740 lines
41 KiB
Plaintext
740 lines
41 KiB
Plaintext
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 8191 MiB):
|
|
Device 0: NVIDIA GeForce RTX 3070, compute capability 8.6, VMM: yes, VRAM: 8191 MiB
|
|
load_backend: loaded CUDA backend from D:\Documents\Github\ai-backend-studio\target\debug\ggml-cuda.dll
|
|
load_backend: loaded RPC backend from D:\Documents\Github\ai-backend-studio\target\debug\ggml-rpc.dll
|
|
load_backend: loaded CPU backend from D:\Documents\Github\ai-backend-studio\target\debug\ggml-cpu-haswell.dll
|
|
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3070) (0000:2b:00.0) - 7113 MiB free
|
|
llama_model_loader: loaded meta data with 53 key-value pairs and 426 tensors from D:\Documents\Github\ai-backend-studio\models\Qwen3.5-4B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled.i1-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 = qwen35
|
|
llama_model_loader: - kv 1: general.type str = model
|
|
llama_model_loader: - kv 2: general.name str = Qwen3.5-4B-Abliterated-Claude-4.6-Opu...
|
|
llama_model_loader: - kv 3: general.version str = 4.6
|
|
llama_model_loader: - kv 4: general.finetune str = Abliterated-Claude-Opus-Reasoning-Dis...
|
|
llama_model_loader: - kv 5: general.basename str = Qwen3.5
|
|
llama_model_loader: - kv 6: general.size_label str = 4B
|
|
llama_model_loader: - kv 7: general.license str = other
|
|
llama_model_loader: - kv 8: general.base_model.count u32 = 1
|
|
llama_model_loader: - kv 9: general.base_model.0.name str = Qwen3.5 4B Claude 4.6 Opus Reasoning ...
|
|
llama_model_loader: - kv 10: general.base_model.0.version str = 4.6
|
|
llama_model_loader: - kv 11: general.base_model.0.organization str = Jackrong
|
|
llama_model_loader: - kv 12: general.base_model.0.repo_url str = https://huggingface.co/Jackrong/Qwen3...
|
|
llama_model_loader: - kv 13: general.tags arr[str,5] = ["abliterated", "de-censored", "reaso...
|
|
llama_model_loader: - kv 14: qwen35.block_count u32 = 32
|
|
llama_model_loader: - kv 15: qwen35.context_length u32 = 262144
|
|
llama_model_loader: - kv 16: qwen35.embedding_length u32 = 2560
|
|
llama_model_loader: - kv 17: qwen35.feed_forward_length u32 = 9216
|
|
llama_model_loader: - kv 18: qwen35.attention.head_count u32 = 16
|
|
llama_model_loader: - kv 19: qwen35.attention.head_count_kv u32 = 4
|
|
llama_model_loader: - kv 20: qwen35.rope.dimension_sections arr[i32,4] = [11, 11, 10, 0]
|
|
llama_model_loader: - kv 21: qwen35.rope.freq_base f32 = 10000000.000000
|
|
llama_model_loader: - kv 22: qwen35.attention.layer_norm_rms_epsilon f32 = 0.000001
|
|
llama_model_loader: - kv 23: qwen35.attention.key_length u32 = 256
|
|
llama_model_loader: - kv 24: qwen35.attention.value_length u32 = 256
|
|
llama_model_loader: - kv 25: qwen35.ssm.conv_kernel u32 = 4
|
|
llama_model_loader: - kv 26: qwen35.ssm.state_size u32 = 128
|
|
llama_model_loader: - kv 27: qwen35.ssm.group_count u32 = 16
|
|
llama_model_loader: - kv 28: qwen35.ssm.time_step_rank u32 = 32
|
|
llama_model_loader: - kv 29: qwen35.ssm.inner_size u32 = 4096
|
|
llama_model_loader: - kv 30: qwen35.full_attention_interval u32 = 4
|
|
llama_model_loader: - kv 31: qwen35.rope.dimension_count u32 = 64
|
|
llama_model_loader: - kv 32: tokenizer.ggml.model str = gpt2
|
|
llama_model_loader: - kv 33: tokenizer.ggml.pre str = qwen35
|
|
llama_model_loader: - kv 34: tokenizer.ggml.tokens arr[str,248320] = ["!", "\"", "#", "$", "%", "&", "'", ...
|
|
llama_model_loader: - kv 35: tokenizer.ggml.token_type arr[i32,248320] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
|
|
llama_model_loader: - kv 36: tokenizer.ggml.merges arr[str,247587] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
|
|
llama_model_loader: - kv 37: tokenizer.ggml.eos_token_id u32 = 248046
|
|
llama_model_loader: - kv 38: tokenizer.ggml.padding_token_id u32 = 248055
|
|
llama_model_loader: - kv 39: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
|
|
llama_model_loader: - kv 40: general.quantization_version u32 = 2
|
|
llama_model_loader: - kv 41: general.file_type u32 = 18
|
|
llama_model_loader: - kv 42: general.url str = https://huggingface.co/mradermacher/Q...
|
|
llama_model_loader: - kv 43: mradermacher.quantize_version str = 2
|
|
llama_model_loader: - kv 44: mradermacher.quantized_by str = mradermacher
|
|
llama_model_loader: - kv 45: mradermacher.quantized_at str = 2026-03-10T09:59:38+01:00
|
|
llama_model_loader: - kv 46: mradermacher.quantized_on str = nico1
|
|
llama_model_loader: - kv 47: general.source.url str = https://huggingface.co/Abhiray/Qwen3....
|
|
llama_model_loader: - kv 48: mradermacher.convert_type str = hf
|
|
llama_model_loader: - kv 49: quantize.imatrix.file str = Qwen3.5-4B-Abliterated-Claude-4.6-Opu...
|
|
llama_model_loader: - kv 50: quantize.imatrix.dataset str = imatrix-training-full-3
|
|
llama_model_loader: - kv 51: quantize.imatrix.entries_count u32 = 248
|
|
llama_model_loader: - kv 52: quantize.imatrix.chunks_count u32 = 319
|
|
llama_model_loader: - type f32: 177 tensors
|
|
llama_model_loader: - type q6_K: 249 tensors
|
|
print_info: file format = GGUF V3 (latest)
|
|
print_info: file type = Q6_K
|
|
print_info: file size = 3.22 GiB (6.57 BPW)
|
|
init_tokenizer: initializing tokenizer for type 2
|
|
load: 0 unused tokens
|
|
load: control token: 248062 '<|fim_suffix|>' is not marked as EOG
|
|
load: control token: 248072 '<tts_pad>' is not marked as EOG
|
|
load: control token: 248050 '<|box_end|>' is not marked as EOG
|
|
load: control token: 248048 '<|object_ref_end|>' is not marked as EOG
|
|
load: control token: 248055 '<|vision_pad|>' is not marked as EOG
|
|
load: control token: 248060 '<|fim_prefix|>' is not marked as EOG
|
|
load: control token: 248049 '<|box_start|>' is not marked as EOG
|
|
load: control token: 248073 '<tts_text_bos>' is not marked as EOG
|
|
load: control token: 248052 '<|quad_end|>' is not marked as EOG
|
|
load: control token: 248054 '<|vision_end|>' is not marked as EOG
|
|
load: control token: 248075 '<tts_text_bos_single>' is not marked as EOG
|
|
load: control token: 248056 '<|image_pad|>' is not marked as EOG
|
|
load: control token: 248071 '<|audio_end|>' is not marked as EOG
|
|
load: control token: 248045 '<|im_start|>' is not marked as EOG
|
|
load: control token: 248047 '<|object_ref_start|>' is not marked as EOG
|
|
load: control token: 248051 '<|quad_start|>' is not marked as EOG
|
|
load: control token: 248053 '<|vision_start|>' is not marked as EOG
|
|
load: control token: 248057 '<|video_pad|>' is not marked as EOG
|
|
load: control token: 248061 '<|fim_middle|>' is not marked as EOG
|
|
load: control token: 248070 '<|audio_start|>' is not marked as EOG
|
|
load: control token: 248074 '<tts_text_eod>' is not marked as EOG
|
|
load: control token: 248076 '<|audio_pad|>' is not marked as EOG
|
|
load: printing all EOG tokens:
|
|
load: - 248044 ('<|endoftext|>')
|
|
load: - 248046 ('<|im_end|>')
|
|
load: - 248063 ('<|fim_pad|>')
|
|
load: - 248064 ('<|repo_name|>')
|
|
load: - 248065 ('<|file_sep|>')
|
|
load: special tokens cache size = 33
|
|
load: token to piece cache size = 1.7581 MB
|
|
print_info: arch = qwen35
|
|
print_info: vocab_only = 0
|
|
print_info: no_alloc = 0
|
|
print_info: n_ctx_train = 262144
|
|
print_info: n_embd = 2560
|
|
print_info: n_embd_inp = 2560
|
|
print_info: n_layer = 32
|
|
print_info: n_head = 16
|
|
print_info: n_head_kv = 4
|
|
print_info: n_rot = 64
|
|
print_info: n_swa = 0
|
|
print_info: is_swa_any = 0
|
|
print_info: n_embd_head_k = 256
|
|
print_info: n_embd_head_v = 256
|
|
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-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 = 9216
|
|
print_info: n_expert = 0
|
|
print_info: n_expert_used = 0
|
|
print_info: n_expert_groups = 0
|
|
print_info: n_group_used = 0
|
|
print_info: causal attn = 1
|
|
print_info: pooling type = -1
|
|
print_info: rope type = 40
|
|
print_info: rope scaling = linear
|
|
print_info: freq_base_train = 10000000.0
|
|
print_info: freq_scale_train = 1
|
|
print_info: n_ctx_orig_yarn = 262144
|
|
print_info: rope_yarn_log_mul = 0.0000
|
|
print_info: rope_finetuned = unknown
|
|
print_info: mrope sections = [11, 11, 10, 0]
|
|
print_info: ssm_d_conv = 4
|
|
print_info: ssm_d_inner = 4096
|
|
print_info: ssm_d_state = 128
|
|
print_info: ssm_dt_rank = 32
|
|
print_info: ssm_n_group = 16
|
|
print_info: ssm_dt_b_c_rms = 0
|
|
print_info: model type = 4B
|
|
print_info: model params = 4.21 B
|
|
print_info: general.name = Qwen3.5-4B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled
|
|
print_info: vocab type = BPE
|
|
print_info: n_vocab = 248320
|
|
print_info: n_merges = 247587
|
|
print_info: BOS token = 11 ','
|
|
print_info: EOS token = 248046 '<|im_end|>'
|
|
print_info: EOT token = 248046 '<|im_end|>'
|
|
print_info: PAD token = 248055 '<|vision_pad|>'
|
|
print_info: LF token = 198 'Ċ'
|
|
print_info: FIM PRE token = 248060 '<|fim_prefix|>'
|
|
print_info: FIM SUF token = 248062 '<|fim_suffix|>'
|
|
print_info: FIM MID token = 248061 '<|fim_middle|>'
|
|
print_info: FIM PAD token = 248063 '<|fim_pad|>'
|
|
print_info: FIM REP token = 248064 '<|repo_name|>'
|
|
print_info: FIM SEP token = 248065 '<|file_sep|>'
|
|
print_info: EOG token = 248044 '<|endoftext|>'
|
|
print_info: EOG token = 248046 '<|im_end|>'
|
|
print_info: EOG token = 248063 '<|fim_pad|>'
|
|
print_info: EOG token = 248064 '<|repo_name|>'
|
|
print_info: EOG token = 248065 '<|file_sep|>'
|
|
print_info: max token length = 256
|
|
load_tensors: loading model tensors, this can take a while... (mmap = false, direct_io = false)
|
|
load_tensors: layer 0 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 1 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 2 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 3 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 4 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 5 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 6 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 7 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 8 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 9 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 10 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 11 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 12 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 13 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 14 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 15 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 16 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 17 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 18 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 19 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 20 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 21 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 22 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 23 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 24 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 25 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 26 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 27 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 28 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 29 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 30 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 31 assigned to device CUDA0, is_swa = 0
|
|
load_tensors: layer 32 assigned to device CUDA0, 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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.0.attn_qkv.weight
|
|
create_tensor: loading tensor blk.0.attn_gate.weight
|
|
create_tensor: loading tensor blk.0.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.0.ssm_dt.bias
|
|
create_tensor: loading tensor blk.0.ssm_a
|
|
create_tensor: loading tensor blk.0.ssm_beta.weight
|
|
create_tensor: loading tensor blk.0.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.0.ssm_norm.weight
|
|
create_tensor: loading tensor blk.0.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.1.attn_qkv.weight
|
|
create_tensor: loading tensor blk.1.attn_gate.weight
|
|
create_tensor: loading tensor blk.1.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.1.ssm_dt.bias
|
|
create_tensor: loading tensor blk.1.ssm_a
|
|
create_tensor: loading tensor blk.1.ssm_beta.weight
|
|
create_tensor: loading tensor blk.1.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.1.ssm_norm.weight
|
|
create_tensor: loading tensor blk.1.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.2.attn_qkv.weight
|
|
create_tensor: loading tensor blk.2.attn_gate.weight
|
|
create_tensor: loading tensor blk.2.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.2.ssm_dt.bias
|
|
create_tensor: loading tensor blk.2.ssm_a
|
|
create_tensor: loading tensor blk.2.ssm_beta.weight
|
|
create_tensor: loading tensor blk.2.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.2.ssm_norm.weight
|
|
create_tensor: loading tensor blk.2.ssm_out.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.post_attention_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_q_norm.weight
|
|
create_tensor: loading tensor blk.3.attn_k_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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.4.attn_qkv.weight
|
|
create_tensor: loading tensor blk.4.attn_gate.weight
|
|
create_tensor: loading tensor blk.4.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.4.ssm_dt.bias
|
|
create_tensor: loading tensor blk.4.ssm_a
|
|
create_tensor: loading tensor blk.4.ssm_beta.weight
|
|
create_tensor: loading tensor blk.4.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.4.ssm_norm.weight
|
|
create_tensor: loading tensor blk.4.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.5.attn_qkv.weight
|
|
create_tensor: loading tensor blk.5.attn_gate.weight
|
|
create_tensor: loading tensor blk.5.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.5.ssm_dt.bias
|
|
create_tensor: loading tensor blk.5.ssm_a
|
|
create_tensor: loading tensor blk.5.ssm_beta.weight
|
|
create_tensor: loading tensor blk.5.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.5.ssm_norm.weight
|
|
create_tensor: loading tensor blk.5.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.6.attn_qkv.weight
|
|
create_tensor: loading tensor blk.6.attn_gate.weight
|
|
create_tensor: loading tensor blk.6.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.6.ssm_dt.bias
|
|
create_tensor: loading tensor blk.6.ssm_a
|
|
create_tensor: loading tensor blk.6.ssm_beta.weight
|
|
create_tensor: loading tensor blk.6.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.6.ssm_norm.weight
|
|
create_tensor: loading tensor blk.6.ssm_out.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.post_attention_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_q_norm.weight
|
|
create_tensor: loading tensor blk.7.attn_k_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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.8.attn_qkv.weight
|
|
create_tensor: loading tensor blk.8.attn_gate.weight
|
|
create_tensor: loading tensor blk.8.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.8.ssm_dt.bias
|
|
create_tensor: loading tensor blk.8.ssm_a
|
|
create_tensor: loading tensor blk.8.ssm_beta.weight
|
|
create_tensor: loading tensor blk.8.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.8.ssm_norm.weight
|
|
create_tensor: loading tensor blk.8.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.9.attn_qkv.weight
|
|
create_tensor: loading tensor blk.9.attn_gate.weight
|
|
create_tensor: loading tensor blk.9.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.9.ssm_dt.bias
|
|
create_tensor: loading tensor blk.9.ssm_a
|
|
create_tensor: loading tensor blk.9.ssm_beta.weight
|
|
create_tensor: loading tensor blk.9.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.9.ssm_norm.weight
|
|
create_tensor: loading tensor blk.9.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.10.attn_qkv.weight
|
|
create_tensor: loading tensor blk.10.attn_gate.weight
|
|
create_tensor: loading tensor blk.10.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.10.ssm_dt.bias
|
|
create_tensor: loading tensor blk.10.ssm_a
|
|
create_tensor: loading tensor blk.10.ssm_beta.weight
|
|
create_tensor: loading tensor blk.10.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.10.ssm_norm.weight
|
|
create_tensor: loading tensor blk.10.ssm_out.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.post_attention_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_q_norm.weight
|
|
create_tensor: loading tensor blk.11.attn_k_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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.12.attn_qkv.weight
|
|
create_tensor: loading tensor blk.12.attn_gate.weight
|
|
create_tensor: loading tensor blk.12.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.12.ssm_dt.bias
|
|
create_tensor: loading tensor blk.12.ssm_a
|
|
create_tensor: loading tensor blk.12.ssm_beta.weight
|
|
create_tensor: loading tensor blk.12.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.12.ssm_norm.weight
|
|
create_tensor: loading tensor blk.12.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.13.attn_qkv.weight
|
|
create_tensor: loading tensor blk.13.attn_gate.weight
|
|
create_tensor: loading tensor blk.13.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.13.ssm_dt.bias
|
|
create_tensor: loading tensor blk.13.ssm_a
|
|
create_tensor: loading tensor blk.13.ssm_beta.weight
|
|
create_tensor: loading tensor blk.13.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.13.ssm_norm.weight
|
|
create_tensor: loading tensor blk.13.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.14.attn_qkv.weight
|
|
create_tensor: loading tensor blk.14.attn_gate.weight
|
|
create_tensor: loading tensor blk.14.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.14.ssm_dt.bias
|
|
create_tensor: loading tensor blk.14.ssm_a
|
|
create_tensor: loading tensor blk.14.ssm_beta.weight
|
|
create_tensor: loading tensor blk.14.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.14.ssm_norm.weight
|
|
create_tensor: loading tensor blk.14.ssm_out.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.post_attention_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_q_norm.weight
|
|
create_tensor: loading tensor blk.15.attn_k_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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.16.attn_qkv.weight
|
|
create_tensor: loading tensor blk.16.attn_gate.weight
|
|
create_tensor: loading tensor blk.16.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.16.ssm_dt.bias
|
|
create_tensor: loading tensor blk.16.ssm_a
|
|
create_tensor: loading tensor blk.16.ssm_beta.weight
|
|
create_tensor: loading tensor blk.16.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.16.ssm_norm.weight
|
|
create_tensor: loading tensor blk.16.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.17.attn_qkv.weight
|
|
create_tensor: loading tensor blk.17.attn_gate.weight
|
|
create_tensor: loading tensor blk.17.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.17.ssm_dt.bias
|
|
create_tensor: loading tensor blk.17.ssm_a
|
|
create_tensor: loading tensor blk.17.ssm_beta.weight
|
|
create_tensor: loading tensor blk.17.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.17.ssm_norm.weight
|
|
create_tensor: loading tensor blk.17.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.18.attn_qkv.weight
|
|
create_tensor: loading tensor blk.18.attn_gate.weight
|
|
create_tensor: loading tensor blk.18.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.18.ssm_dt.bias
|
|
create_tensor: loading tensor blk.18.ssm_a
|
|
create_tensor: loading tensor blk.18.ssm_beta.weight
|
|
create_tensor: loading tensor blk.18.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.18.ssm_norm.weight
|
|
create_tensor: loading tensor blk.18.ssm_out.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.post_attention_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_q_norm.weight
|
|
create_tensor: loading tensor blk.19.attn_k_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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.20.attn_qkv.weight
|
|
create_tensor: loading tensor blk.20.attn_gate.weight
|
|
create_tensor: loading tensor blk.20.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.20.ssm_dt.bias
|
|
create_tensor: loading tensor blk.20.ssm_a
|
|
create_tensor: loading tensor blk.20.ssm_beta.weight
|
|
create_tensor: loading tensor blk.20.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.20.ssm_norm.weight
|
|
create_tensor: loading tensor blk.20.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.21.attn_qkv.weight
|
|
create_tensor: loading tensor blk.21.attn_gate.weight
|
|
create_tensor: loading tensor blk.21.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.21.ssm_dt.bias
|
|
create_tensor: loading tensor blk.21.ssm_a
|
|
create_tensor: loading tensor blk.21.ssm_beta.weight
|
|
create_tensor: loading tensor blk.21.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.21.ssm_norm.weight
|
|
create_tensor: loading tensor blk.21.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.22.attn_qkv.weight
|
|
create_tensor: loading tensor blk.22.attn_gate.weight
|
|
create_tensor: loading tensor blk.22.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.22.ssm_dt.bias
|
|
create_tensor: loading tensor blk.22.ssm_a
|
|
create_tensor: loading tensor blk.22.ssm_beta.weight
|
|
create_tensor: loading tensor blk.22.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.22.ssm_norm.weight
|
|
create_tensor: loading tensor blk.22.ssm_out.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.post_attention_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_q_norm.weight
|
|
create_tensor: loading tensor blk.23.attn_k_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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.24.attn_qkv.weight
|
|
create_tensor: loading tensor blk.24.attn_gate.weight
|
|
create_tensor: loading tensor blk.24.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.24.ssm_dt.bias
|
|
create_tensor: loading tensor blk.24.ssm_a
|
|
create_tensor: loading tensor blk.24.ssm_beta.weight
|
|
create_tensor: loading tensor blk.24.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.24.ssm_norm.weight
|
|
create_tensor: loading tensor blk.24.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.25.attn_qkv.weight
|
|
create_tensor: loading tensor blk.25.attn_gate.weight
|
|
create_tensor: loading tensor blk.25.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.25.ssm_dt.bias
|
|
create_tensor: loading tensor blk.25.ssm_a
|
|
create_tensor: loading tensor blk.25.ssm_beta.weight
|
|
create_tensor: loading tensor blk.25.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.25.ssm_norm.weight
|
|
create_tensor: loading tensor blk.25.ssm_out.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.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.26.attn_qkv.weight
|
|
create_tensor: loading tensor blk.26.attn_gate.weight
|
|
create_tensor: loading tensor blk.26.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.26.ssm_dt.bias
|
|
create_tensor: loading tensor blk.26.ssm_a
|
|
create_tensor: loading tensor blk.26.ssm_beta.weight
|
|
create_tensor: loading tensor blk.26.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.26.ssm_norm.weight
|
|
create_tensor: loading tensor blk.26.ssm_out.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.post_attention_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_q_norm.weight
|
|
create_tensor: loading tensor blk.27.attn_k_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
|
|
create_tensor: loading tensor blk.28.attn_norm.weight
|
|
create_tensor: loading tensor blk.28.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.28.attn_qkv.weight
|
|
create_tensor: loading tensor blk.28.attn_gate.weight
|
|
create_tensor: loading tensor blk.28.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.28.ssm_dt.bias
|
|
create_tensor: loading tensor blk.28.ssm_a
|
|
create_tensor: loading tensor blk.28.ssm_beta.weight
|
|
create_tensor: loading tensor blk.28.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.28.ssm_norm.weight
|
|
create_tensor: loading tensor blk.28.ssm_out.weight
|
|
create_tensor: loading tensor blk.28.ffn_gate.weight
|
|
create_tensor: loading tensor blk.28.ffn_down.weight
|
|
create_tensor: loading tensor blk.28.ffn_up.weight
|
|
create_tensor: loading tensor blk.29.attn_norm.weight
|
|
create_tensor: loading tensor blk.29.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.29.attn_qkv.weight
|
|
create_tensor: loading tensor blk.29.attn_gate.weight
|
|
create_tensor: loading tensor blk.29.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.29.ssm_dt.bias
|
|
create_tensor: loading tensor blk.29.ssm_a
|
|
create_tensor: loading tensor blk.29.ssm_beta.weight
|
|
create_tensor: loading tensor blk.29.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.29.ssm_norm.weight
|
|
create_tensor: loading tensor blk.29.ssm_out.weight
|
|
create_tensor: loading tensor blk.29.ffn_gate.weight
|
|
create_tensor: loading tensor blk.29.ffn_down.weight
|
|
create_tensor: loading tensor blk.29.ffn_up.weight
|
|
create_tensor: loading tensor blk.30.attn_norm.weight
|
|
create_tensor: loading tensor blk.30.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.30.attn_qkv.weight
|
|
create_tensor: loading tensor blk.30.attn_gate.weight
|
|
create_tensor: loading tensor blk.30.ssm_conv1d.weight
|
|
create_tensor: loading tensor blk.30.ssm_dt.bias
|
|
create_tensor: loading tensor blk.30.ssm_a
|
|
create_tensor: loading tensor blk.30.ssm_beta.weight
|
|
create_tensor: loading tensor blk.30.ssm_alpha.weight
|
|
create_tensor: loading tensor blk.30.ssm_norm.weight
|
|
create_tensor: loading tensor blk.30.ssm_out.weight
|
|
create_tensor: loading tensor blk.30.ffn_gate.weight
|
|
create_tensor: loading tensor blk.30.ffn_down.weight
|
|
create_tensor: loading tensor blk.30.ffn_up.weight
|
|
create_tensor: loading tensor blk.31.attn_norm.weight
|
|
create_tensor: loading tensor blk.31.post_attention_norm.weight
|
|
create_tensor: loading tensor blk.31.attn_q.weight
|
|
create_tensor: loading tensor blk.31.attn_k.weight
|
|
create_tensor: loading tensor blk.31.attn_v.weight
|
|
create_tensor: loading tensor blk.31.attn_output.weight
|
|
create_tensor: loading tensor blk.31.attn_q_norm.weight
|
|
create_tensor: loading tensor blk.31.attn_k_norm.weight
|
|
create_tensor: loading tensor blk.31.ffn_gate.weight
|
|
create_tensor: loading tensor blk.31.ffn_down.weight
|
|
create_tensor: loading tensor blk.31.ffn_up.weight
|
|
done_getting_tensors: tensor 'token_embd.weight' (q6_K) (and 0 others) cannot be used with preferred buffer type CUDA_Host, using CPU instead
|
|
load_tensors: offloading output layer to GPU
|
|
load_tensors: offloading 31 repeating layers to GPU
|
|
load_tensors: offloaded 33/33 layers to GPU
|
|
load_tensors: CPU model buffer size = 497.31 MiB
|
|
load_tensors: CUDA0 model buffer size = 3293.12 MiB
|
|
load_all_data: no device found for buffer type CPU for async uploads
|
|
load_all_data: using async uploads for device CUDA0, buffer type CUDA0, backend CUDA0
|
|
............................................................................
|
|
llama_context: constructing llama_context
|
|
llama_context: n_seq_max = 1
|
|
llama_context: n_ctx = 16384
|
|
llama_context: n_ctx_seq = 16384
|
|
llama_context: n_batch = 128
|
|
llama_context: n_ubatch = 128
|
|
llama_context: causal_attn = 1
|
|
llama_context: flash_attn = enabled
|
|
llama_context: kv_unified = false
|
|
llama_context: freq_base = 10000000.0
|
|
llama_context: freq_scale = 1
|
|
llama_context: n_ctx_seq (16384) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
|
|
set_abort_callback: call
|
|
llama_context: CUDA_Host output buffer size = 0.95 MiB
|
|
llama_kv_cache: layer 0: filtered
|
|
llama_kv_cache: layer 1: filtered
|
|
llama_kv_cache: layer 2: filtered
|
|
llama_kv_cache: layer 3: dev = CUDA0
|
|
llama_kv_cache: layer 4: filtered
|
|
llama_kv_cache: layer 5: filtered
|
|
llama_kv_cache: layer 6: filtered
|
|
llama_kv_cache: layer 7: dev = CUDA0
|
|
llama_kv_cache: layer 8: filtered
|
|
llama_kv_cache: layer 9: filtered
|
|
llama_kv_cache: layer 10: filtered
|
|
llama_kv_cache: layer 11: dev = CUDA0
|
|
llama_kv_cache: layer 12: filtered
|
|
llama_kv_cache: layer 13: filtered
|
|
llama_kv_cache: layer 14: filtered
|
|
llama_kv_cache: layer 15: dev = CUDA0
|
|
llama_kv_cache: layer 16: filtered
|
|
llama_kv_cache: layer 17: filtered
|
|
llama_kv_cache: layer 18: filtered
|
|
llama_kv_cache: layer 19: dev = CUDA0
|
|
llama_kv_cache: layer 20: filtered
|
|
llama_kv_cache: layer 21: filtered
|
|
llama_kv_cache: layer 22: filtered
|
|
llama_kv_cache: layer 23: dev = CUDA0
|
|
llama_kv_cache: layer 24: filtered
|
|
llama_kv_cache: layer 25: filtered
|
|
llama_kv_cache: layer 26: filtered
|
|
llama_kv_cache: layer 27: dev = CUDA0
|
|
llama_kv_cache: layer 28: filtered
|
|
llama_kv_cache: layer 29: filtered
|
|
llama_kv_cache: layer 30: filtered
|
|
llama_kv_cache: layer 31: dev = CUDA0
|
|
llama_kv_cache: CUDA0 KV buffer size = 512.00 MiB
|
|
llama_kv_cache: size = 512.00 MiB ( 16384 cells, 8 layers, 1/1 seqs), K (f16): 256.00 MiB, V (f16): 256.00 MiB
|
|
llama_memory_recurrent, layer 0: dev = CUDA0
|
|
llama_memory_recurrent, layer 1: dev = CUDA0
|
|
llama_memory_recurrent, layer 2: dev = CUDA0
|
|
llama_memory_recurrent: layer 3: skipped
|
|
llama_memory_recurrent, layer 4: dev = CUDA0
|
|
llama_memory_recurrent, layer 5: dev = CUDA0
|
|
llama_memory_recurrent, layer 6: dev = CUDA0
|
|
llama_memory_recurrent: layer 7: skipped
|
|
llama_memory_recurrent, layer 8: dev = CUDA0
|
|
llama_memory_recurrent, layer 9: dev = CUDA0
|
|
llama_memory_recurrent, layer 10: dev = CUDA0
|
|
llama_memory_recurrent: layer 11: skipped
|
|
llama_memory_recurrent, layer 12: dev = CUDA0
|
|
llama_memory_recurrent, layer 13: dev = CUDA0
|
|
llama_memory_recurrent, layer 14: dev = CUDA0
|
|
llama_memory_recurrent: layer 15: skipped
|
|
llama_memory_recurrent, layer 16: dev = CUDA0
|
|
llama_memory_recurrent, layer 17: dev = CUDA0
|
|
llama_memory_recurrent, layer 18: dev = CUDA0
|
|
llama_memory_recurrent: layer 19: skipped
|
|
llama_memory_recurrent, layer 20: dev = CUDA0
|
|
llama_memory_recurrent, layer 21: dev = CUDA0
|
|
llama_memory_recurrent, layer 22: dev = CUDA0
|
|
llama_memory_recurrent: layer 23: skipped
|
|
llama_memory_recurrent, layer 24: dev = CUDA0
|
|
llama_memory_recurrent, layer 25: dev = CUDA0
|
|
llama_memory_recurrent, layer 26: dev = CUDA0
|
|
llama_memory_recurrent: layer 27: skipped
|
|
llama_memory_recurrent, layer 28: dev = CUDA0
|
|
llama_memory_recurrent, layer 29: dev = CUDA0
|
|
llama_memory_recurrent, layer 30: dev = CUDA0
|
|
llama_memory_recurrent: layer 31: skipped
|
|
llama_memory_recurrent: CUDA0 RS buffer size = 50.25 MiB
|
|
llama_memory_recurrent: size = 50.25 MiB ( 1 cells, 32 layers, 1 seqs), R (f32): 2.25 MiB, S (f32): 48.00 MiB
|
|
llama_context: enumerating backends
|
|
llama_context: backend_ptrs.size() = 2
|
|
sched_reserve: reserving ...
|
|
sched_reserve: max_nodes = 13664
|
|
sched_reserve: reserving full memory module
|
|
sched_reserve: worst-case: n_tokens = 128, n_seqs = 1, n_outputs = 1
|
|
sched_reserve: resolving fused Gated Delta Net support:
|
|
graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1
|
|
sched_reserve: fused Gated Delta Net (autoregressive) enabled
|
|
graph_reserve: reserving a graph for ubatch with n_tokens = 16, n_seqs = 1, n_outputs = 16
|
|
sched_reserve: fused Gated Delta Net (chunked) enabled
|
|
graph_reserve: reserving a graph for ubatch with n_tokens = 128, n_seqs = 1, n_outputs = 128
|
|
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 = 128, n_seqs = 1, n_outputs = 128
|
|
sched_reserve: CUDA0 compute buffer size = 122.50 MiB
|
|
sched_reserve: CUDA_Host compute buffer size = 10.50 MiB
|
|
sched_reserve: graph nodes = 1833
|
|
sched_reserve: graph splits = 2
|
|
sched_reserve: reserve took 11.26 ms, sched copies = 1
|
|
set_warmup: value = 1
|
|
set_warmup: value = 0
|
|
ggml_backend_cuda_graph_compute: CUDA graph warmup complete
|