$ ~/llama.cpp/build/bin/llama-server -m /models/Llama-3.3-70B-Instruct-Q8_0.gguf --port 8000 -t 8 -ngl 81 -c 15360 --jinja
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA A800-SXM4-80GB MIG 7g.80gb, compute capability 8.0, VMM: yes
build: 5002 (2c3f8b85) with x86_64-conda-linux-gnu-cc (conda-forge gcc 11.4.0-13) 11.4.0 for x86_64-conda-linux-gnu
system info: n_threads = 8, n_threads_batch = 8, total_threads = 256

system_info: n_threads = 8 (n_threads_batch = 8) / 256 | CUDA : ARCHS = 500,610,700,750,800 | USE_GRAPHS = 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 | AARCH64_REPACK = 1 | 

main: binding port with default address family
main: HTTP server is listening, hostname: 127.0.0.1, port: 8000, http threads: 255
main: loading model
srv    load_model: loading model '/models/Llama-3.3-70B-Instruct-Q8_0.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA A800-SXM4-80GB MIG 7g.80gb) - 80839 MiB free
llama_model_loader: loaded meta data with 33 key-value pairs and 724 tensors from /models/Llama-3.3-70B-Instruct-Q8_0.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.size_label str              = 71B
llama_model_loader: - kv   3:                            general.license str              = llama3.3
llama_model_loader: - kv   4:                   general.base_model.count u32              = 1
llama_model_loader: - kv   5:                  general.base_model.0.name str              = Llama 3.1 70B
llama_model_loader: - kv   6:          general.base_model.0.organization str              = Meta Llama
llama_model_loader: - kv   7:              general.base_model.0.repo_url str              = https://huggingface.co/meta-llama/Lla...
llama_model_loader: - kv   8:                               general.tags arr[str,5]       = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv   9:                          general.languages arr[str,8]       = ["en", "fr", "it", "pt", "hi", "es", ...
llama_model_loader: - kv  10:                          llama.block_count u32              = 80
llama_model_loader: - kv  11:                       llama.context_length u32              = 131072
llama_model_loader: - kv  12:                     llama.embedding_length u32              = 8192
llama_model_loader: - kv  13:                  llama.feed_forward_length u32              = 28672
llama_model_loader: - kv  14:                 llama.attention.head_count u32              = 64
llama_model_loader: - kv  15:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  16:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  17:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  18:                 llama.attention.key_length u32              = 128
llama_model_loader: - kv  19:               llama.attention.value_length u32              = 128
llama_model_loader: - kv  20:                          general.file_type u32              = 7
llama_model_loader: - kv  21:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  22:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = llama-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              = 128009
llama_model_loader: - kv  30:            tokenizer.ggml.padding_token_id u32              = 128004
llama_model_loader: - kv  31:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv  32:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  162 tensors
llama_model_loader: - type q8_0:  562 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 69.82 GiB (8.50 BPW) 
load: special tokens cache size = 256
load: token to piece cache size = 0.7999 MB
print_info: arch             = llama
print_info: vocab_only       = 0
print_info: n_ctx_train      = 131072
print_info: n_embd           = 8192
print_info: n_layer          = 80
print_info: n_head           = 64
print_info: n_head_kv        = 8
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_swa_pattern    = 1
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 8
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             = 28672
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  = 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       = 70B
print_info: model params     = 70.55 B
print_info: general.name     = n/a
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        = 128009 '<|eot_id|>'
print_info: EOT token        = 128009 '<|eot_id|>'
print_info: EOM token        = 128008 '<|eom_id|>'
print_info: PAD token        = 128004 '<|finetune_right_pad_id|>'
print_info: LF token         = 198 'Ċ'
print_info: EOG token        = 128008 '<|eom_id|>'
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 80 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 81/81 layers to GPU
load_tensors:        CUDA0 model buffer size = 70429.66 MiB
load_tensors:   CPU_Mapped model buffer size =  1064.62 MiB
...................................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 15360
llama_context: n_ctx_per_seq = 15360
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 (15360) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     0.49 MiB
init: kv_size = 15360, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 80, can_shift = 1
init:      CUDA0 KV buffer size =  4800.00 MiB
llama_context: KV self size  = 4800.00 MiB, K (f16): 2400.00 MiB, V (f16): 2400.00 MiB
llama_context:      CUDA0 compute buffer size =  2014.00 MiB
llama_context:  CUDA_Host compute buffer size =    46.01 MiB
llama_context: graph nodes  = 2726
llama_context: graph splits = 2
common_init_from_params: setting dry_penalty_last_n to ctx_size = 15360
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 = 15360
main: model loaded
main: chat template, chat_template: {{- bos_token }}
{%- if custom_tools is defined %}
    {%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
    {%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
    {%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
    {%- set tools = none %}
{%- endif %}

{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
    {%- set system_message = messages[0]['content']|trim %}
    {%- set messages = messages[1:] %}
{%- else %}
    {%- set system_message = "" %}
{%- endif %}

{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
    {{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
    {{- "Do not use variables.\n\n" }}
    {%- for t in tools %}
        {{- t | tojson(indent=4) }}
        {{- "\n\n" }}
    {%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}

{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
    {#- Extract the first user message so we can plug it in here #}
    {%- if messages | length != 0 %}
        {%- set first_user_message = messages[0]['content']|trim %}
        {%- set messages = messages[1:] %}
    {%- else %}
        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
    {{- "Given the following functions, please respond with a JSON for a function call " }}
    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
    {{- "Do not use variables.\n\n" }}
    {%- for t in tools %}
        {{- t | tojson(indent=4) }}
        {{- "\n\n" }}
    {%- endfor %}
    {{- first_user_message + "<|eot_id|>"}}
{%- endif %}

{%- for message in messages %}
    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
    {%- elif 'tool_calls' in message %}
        {%- if not message.tool_calls|length == 1 %}
            {{- raise_exception("This model only supports single tool-calls at once!") }}
        {%- endif %}
        {%- set tool_call = message.tool_calls[0].function %}
        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
            {%- for arg_name, arg_val in tool_call.arguments | items %}
                {{- arg_name + '="' + arg_val + '"' }}
                {%- if not loop.last %}
                    {{- ", " }}
                {%- endif %}
                {%- endfor %}
            {{- ")" }}
        {%- else  %}
            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
            {{- '{"name": "' + tool_call.name + '", ' }}
            {{- '"parameters": ' }}
            {{- tool_call.arguments | tojson }}
            {{- "}" }}
        {%- endif %}
        {%- if builtin_tools is defined %}
            {#- This means we're in ipython mode #}
            {{- "<|eom_id|>" }}
        {%- else %}
            {{- "<|eot_id|>" }}
        {%- endif %}
    {%- elif message.role == "tool" or message.role == "ipython" %}
        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
        {%- if message.content is mapping or message.content is iterable %}
            {{- message.content | tojson }}
        {%- else %}
            {{- message.content }}
        {%- endif %}
        {{- "<|eot_id|>" }}
    {%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}
, example_format: '<|start_header_id|>system<|end_header_id|>

Cutting Knowledge Date: December 2023
Today Date: 26 Jul 2024

You are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>

Hello<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Hi there<|eot_id|><|start_header_id|>user<|end_header_id|>

How are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

'
main: server is listening on http://127.0.0.1:8000 - starting the main loop
srv  update_slots: all slots are idle