Misc. bug: [Mac M4]llama-server cannot run in release-4409 but can run in 4406

[bobleer]

Name and Version

llama-b4409-bin-macos-arm64.zip
llama-b4406-bin-macos-arm64.zip

Operating systems

Mac

Which llama.cpp modules do you know to be affected?

llama-server

Problem description & steps to reproduce

4409 run log:

/Users/liwenbo/Downloads/4409-llamacpp/bin/llama-server -m /Users/liwenbo/models/qwen/Qwen2.5-1.5B-Instruct.Q4_K_M.gguf
dyld[18622]: Library not loaded: @rpath/libllama.dylib
  Referenced from: <A6F705D2-0AC3-32BD-8CF2-3A55262E9195> /Users/liwenbo/Downloads/4409-llamacpp/bin/llama-server
  Reason: tried: '/Users/runner/work/llama.cpp/llama.cpp/build/src/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/src/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-blas/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-blas/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-metal/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-metal/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-rpc/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-rpc/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/src/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/src/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-blas/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-blas/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-metal/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-metal/libllama.dylib' (no such file), '/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-rpc/libllama.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Users/runner/work/llama.cpp/llama.cpp/build/ggml/src/ggml-rpc/libllama.dylib' (no such file)
zsh: abort      /Users/liwenbo/Downloads/4409-llamacpp/bin/llama-server -m 

4406 run log:

/Users/liwenbo/Downloads/4406-llamacpp/bin/llama-server -m /Users/liwenbo/models/qwen/Qwen2.5-1.5B-Instruct.Q4_K_M.gguf
build: 4406 (0da5d860) with Apple clang version 15.0.0 (clang-1500.3.9.4) for arm64-apple-darwin23.6.0
system info: n_threads = 4, n_threads_batch = 4, total_threads = 10

system_info: n_threads = 4 (n_threads_batch = 4) / 10 | Metal : EMBED_LIBRARY = 1 | BF16 = 1 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | DOTPROD = 1 | LLAMAFILE = 1 | ACCELERATE = 1 | AARCH64_REPACK = 1 | 

main: HTTP server is listening, hostname: 127.0.0.1, port: 8080, http threads: 9
main: loading model
srv    load_model: loading model '/Users/liwenbo/models/qwen/Qwen2.5-1.5B-Instruct.Q4_K_M.gguf'
llama_load_model_from_file: using device Metal (Apple M4) - 10922 MiB free
llama_model_loader: loaded meta data with 32 key-value pairs and 338 tensors from /Users/liwenbo/models/qwen/Qwen2.5-1.5B-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              = qwen2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Models
llama_model_loader: - kv   3:                         general.size_label str              = 1.5B
llama_model_loader: - kv   4:                            general.license str              = apache-2.0
llama_model_loader: - kv   5:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-1...
llama_model_loader: - kv   6:                   general.base_model.count u32              = 1
llama_model_loader: - kv   7:                  general.base_model.0.name str              = Qwen2.5 1.5B
llama_model_loader: - kv   8:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv   9:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-1.5B
llama_model_loader: - kv  10:                               general.tags arr[str,2]       = ["chat", "text-generation"]
llama_model_loader: - kv  11:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  12:                          qwen2.block_count u32              = 28
llama_model_loader: - kv  13:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  14:                     qwen2.embedding_length u32              = 1536
llama_model_loader: - kv  15:                  qwen2.feed_forward_length u32              = 8960
llama_model_loader: - kv  16:                 qwen2.attention.head_count u32              = 12
llama_model_loader: - kv  17:              qwen2.attention.head_count_kv u32              = 2
llama_model_loader: - kv  18:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  19:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  20:                          general.file_type u32              = 15
llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  26:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  27:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  29:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  30:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  31:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  141 tensors
llama_model_loader: - type q4_K:  168 tensors
llama_model_loader: - type q6_K:   29 tensors
llm_load_vocab: special tokens cache size = 22
llm_load_vocab: token to piece cache size = 0.9310 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          = 151936
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           = 1536
llm_load_print_meta: n_layer          = 28
llm_load_print_meta: n_head           = 12
llm_load_print_meta: n_head_kv        = 2
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            = 6
llm_load_print_meta: n_embd_k_gqa     = 256
llm_load_print_meta: n_embd_v_gqa     = 256
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             = 8960
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       = 1.5B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 1.54 B
llm_load_print_meta: model size       = 934.69 MiB (5.08 BPW) 
llm_load_print_meta: general.name     = Models
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: FIM PRE token    = 151659 '<|fim_prefix|>'
llm_load_print_meta: FIM SUF token    = 151661 '<|fim_suffix|>'
llm_load_print_meta: FIM MID token    = 151660 '<|fim_middle|>'
llm_load_print_meta: FIM PAD token    = 151662 '<|fim_pad|>'
llm_load_print_meta: FIM REP token    = 151663 '<|repo_name|>'
llm_load_print_meta: FIM SEP token    = 151664 '<|file_sep|>'
llm_load_print_meta: EOG token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token        = 151645 '<|im_end|>'
llm_load_print_meta: EOG token        = 151662 '<|fim_pad|>'
llm_load_print_meta: EOG token        = 151663 '<|repo_name|>'
llm_load_print_meta: EOG token        = 151664 '<|file_sep|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: offloading 28 repeating layers to GPU
llm_load_tensors: offloading output layer to GPU
llm_load_tensors: offloaded 29/29 layers to GPU
llm_load_tensors: Metal_Mapped model buffer size =   934.70 MiB
llm_load_tensors:   CPU_Mapped model buffer size =   182.57 MiB
.....................................................................
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 M4
ggml_metal_init: picking default device: Apple M4
ggml_metal_init: using embedded metal library
ggml_metal_init: GPU name:   Apple M4
ggml_metal_init: GPU family: MTLGPUFamilyApple9  (1009)
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            = true
ggml_metal_init: hasUnifiedMemory      = true
ggml_metal_init: recommendedMaxWorkingSetSize  = 11453.25 MB
llama_kv_cache_init: kv_size = 4096, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 28
llama_kv_cache_init:      Metal KV buffer size =   112.00 MiB
llama_new_context_with_model: KV self size  =  112.00 MiB, K (f16):   56.00 MiB, V (f16):   56.00 MiB
llama_new_context_with_model:        CPU  output buffer size =     0.58 MiB
llama_new_context_with_model:      Metal compute buffer size =   299.75 MiB
llama_new_context_with_model:        CPU compute buffer size =    11.01 MiB
llama_new_context_with_model: graph nodes  = 986
llama_new_context_with_model: graph splits = 2
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
srv          init: initializing slots, n_slots = 1
slot         init: id  0 | task -1 | new slot n_ctx_slot = 4096
main: model loaded
main: chat template, chat_template: (built-in), example_format: '<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Hello<|im_end|>
<|im_start|>assistant
Hi there<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
'
main: server is listening on http://127.0.0.1:8080 - starting the main loop
srv  update_slots: all slots are idle
^C

First Bad Commit

No response

Relevant log output

No response