ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon RX 9070, gfx1201 (0x1201), VMM: no, Wave Size: 32
build: 5631 (1f7d50b2) with cc (GCC) 15.1.1 20250425 for x86_64-pc-linux-gnu
system info: n_threads = 12, n_threads_batch = 12, total_threads = 12

system_info: n_threads = 12 (n_threads_batch = 12) / 12 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | 

main: binding port with default address family
main: HTTP server is listening, hostname: 127.0.0.1, port: 8080, http threads: 11
main: loading model
srv    load_model: loading model './gemma-3-12b-it-Q4_K_M.gguf'
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon RX 9070) - 15768 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 626 tensors from ./gemma-3-12b-it-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              = gemma3
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Gemma-3-12B-It
llama_model_loader: - kv   3:                           general.finetune str              = it
llama_model_loader: - kv   4:                           general.basename str              = Gemma-3-12B-It
llama_model_loader: - kv   5:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   6:                         general.size_label str              = 12B
llama_model_loader: - kv   7:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   8:                      gemma3.context_length u32              = 131072
llama_model_loader: - kv   9:                    gemma3.embedding_length u32              = 3840
llama_model_loader: - kv  10:                         gemma3.block_count u32              = 48
llama_model_loader: - kv  11:                 gemma3.feed_forward_length u32              = 15360
llama_model_loader: - kv  12:                gemma3.attention.head_count u32              = 16
llama_model_loader: - kv  13:    gemma3.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  14:                gemma3.attention.key_length u32              = 256
llama_model_loader: - kv  15:              gemma3.attention.value_length u32              = 256
llama_model_loader: - kv  16:                      gemma3.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  17:            gemma3.attention.sliding_window u32              = 1024
llama_model_loader: - kv  18:             gemma3.attention.head_count_kv u32              = 8
llama_model_loader: - kv  19:                   gemma3.rope.scaling.type str              = linear
llama_model_loader: - kv  20:                 gemma3.rope.scaling.factor f32              = 8.000000
llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = default
llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,262208]  = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv  24:                      tokenizer.ggml.scores arr[f32,262208]  = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv  25:                  tokenizer.ggml.token_type arr[i32,262208]  = [3, 3, 3, 3, 3, 4, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 2
llama_model_loader: - kv  27:                tokenizer.ggml.eos_token_id u32              = 106
llama_model_loader: - kv  28:            tokenizer.ggml.unknown_token_id u32              = 3
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 0
llama_model_loader: - kv  30:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  31:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {{ bos_token }}\n{%- if messages[0]['r...
llama_model_loader: - kv  33:            tokenizer.ggml.add_space_prefix bool             = false
llama_model_loader: - kv  34:               general.quantization_version u32              = 2
llama_model_loader: - kv  35:                          general.file_type u32              = 18
llama_model_loader: - kv  36:                      quantize.imatrix.file str              = gemma-3-12b-it-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv  37:                   quantize.imatrix.dataset str              = unsloth_calibration_gemma-3-12b-it.txt
llama_model_loader: - kv  38:             quantize.imatrix.entries_count i32              = 336
llama_model_loader: - kv  39:              quantize.imatrix.chunks_count i32              = 663
llama_model_loader: - type  f32:  289 tensors
llama_model_loader: - type q8_0:  165 tensors
llama_model_loader: - type q6_K:  172 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q6_K
print_info: file size   = 9.82 GiB (7.17 BPW) 
load: special tokens cache size = 6415
load: token to piece cache size = 1.9446 MB
print_info: arch             = gemma3
print_info: vocab_only       = 0
print_info: n_ctx_train      = 131072
print_info: n_embd           = 3840
print_info: n_layer          = 48
print_info: n_head           = 16
print_info: n_head_kv        = 8
print_info: n_rot            = 256
print_info: n_swa            = 1024
print_info: is_swa_any       = 1
print_info: n_embd_head_k    = 256
print_info: n_embd_head_v    = 256
print_info: n_gqa            = 2
print_info: n_embd_k_gqa     = 2048
print_info: n_embd_v_gqa     = 2048
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     = 6.2e-02
print_info: n_ff             = 15360
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        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 0.125
print_info: n_ctx_orig_yarn  = 131072
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       = 12B
print_info: model params     = 11.77 B
print_info: general.name     = Gemma-3-12B-It
print_info: vocab type       = SPM
print_info: n_vocab          = 262208
print_info: n_merges         = 0
print_info: BOS token        = 2 '<bos>'
print_info: EOS token        = 106 '<end_of_turn>'
print_info: EOT token        = 106 '<end_of_turn>'
print_info: UNK token        = 3 '<unk>'
print_info: PAD token        = 0 '<pad>'
print_info: LF token         = 248 '<0x0A>'
print_info: EOG token        = 106 '<end_of_turn>'
print_info: max token length = 48
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 48 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 49/49 layers to GPU
load_tensors:        ROCm0 model buffer size = 10060.86 MiB
load_tensors:   CPU_Mapped model buffer size =  1020.25 MiB
...................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 50000
llama_context: n_ctx_per_seq = 50000
llama_context: n_batch       = 2048
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 0.9
llama_context: n_ctx_per_seq (50000) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context:  ROCm_Host  output buffer size =     1.00 MiB
llama_kv_cache_unified_iswa: creating non-SWA KV cache, size = 50016 cells
llama_kv_cache_unified:      ROCm0 KV buffer size =  3126.00 MiB
llama_kv_cache_unified: size = 3126.00 MiB ( 50016 cells,   8 layers,  1 seqs), K (f16): 1563.00 MiB, V (f16): 1563.00 MiB
llama_kv_cache_unified_iswa: creating     SWA KV cache, size = 1536 cells
llama_kv_cache_unified:      ROCm0 KV buffer size =   480.00 MiB
llama_kv_cache_unified: size =  480.00 MiB (  1536 cells,  40 layers,  1 seqs), K (f16):  240.00 MiB, V (f16):  240.00 MiB
llama_context:      ROCm0 compute buffer size =  1694.69 MiB
llama_context:  ROCm_Host compute buffer size =   108.19 MiB
llama_context: graph nodes  = 2167
llama_context: graph splits = 2
common_init_from_params: KV cache shifting is not supported for this context, disabling KV cache shifting
common_init_from_params: setting dry_penalty_last_n to ctx_size = 50016
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 = 50016
main: model loaded
main: chat template, chat_template: {{ bos_token }}
{%- if messages[0]['role'] == 'system' -%}
    {%- if messages[0]['content'] is string -%}
        {%- set first_user_prefix = messages[0]['content'] + '

' -%}
    {%- else -%}
        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '

' -%}
    {%- endif -%}
    {%- set loop_messages = messages[1:] -%}
{%- else -%}
    {%- set first_user_prefix = "" -%}
    {%- set loop_messages = messages -%}
{%- endif -%}
{%- for message in loop_messages -%}
    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
    {%- endif -%}
    {%- if (message['role'] == 'assistant') -%}
        {%- set role = "model" -%}
    {%- else -%}
        {%- set role = message['role'] -%}
    {%- endif -%}
    {{ '<start_of_turn>' + role + '
' + (first_user_prefix if loop.first else "") }}
    {%- if message['content'] is string -%}
        {{ message['content'] | trim }}
    {%- elif message['content'] is iterable -%}
        {%- for item in message['content'] -%}
            {%- if item['type'] == 'image' -%}
                {{ '<start_of_image>' }}
            {%- elif item['type'] == 'text' -%}
                {{ item['text'] | trim }}
            {%- endif -%}
        {%- endfor -%}
    {%- else -%}
        {{ raise_exception("Invalid content type") }}
    {%- endif -%}
    {{ '<end_of_turn>
' }}
{%- endfor -%}
{%- if add_generation_prompt -%}
    {{'<start_of_turn>model
'}}
{%- endif -%}
, example_format: '<start_of_turn>user
You are a helpful assistant

Hello<end_of_turn>
<start_of_turn>model
Hi there<end_of_turn>
<start_of_turn>user
How are you?<end_of_turn>
<start_of_turn>model
'
main: server is listening on http://127.0.0.1:8080 - starting the main loop
srv  update_slots: all slots are idle