Run 13B Alpaca Llama Failed

[PeterFujiyu]

这是运行时的log,提问后不断ggml_metal_graph_compute: command buffer 0 failed with status 5
基本设备信息都在log里，使用最新llama.cpp,和最新模型。

'''
$ ./chat.sh models/chinese-alpaca-2-13b-16k-hf/ggml-model-q6_k.gguf '作为一个 AI 助手，你可以帮助人类做哪些事情？'
Log start
main: build = 1 (d83fdc2)
main: built with Apple clang version 15.0.0 (clang-1500.1.0.2.5) for arm64-apple-darwin23.3.0
main: seed = 1706339166
llama_model_loader: loaded meta data with 22 key-value pairs and 363 tensors from models/chinese-alpaca-2-13b-16k-hf/ggml-model-q6_k.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 = models
llama_model_loader: - kv 2: llama.context_length u32 = 16384
llama_model_loader: - kv 3: llama.embedding_length u32 = 5120
llama_model_loader: - kv 4: llama.block_count u32 = 40
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 13824
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 7: llama.attention.head_count u32 = 40
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 40
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: llama.rope.scaling.type str = linear
llama_model_loader: - kv 11: llama.rope.scaling.factor f32 = 4.000000
llama_model_loader: - kv 12: general.file_type u32 = 18
llama_model_loader: - kv 13: tokenizer.ggml.model str = llama
llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,55296] = ["", "", "", "<0x00>", "<...
llama_model_loader: - kv 15: tokenizer.ggml.scores arr[f32,55296] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,55296] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 19: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 20: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 21: general.quantization_version u32 = 2
llama_model_loader: - type f32: 81 tensors
llama_model_loader: - type q6_K: 282 tensors
llm_load_vocab: mismatch in special tokens definition ( 889/55296 vs 259/55296 ).
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 = 55296
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 16384
llm_load_print_meta: n_embd = 5120
llm_load_print_meta: n_head = 40
llm_load_print_meta: n_head_kv = 40
llm_load_print_meta: n_layer = 40
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 5120
llm_load_print_meta: n_embd_v_gqa = 5120
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: n_ff = 13824
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 0.25
llm_load_print_meta: n_yarn_orig_ctx = 16384
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 13B
llm_load_print_meta: model ftype = Q6_K
llm_load_print_meta: model params = 13.25 B
llm_load_print_meta: model size = 10.13 GiB (6.56 BPW)
llm_load_print_meta: general.name = models
llm_load_print_meta: BOS token = 1 ''
llm_load_print_meta: EOS token = 2 ''
llm_load_print_meta: UNK token = 0 ''
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.28 MiB
ggml_backend_metal_buffer_from_ptr: allocated buffer, size = 8192.00 MiB, offs = 0
ggml_backend_metal_buffer_from_ptr: allocated buffer, size = 2178.36 MiB, offs = 8357675008, (10370.42 / 10922.67)
llm_load_tensors: offloading 40 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 41/41 layers to GPU
llm_load_tensors: Metal buffer size = 10148.86 MiB
llm_load_tensors: CPU buffer size = 221.48 MiB
.................................................................................................
llama_new_context_with_model: n_ctx = 4096
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 0.25
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1 Pro
ggml_metal_init: picking default device: Apple M1 Pro
ggml_metal_init: default.metallib not found, loading from source
ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil
ggml_metal_init: loading '/Users/peter/Documents/Peter_Code/GitHub/llama/llama.cpp/ggml-metal.metal'
ggml_metal_init: GPU name: Apple M1 Pro
ggml_metal_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_init: simdgroup reduction support = true
ggml_metal_init: simdgroup matrix mul. support = true
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 3200.00 MiB, (13571.98 / 10922.67)ggml_backend_metal_log_allocated_size: warning: current allocated size is greater than the recommended max working set size
llama_kv_cache_init: Metal KV buffer size = 3200.00 MiB
llama_new_context_with_model: KV self size = 3200.00 MiB, K (f16): 1600.00 MiB, V (f16): 1600.00 MiB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, (13572.00 / 10922.67)ggml_backend_metal_log_allocated_size: warning: current allocated size is greater than the recommended max working set size
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 358.02 MiB, (13930.00 / 10922.67)ggml_backend_metal_log_allocated_size: warning: current allocated size is greater than the recommended max working set size
llama_new_context_with_model: graph splits (measure): 3
llama_new_context_with_model: Metal compute buffer size = 358.00 MiB
llama_new_context_with_model: CPU compute buffer size = 18.00 MiB
ggml_metal_graph_compute: command buffer 0 failed with status 5

system_info: n_threads = 8 / 8 | AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |
main: interactive mode on.
Input prefix with BOS
Input prefix: ' [INST] '
Input suffix: ' [/INST]'
sampling:
repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000
top_k = 40, tfs_z = 1.000, top_p = 0.900, min_p = 0.050, typical_p = 1.000, temp = 0.500
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order:
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temp
generate: n_ctx = 4096, n_batch = 512, n_predict = -1, n_keep = 0

== Running in interactive mode. ==

• Press Ctrl+C to interject at any time.
• Press Return to return control to LLaMa.
• To return control without starting a new line, end your input with '/'.
• If you want to submit another line, end your input with ''.

[INST] <>
You are a helpful assistant. 你是一个乐于助人的助手。请你提供专业、有逻辑、内容真实、有价值的详细回复。
<>

作为一个 AI 助手，你可以帮助人类做哪些事情？ [/INST]ggml_metal_graph_compute: command buffer 0 failed with status 5

ggml_metal_graph_compute: command buffer 0 failed with status 5
用了ggml_metal_graph_compute: command buffer 0 failed with status 5
《ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
ggml_metal_graph_compute: command buffer 0 failed with status 5
'''

[ymcui]

很明显是你offload到GPU的显存超过最大值了。log里有明显提示。

ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 3200.00 MiB, (13571.98 / 10922.67)ggml_backend_metal_log_allocated_size: warning: current allocated size is greater than the recommended max working set size

-ngl的值调小一点（速度也会变慢一些），可以解决。