Segmentation fault #98
Description
command as follow:
python3.10 tools/run_pipeline.py -o ~/Workshop/T-MAC/Llama-2-7b-EfficientQAT-w2g128-GPTQ -m llama-2-7b-2bit -d android -ndk /Users/jyxc-dz-0100660/Library/Android/sdk/ndk/26.1.10909125 -u -q int_n
adb shell TMAC_KCFG_FILE=/data/local/tmp/kcfg.ini LD_LIBRARY_PATH=/data/local/tmp/bin/ /data/local/tmp/bin/llama-cli -m /data/local/tmp/Llama-2-7b-EfficientQAT-w2g128-GPTQ-Llama-2-7b-EfficientQAT-w2g128-GPTQ.INT_N.gguf -n 128 -t 4 -p "Microsoft Corporation is an American multinational corporation and technology company headquartered in Redmond, Washington." -ngl 0 -c 2048
warning: not compiled with GPU offload support, --gpu-layers option will be ignored
warning: see main README.md for information on enabling GPU BLAS support
build: 3913 (eb07ecf0) with Android (10552028, +pgo, +bolt, +lto, -mlgo, based on r487747d) clang version 17.0.2 (https://android.googlesource.com/toolchain/llvm-project d9f89f4d16663d5012e5c09495f3b30ece3d2362) for x86_64-apple-darwin24.6.0
main: llama backend init
[01:29:43] /Users/jyxc-dz-0100660/Workshop/T-MAC/3rdparty/llama.cpp/ggml/src/ggml-tmac.cpp:38: ggml_tmac_init
main: load the model and apply lora adapter, if any
llama_model_loader: loaded meta data with 29 key-value pairs and 291 tensors from /data/local/tmp/Llama-2-7b-EfficientQAT-w2g128-GPTQ-Llama-2-7b-EfficientQAT-w2g128-GPTQ.INT_N.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 = Llama 2 7b EfficientQAT W2G128 GPTQ
llama_model_loader: - kv 3: general.finetune str = EfficientQAT-w2g128-GPTQ
llama_model_loader: - kv 4: general.basename str = Llama-2
llama_model_loader: - kv 5: general.size_label str = 7B
llama_model_loader: - kv 6: llama.block_count u32 = 32
llama_model_loader: - kv 7: llama.context_length u32 = 4096
llama_model_loader: - kv 8: llama.embedding_length u32 = 4096
llama_model_loader: - kv 9: llama.feed_forward_length u32 = 11008
llama_model_loader: - kv 10: llama.attention.head_count u32 = 32
llama_model_loader: - kv 11: llama.attention.head_count_kv u32 = 32
llama_model_loader: - kv 12: llama.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 13: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 14: general.file_type u32 = 38
llama_model_loader: - kv 15: llama.vocab_size u32 = 32001
llama_model_loader: - kv 16: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 17: tokenizer.ggml.add_space_prefix bool = true
llama_model_loader: - kv 18: tokenizer.ggml.model str = llama
llama_model_loader: - kv 19: tokenizer.ggml.pre str = default
llama_model_loader: - kv 20: tokenizer.ggml.tokens arr[str,32001] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 21: tokenizer.ggml.scores arr[f32,32001] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,32001] = [3, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 28: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type f16: 2 tensors
llama_model_loader: - type i2: 224 tensors
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 4
llm_load_vocab: token to piece cache size = 0.1684 MB
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 = 32001
llm_load_print_meta: n_merges = 0
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 4096
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
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 = 1
llm_load_print_meta: n_embd_k_gqa = 4096
llm_load_print_meta: n_embd_v_gqa = 4096
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: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 11008
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 = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 4096
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 = 7B
llm_load_print_meta: model ftype = INT_N
llm_load_print_meta: model params = 6.74 B
llm_load_print_meta: model size = 2.37 GiB (3.03 BPW)
llm_load_print_meta: general.name = Llama 2 7b EfficientQAT W2G128 GPTQ
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_print_meta: EOG token = 2 '</s>'
llm_load_print_meta: max token length = 48
llm_load_tensors: ggml ctx size = 0.14 MiB
llm_load_tensors: CPU buffer size = 2431.03 MiB
..Segmentation fault