blk.15.attn_norm.weight
create_tensor: loading tensor blk.15.attn_q.weight
create_tensor: loading tensor blk.15.attn_k.weight
create_tensor: loading tensor blk.15.attn_v.weight
create_tensor: loading tensor blk.15.attn_output.weight
create_tensor: loading tensor blk.15.attn_k_norm.weight
create_tensor: loading tensor blk.15.attn_q_norm.weight
create_tensor: loading tensor blk.15.ffn_norm.weight
create_tensor: loading tensor blk.15.ffn_gate.weight
create_tensor: loading tensor blk.15.ffn_down.weight
create_tensor: loading tensor blk.15.ffn_up.weight
create_tensor: loading tensor blk.16.attn_norm.weight
create_tensor: loading tensor blk.16.attn_q.weight
create_tensor: loading tensor blk.16.attn_k.weight
create_tensor: loading tensor blk.16.attn_v.weight
create_tensor: loading tensor blk.16.attn_output.weight
create_tensor: loading tensor blk.16.attn_k_norm.weight
create_tensor: loading tensor blk.16.attn_q_norm.weight
create_tensor: loading tensor blk.16.ffn_norm.weight
create_tensor: loading tensor blk.16.ffn_gate.weight
create_tensor: loading tensor blk.16.ffn_down.weight
create_tensor: loading tensor blk.16.ffn_up.weight
create_tensor: loading tensor blk.17.attn_norm.weight
create_tensor: loading tensor blk.17.attn_q.weight
create_tensor: loading tensor blk.17.attn_k.weight
create_tensor: loading tensor blk.17.attn_v.weight
create_tensor: loading tensor blk.17.attn_output.weight
create_tensor: loading tensor blk.17.attn_k_norm.weight
create_tensor: loading tensor blk.17.attn_q_norm.weight
create_tensor: loading tensor blk.17.ffn_norm.weight
create_tensor: loading tensor blk.17.ffn_gate.weight
create_tensor: loading tensor blk.17.ffn_down.weight
create_tensor: loading tensor blk.17.ffn_up.weight
create_tensor: loading tensor blk.18.attn_norm.weight
create_tensor: loading tensor blk.18.attn_q.weight
create_tensor: loading tensor blk.18.attn_k.weight
create_tensor: loading tensor blk.18.attn_v.weight
create_tensor: loading tensor blk.18.attn_output.weight
create_tensor: loading tensor blk.18.attn_k_norm.weight
create_tensor: loading tensor blk.18.attn_q_norm.weight
create_tensor: loading tensor blk.18.ffn_norm.weight
create_tensor: loading tensor blk.18.ffn_gate.weight
create_tensor: loading tensor blk.18.ffn_down.weight
create_tensor: loading tensor blk.18.ffn_up.weight
create_tensor: loading tensor blk.19.attn_norm.weight
create_tensor: loading tensor blk.19.attn_q.weight
create_tensor: loading tensor blk.19.attn_k.weight
create_tensor: loading tensor blk.19.attn_v.weight
create_tensor: loading tensor blk.19.attn_output.weight
create_tensor: loading tensor blk.19.attn_k_norm.weight
create_tensor: loading tensor blk.19.attn_q_norm.weight
create_tensor: loading tensor blk.19.ffn_norm.weight
create_tensor: loading tensor blk.19.ffn_gate.weight
create_tensor: loading tensor blk.19.ffn_down.weight
create_tensor: loading tensor blk.19.ffn_up.weight
create_tensor: loading tensor blk.20.attn_norm.weight
create_tensor: loading tensor blk.20.attn_q.weight
create_tensor: loading tensor blk.20.attn_k.weight
create_tensor: loading tensor blk.20.attn_v.weight
create_tensor: loading tensor blk.20.attn_output.weight
create_tensor: loading tensor blk.20.attn_k_norm.weight
create_tensor: loading tensor blk.20.attn_q_norm.weight
create_tensor: loading tensor blk.20.ffn_norm.weight
create_tensor: loading tensor blk.20.ffn_gate.weight
create_tensor: loading tensor blk.20.ffn_down.weight
create_tensor: loading tensor blk.20.ffn_up.weight
create_tensor: loading tensor blk.21.attn_norm.weight
create_tensor: loading tensor blk.21.attn_q.weight
create_tensor: loading tensor blk.21.attn_k.weight
create_tensor: loading tensor blk.21.attn_v.weight
create_tensor: loading tensor blk.21.attn_output.weight
create_tensor: loading tensor blk.21.attn_k_norm.weight
create_tensor: loading tensor blk.21.attn_q_norm.weight
create_tensor: loading tensor blk.21.ffn_norm.weight
create_tensor: loading tensor blk.21.ffn_gate.weight
create_tensor: loading tensor blk.21.ffn_down.weight
create_tensor: loading tensor blk.21.ffn_up.weight
create_tensor: loading tensor blk.22.attn_norm.weight
create_tensor: loading tensor blk.22.attn_q.weight
create_tensor: loading tensor blk.22.attn_k.weight
create_tensor: loading tensor blk.22.attn_v.weight
create_tensor: loading tensor blk.22.attn_output.weight
create_tensor: loading tensor blk.22.attn_k_norm.weight
create_tensor: loading tensor blk.22.attn_q_norm.weight
create_tensor: loading tensor blk.22.ffn_norm.weight
create_tensor: loading tensor blk.22.ffn_gate.weight
create_tensor: loading tensor blk.22.ffn_down.weight
create_tensor: loading tensor blk.22.ffn_up.weight
create_tensor: loading tensor blk.23.attn_norm.weight
create_tensor: loading tensor blk.23.attn_q.weight
create_tensor: loading tensor blk.23.attn_k.weight
create_tensor: loading tensor blk.23.attn_v.weight
create_tensor: loading tensor blk.23.attn_output.weight
create_tensor: loading tensor blk.23.attn_k_norm.weight
create_tensor: loading tensor blk.23.attn_q_norm.weight
create_tensor: loading tensor blk.23.ffn_norm.weight
create_tensor: loading tensor blk.23.ffn_gate.weight
create_tensor: loading tensor blk.23.ffn_down.weight
create_tensor: loading tensor blk.23.ffn_up.weight
create_tensor: loading tensor blk.24.attn_norm.weight
create_tensor: loading tensor blk.24.attn_q.weight
create_tensor: loading tensor blk.24.attn_k.weight
create_tensor: loading tensor blk.24.attn_v.weight
create_tensor: loading tensor blk.24.attn_output.weight
create_tensor: loading tensor blk.24.attn_k_norm.weight
create_tensor: loading tensor blk.24.attn_q_norm.weight
create_tensor: loading tensor blk.24.ffn_norm.weight
create_tensor: loading tensor blk.24.ffn_gate.weight
create_tensor: loading tensor blk.24.ffn_down.weight
create_tensor: loading tensor blk.24.ffn_up.weight
create_tensor: loading tensor blk.25.attn_norm.weight
create_tensor: loading tensor blk.25.attn_q.weight
create_tensor: loading tensor blk.25.attn_k.weight
create_tensor: loading tensor blk.25.attn_v.weight
create_tensor: loading tensor blk.25.attn_output.weight
create_tensor: loading tensor blk.25.attn_k_norm.weight
create_tensor: loading tensor blk.25.attn_q_norm.weight
create_tensor: loading tensor blk.25.ffn_norm.weight
create_tensor: loading tensor blk.25.ffn_gate.weight
create_tensor: loading tensor blk.25.ffn_down.weight
create_tensor: loading tensor blk.25.ffn_up.weight
create_tensor: loading tensor blk.26.attn_norm.weight
create_tensor: loading tensor blk.26.attn_q.weight
create_tensor: loading tensor blk.26.attn_k.weight
create_tensor: loading tensor blk.26.attn_v.weight
create_tensor: loading tensor blk.26.attn_output.weight
create_tensor: loading tensor blk.26.attn_k_norm.weight
create_tensor: loading tensor blk.26.attn_q_norm.weight
create_tensor: loading tensor blk.26.ffn_norm.weight
create_tensor: loading tensor blk.26.ffn_gate.weight
create_tensor: loading tensor blk.26.ffn_down.weight
create_tensor: loading tensor blk.26.ffn_up.weight
create_tensor: loading tensor blk.27.attn_norm.weight
create_tensor: loading tensor blk.27.attn_q.weight
create_tensor: loading tensor blk.27.attn_k.weight
create_tensor: loading tensor blk.27.attn_v.weight
create_tensor: loading tensor blk.27.attn_output.weight
create_tensor: loading tensor blk.27.attn_k_norm.weight
create_tensor: loading tensor blk.27.attn_q_norm.weight
create_tensor: loading tensor blk.27.ffn_norm.weight
create_tensor: loading tensor blk.27.ffn_gate.weight
create_tensor: loading tensor blk.27.ffn_down.weight
create_tensor: loading tensor blk.27.ffn_up.weight
load_tensors: tensor 'token_embd.weight' (q6_K) (and 0 others) cannot be used with preferred buffer type CPU_REPACK, using CPU instead
ggml_backend_metal_log_allocated_size: allocated buffer, size = 890.34 MiB, ( 890.72 / 4096.02)
load_tensors: offloading 28 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 29/29 layers to GPU
load_tensors: Metal_Mapped model buffer size = 890.34 MiB
load_tensors: CPU_Mapped model buffer size = 243.43 MiB
...........................................................
[LlamaRunner] Metal initialized with safe mode toggles enabled.
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 8192
llama_context: n_ctx_per_seq = 8192
llama_context: n_batch = 512
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = auto
llama_context: kv_unified = false
llama_context: freq_base = 1000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (8192) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
ggml_metal_init: allocating
ggml_metal_init: picking default device: Apple A16 GPU
ggml_metal_load_library: using embedded metal library
ggml_metal_load_library: loaded in 0.031 sec
ggml_metal_init: GPU name: Apple A16 GPU
ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal4 (5002)
ggml_metal_init: simdgroup reduction = true
ggml_metal_init: simdgroup matrix mul. = true
ggml_metal_init: has residency sets = false
ggml_metal_init: has bfloat = true
ggml_metal_init: use bfloat = false
ggml_metal_init: use fusion = false
ggml_metal_init: use concurrency = false
ggml_metal_init: use shared buffers = false
ggml_metal_init: use graph optimize = true
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 4294.98 MB
ggml_metal_init: loaded kernels
set_abort_callback: call
llama_context: CPU output buffer size = 0.58 MiB
create_memory: n_ctx = 8192 (padded)
llama_kv_cache: layer 0: dev = Metal
llama_kv_cache: layer 1: dev = Metal
llama_kv_cache: layer 2: dev = Metal
llama_kv_cache: layer 3: dev = Metal
llama_kv_cache: layer 4: dev = Metal
llama_kv_cache: layer 5: dev = Metal
llama_kv_cache: layer 6: dev = Metal
llama_kv_cache: layer 7: dev = Metal
llama_kv_cache: layer 8: dev = Metal
llama_kv_cache: layer 9: dev = Metal
llama_kv_cache: layer 10: dev = Metal
llama_kv_cache: layer 11: dev = Metal
llama_kv_cache: layer 12: dev = Metal
llama_kv_cache: layer 13: dev = Metal
llama_kv_cache: layer 14: dev = Metal
llama_kv_cache: layer 15: dev = Metal
llama_kv_cache: layer 16: dev = Metal
llama_kv_cache: layer 17: dev = Metal
llama_kv_cache: layer 18: dev = Metal
llama_kv_cache: layer 19: dev = Metal
llama_kv_cache: layer 20: dev = Metal
llama_kv_cache: layer 21: dev = Metal
llama_kv_cache: layer 22: dev = Metal
llama_kv_cache: layer 23: dev = Metal
llama_kv_cache: layer 24: dev = Metal
llama_kv_cache: layer 25: dev = Metal
llama_kv_cache: layer 26: dev = Metal
llama_kv_cache: layer 27: dev = Metal
llama_kv_cache: Metal_Private KV buffer size = 896.00 MiB
llama_kv_cache: size = 896.00 MiB ( 8192 cells, 28 layers, 1/1 seqs), K (f16): 448.00 MiB, V (f16): 448.00 MiB
llama_context: enumerating backends
llama_context: backend_ptrs.size() = 3
llama_context: max_nodes = 2488
llama_context: reserving full memory module
llama_context: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 1
graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1
llama_context: Flash Attention was auto, set to enabled
graph_reserve: reserving a graph for ubatch with n_tokens = 512, n_seqs = 1, n_outputs = 512
graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1
graph_reserve: reserving a graph for ubatch with n_tokens = 512, n_seqs = 1, n_outputs = 512
llama_context: Metal_Private compute buffer size = 304.75 MiB
llama_context: CPU compute buffer size = 20.01 MiB
llama_context: graph nodes = 987
llama_context: graph splits = 2
set_n_threads: n_threads = 6, n_threads_batch = 6
[LlamaRunner] Context ready. n_ctx=8192, n_seq_max=1, n_gpu_layers=1000000
On first message:
ggml_metal_compile_kernel: compiling kernel: base = 'kernel_rms_norm_mul', name = 'kernel_rms_norm_mul'
validateNewFunctionWithConstantArguments:305: failed assertion `constantValues must not be nil.'
validateNewFunctionWithConstantArguments:305: failed assertion `constantValues must not be nil.'