Closed
Description
Name and Version
llama-eval-callback
version: 5770 (b25e927)
Operating systems
Mac
GGML backends
Metal
Hardware
m3 processor
Models
Llama 3 8b instruct, 16 fp, https://huggingface.co/ByteResearch/Llama-3-8B-Instruct then used the hf -> gguf script to get gguf
Problem description & steps to reproduce
./build/bin/llama-eval-callback -m ./models/llama.gguf
First Bad Commit
No response
Relevant log output
build: 5770 (b25e9277) with Apple clang version 17.0.0 (clang-1700.0.13.5) for arm64-apple-darwin24.5.0
llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free
Arch name: llama
llama_model_loader: loaded meta data with 31 key-value pairs and 291 tensors from ./models/lama.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.type str = model
llama_model_loader: - kv 2: general.name str = F59E729Ac709F2Fa41383C7Aa29276538D20Cc37
llama_model_loader: - kv 3: general.size_label str = 8.0B
llama_model_loader: - kv 4: general.license str = other
llama_model_loader: - kv 5: general.license.name str = llama3
llama_model_loader: - kv 6: general.license.link str = LICENSE
llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv 8: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 9: llama.block_count u32 = 32
llama_model_loader: - kv 10: llama.context_length u32 = 8192
llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 17: llama.attention.key_length u32 = 128
llama_model_loader: - kv 18: llama.attention.value_length u32 = 128
llama_model_loader: - kv 19: general.file_type u32 = 1
llama_model_loader: - kv 20: llama.vocab_size u32 = 128256
llama_model_loader: - kv 21: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 22: general.quantization_version u32 = 2
llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 24: tokenizer.ggml.pre str = smaug-bpe
llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 128001
llama_model_loader: - kv 30: tokenizer.chat_template str = {% set loop_messages = messages %}{% ...
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type f16: 226 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = F16
print_info: file size = 14.96 GiB (16.00 BPW)
name: general.architecture, value: llama
name: general.type, value: model
name: general.name, value: F59E729Ac709F2Fa41383C7Aa29276538D20Cc37
name: general.size_label, value: 8.0B
name: general.license, value: other
name: general.license.name, value: llama3
name: general.license.link, value: LICENSE
name: llama.block_count, value: 32
name: llama.context_length, value: 8192
name: llama.embedding_length, value: 4096
name: llama.feed_forward_length, value: 14336
name: llama.attention.head_count, value: 32
name: llama.attention.head_count_kv, value: 8
name: llama.rope.freq_base, value: 500000.000000
name: llama.attention.layer_norm_rms_epsilon, value: 0.000010
name: llama.attention.key_length, value: 128
name: llama.attention.value_length, value: 128
name: general.file_type, value: 1
name: llama.vocab_size, value: 128256
name: llama.rope.dimension_count, value: 128
name: general.quantization_version, value: 2
name: tokenizer.ggml.model, value: gpt2
name: tokenizer.ggml.pre, value: smaug-bpe
name: tokenizer.ggml.bos_token_id, value: 128000
name: tokenizer.ggml.eos_token_id, value: 128001
name: tokenizer.chat_template, value: {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>
' }}
load: special tokens cache size = 256
load: token to piece cache size = 0.8000 MB
print_info: arch = llama
print_info: vocab_only = 0
print_info: n_ctx_train = 8192
print_info: n_embd = 4096
print_info: n_layer = 32
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-05
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 = 14336
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 0
print_info: rope scaling = linear
print_info: freq_base_train = 500000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 8192
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 8B
print_info: model params = 8.03 B
print_info: general.name = F59E729Ac709F2Fa41383C7Aa29276538D20Cc37
print_info: vocab type = BPE
print_info: n_vocab = 128256
print_info: n_merges = 280147
print_info: BOS token = 128000 '<|begin_of_text|>'
print_info: EOS token = 128001 '<|end_of_text|>'
print_info: EOT token = 128009 '<|eot_id|>'
print_info: LF token = 198 'Ċ'
print_info: EOG token = 128001 '<|end_of_text|>'
print_info: EOG token = 128009 '<|eot_id|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 32 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 33/33 layers to GPU
load_tensors: Metal_Mapped model buffer size = 14315.02 MiB
load_tensors: CPU_Mapped model buffer size = 1002.00 MiB
.........................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: freq_base = 500000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (8192) -- the full capacity of the model will not be utilized
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M3 Pro
ggml_metal_init: picking default device: Apple M3 Pro
ggml_metal_load_library: using embedded metal library
ggml_metal_init: GPU name: Apple M3 Pro
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 residency sets = true
ggml_metal_init: has bfloat = true
ggml_metal_init: use bfloat = false
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 28991.03 MB
ggml_metal_init: skipping kernel_get_rows_bf16 (not supported)
ggml_metal_init: skipping kernel_set_rows_bf16 (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_c4 (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_f16 (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_h192 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_hk192_hv128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_hk576_hv512 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h64 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h96 (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_h192 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_hk192_hv128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_hk576_hv512 (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_context: CPU output buffer size = 0.49 MiB
llama_kv_cache_unified: Metal KV buffer size = 512.00 MiB
llama_kv_cache_unified: size = 512.00 MiB ( 4096 cells, 32 layers, 1 seqs), K (f16): 256.00 MiB, V (f16): 256.00 MiB
llama_context: Metal compute buffer size = 296.00 MiB
llama_context: CPU compute buffer size = 16.01 MiB
llama_context: graph nodes = 1158
llama_context: graph splits = 2
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
system_info: n_threads = 6 (n_threads_batch = 6) / 12 | Metal : EMBED_LIBRARY = 1 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | MATMUL_INT8 = 1 | DOTPROD = 1 | ACCELERATE = 1 | REPACK = 1 |
/Users/ryanmangeno/Documents/dev/ai/gits/llama/llama.cpp/src/llama-context.cpp:881: GGML_ASSERT((!batch_inp.token && batch_inp.embd) || (batch_inp.token && !batch_inp.embd)) failed
(lldb) process attach --pid 53077
Process 53077 stopped
* thread #1, queue = 'com.apple.main-thread', stop reason = signal SIGSTOP
frame #0: 0x0000000197068204 libsystem_kernel.dylib`__wait4 + 8
libsystem_kernel.dylib`__wait4:
-> 0x197068204 <+8>: b.lo 0x197068224 ; <+40>
0x197068208 <+12>: pacibsp
0x19706820c <+16>: stp x29, x30, [sp, #-0x10]!
0x197068210 <+20>: mov x29, sp
Target 0: (llama-eval-callback) stopped.
Executable binary set to "/Users/ryanmangeno/Documents/dev/ai/gits/llama/llama.cpp/build/bin/llama-eval-callback".
Architecture set to: arm64-apple-macosx-.
(lldb) bt
* thread #1, queue = 'com.apple.main-thread', stop reason = signal SIGSTOP
* frame #0: 0x0000000197068204 libsystem_kernel.dylib`__wait4 + 8
frame #1: 0x0000000102811430 libggml-base.dylib`ggml_abort + 116
frame #2: 0x0000000102581ef4 libllama.dylib`llama_context::decode(llama_batch const&) + 4184
frame #3: 0x00000001025856d8 libllama.dylib`llama_decode + 20
frame #4: 0x00000001020eae60 llama-eval-callback`main + 408
frame #5: 0x0000000196d02b98 dyld`start + 6076
(lldb) quit