778 lines
52 KiB
Plaintext
778 lines
52 KiB
Plaintext
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 GeForce RTX 4060 Ti, compute capability 8.9, VMM: yes
|
|
build: 6097 (9515c613) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
|
|
system info: n_threads = 8, n_threads_batch = 8, total_threads = 16
|
|
|
|
system_info: n_threads = 8 (n_threads_batch = 8) / 16 | CUDA : ARCHS = 500,610,700,750,800,860,890 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 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: 0.0.0.0, port: 8081, http threads: 15
|
|
main: loading model
|
|
srv load_model: loading model '/home/huangfukk/models/gguf/Qwen/Qwen3-4B/Qwen3-4B-Q5_K_M.gguf'
|
|
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4060 Ti) - 15225 MiB free
|
|
llama_model_loader: loaded meta data with 28 key-value pairs and 398 tensors from /home/huangfukk/models/gguf/Qwen/Qwen3-4B/Qwen3-4B-Q5_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 = qwen3
|
|
llama_model_loader: - kv 1: general.type str = model
|
|
llama_model_loader: - kv 2: general.name str = Qwen3 4B Instruct
|
|
llama_model_loader: - kv 3: general.finetune str = Instruct
|
|
llama_model_loader: - kv 4: general.basename str = Qwen3
|
|
llama_model_loader: - kv 5: general.size_label str = 4B
|
|
llama_model_loader: - kv 6: qwen3.block_count u32 = 36
|
|
llama_model_loader: - kv 7: qwen3.context_length u32 = 40960
|
|
llama_model_loader: - kv 8: qwen3.embedding_length u32 = 2560
|
|
llama_model_loader: - kv 9: qwen3.feed_forward_length u32 = 9728
|
|
llama_model_loader: - kv 10: qwen3.attention.head_count u32 = 32
|
|
llama_model_loader: - kv 11: qwen3.attention.head_count_kv u32 = 8
|
|
llama_model_loader: - kv 12: qwen3.rope.freq_base f32 = 1000000.000000
|
|
llama_model_loader: - kv 13: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
|
|
llama_model_loader: - kv 14: qwen3.attention.key_length u32 = 128
|
|
llama_model_loader: - kv 15: qwen3.attention.value_length u32 = 128
|
|
llama_model_loader: - kv 16: tokenizer.ggml.model str = gpt2
|
|
llama_model_loader: - kv 17: tokenizer.ggml.pre str = qwen2
|
|
llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
|
|
llama_model_loader: - kv 19: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
|
|
llama_model_loader: - kv 20: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
|
|
llama_model_loader: - kv 21: tokenizer.ggml.eos_token_id u32 = 151645
|
|
llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 151643
|
|
llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 151643
|
|
llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = false
|
|
llama_model_loader: - kv 25: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
|
|
llama_model_loader: - kv 26: general.quantization_version u32 = 2
|
|
llama_model_loader: - kv 27: general.file_type u32 = 17
|
|
llama_model_loader: - type f32: 145 tensors
|
|
llama_model_loader: - type q5_K: 216 tensors
|
|
llama_model_loader: - type q6_K: 37 tensors
|
|
print_info: file format = GGUF V3 (latest)
|
|
print_info: file type = Q5_K - Medium
|
|
print_info: file size = 2.69 GiB (5.73 BPW)
|
|
load: printing all EOG tokens:
|
|
load: - 151643 ('<|endoftext|>')
|
|
load: - 151645 ('<|im_end|>')
|
|
load: - 151662 ('<|fim_pad|>')
|
|
load: - 151663 ('<|repo_name|>')
|
|
load: - 151664 ('<|file_sep|>')
|
|
load: special tokens cache size = 26
|
|
load: token to piece cache size = 0.9311 MB
|
|
print_info: arch = qwen3
|
|
print_info: vocab_only = 0
|
|
print_info: n_ctx_train = 40960
|
|
print_info: n_embd = 2560
|
|
print_info: n_layer = 36
|
|
print_info: n_head = 32
|
|
print_info: n_head_kv = 8
|
|
print_info: n_rot = 128
|
|
print_info: n_swa = 0
|
|
print_info: is_swa_any = 0
|
|
print_info: n_embd_head_k = 128
|
|
print_info: n_embd_head_v = 128
|
|
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 = 9728
|
|
print_info: n_expert = 0
|
|
print_info: n_expert_used = 0
|
|
print_info: causal attn = 1
|
|
print_info: pooling type = -1
|
|
print_info: rope type = 2
|
|
print_info: rope scaling = linear
|
|
print_info: freq_base_train = 1000000.0
|
|
print_info: freq_scale_train = 1
|
|
print_info: n_ctx_orig_yarn = 40960
|
|
print_info: rope_finetuned = unknown
|
|
print_info: model type = 4B
|
|
print_info: model params = 4.02 B
|
|
print_info: general.name = Qwen3 4B Instruct
|
|
print_info: vocab type = BPE
|
|
print_info: n_vocab = 151936
|
|
print_info: n_merges = 151387
|
|
print_info: BOS token = 151643 '<|endoftext|>'
|
|
print_info: EOS token = 151645 '<|im_end|>'
|
|
print_info: EOT token = 151645 '<|im_end|>'
|
|
print_info: PAD token = 151643 '<|endoftext|>'
|
|
print_info: LF token = 198 'Ċ'
|
|
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
|
|
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
|
|
print_info: FIM MID token = 151660 '<|fim_middle|>'
|
|
print_info: FIM PAD token = 151662 '<|fim_pad|>'
|
|
print_info: FIM REP token = 151663 '<|repo_name|>'
|
|
print_info: FIM SEP token = 151664 '<|file_sep|>'
|
|
print_info: EOG token = 151643 '<|endoftext|>'
|
|
print_info: EOG token = 151645 '<|im_end|>'
|
|
print_info: EOG token = 151662 '<|fim_pad|>'
|
|
print_info: EOG token = 151663 '<|repo_name|>'
|
|
print_info: EOG token = 151664 '<|file_sep|>'
|
|
print_info: max token length = 256
|
|
load_tensors: loading model tensors, this can take a while... (mmap = true)
|
|
load_tensors: offloading 36 repeating layers to GPU
|
|
load_tensors: offloaded 36/37 layers to GPU
|
|
load_tensors: CUDA0 model buffer size = 2445.68 MiB
|
|
load_tensors: CPU_Mapped model buffer size = 304.29 MiB
|
|
..........................................................................................
|
|
llama_context: constructing llama_context
|
|
llama_context: n_seq_max = 1
|
|
llama_context: n_ctx = 8192
|
|
llama_context: n_ctx_per_seq = 8192
|
|
llama_context: n_batch = 2048
|
|
llama_context: n_ubatch = 512
|
|
llama_context: causal_attn = 1
|
|
llama_context: flash_attn = 0
|
|
llama_context: kv_unified = false
|
|
llama_context: freq_base = 1000000.0
|
|
llama_context: freq_scale = 1
|
|
llama_context: n_ctx_per_seq (8192) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
|
|
llama_context: CPU output buffer size = 0.58 MiB
|
|
llama_kv_cache_unified: CUDA0 KV buffer size = 1152.00 MiB
|
|
llama_kv_cache_unified: size = 1152.00 MiB ( 8192 cells, 36 layers, 1/1 seqs), K (f16): 576.00 MiB, V (f16): 576.00 MiB
|
|
llama_context: CUDA0 compute buffer size = 606.03 MiB
|
|
llama_context: CUDA_Host compute buffer size = 25.01 MiB
|
|
llama_context: graph nodes = 1410
|
|
llama_context: graph splits = 4 (with bs=512), 3 (with bs=1)
|
|
common_init_from_params: added <|endoftext|> logit bias = -inf
|
|
common_init_from_params: added <|im_end|> logit bias = -inf
|
|
common_init_from_params: added <|fim_pad|> logit bias = -inf
|
|
common_init_from_params: added <|repo_name|> logit bias = -inf
|
|
common_init_from_params: added <|file_sep|> logit bias = -inf
|
|
common_init_from_params: setting dry_penalty_last_n to ctx_size = 8192
|
|
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 = 8192
|
|
main: model loaded
|
|
main: chat template, chat_template: {%- if tools %}
|
|
{{- '<|im_start|>system\n' }}
|
|
{%- if messages[0].role == 'system' %}
|
|
{{- messages[0].content + '\n\n' }}
|
|
{%- endif %}
|
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
|
{%- for tool in tools %}
|
|
{{- "\n" }}
|
|
{{- tool | tojson }}
|
|
{%- endfor %}
|
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
|
{%- else %}
|
|
{%- if messages[0].role == 'system' %}
|
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
|
{%- endif %}
|
|
{%- endif %}
|
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
|
{%- for index in range(ns.last_query_index, -1, -1) %}
|
|
{%- set message = messages[index] %}
|
|
{%- if ns.multi_step_tool and message.role == "user" and not('<tool_response>' in message.content and '</tool_response>' in message.content) %}
|
|
{%- set ns.multi_step_tool = false %}
|
|
{%- set ns.last_query_index = index %}
|
|
{%- endif %}
|
|
{%- endfor %}
|
|
{%- for message in messages %}
|
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
|
{%- elif message.role == "assistant" %}
|
|
{%- set content = message.content %}
|
|
{%- set reasoning_content = '' %}
|
|
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
|
{%- set reasoning_content = message.reasoning_content %}
|
|
{%- else %}
|
|
{%- if '</think>' in message.content %}
|
|
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
|
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
|
{%- endif %}
|
|
{%- endif %}
|
|
{%- if loop.index0 > ns.last_query_index %}
|
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
|
{%- else %}
|
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
|
{%- endif %}
|
|
{%- else %}
|
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
|
{%- endif %}
|
|
{%- if message.tool_calls %}
|
|
{%- for tool_call in message.tool_calls %}
|
|
{%- if (loop.first and content) or (not loop.first) %}
|
|
{{- '\n' }}
|
|
{%- endif %}
|
|
{%- if tool_call.function %}
|
|
{%- set tool_call = tool_call.function %}
|
|
{%- endif %}
|
|
{{- '<tool_call>\n{"name": "' }}
|
|
{{- tool_call.name }}
|
|
{{- '", "arguments": ' }}
|
|
{%- if tool_call.arguments is string %}
|
|
{{- tool_call.arguments }}
|
|
{%- else %}
|
|
{{- tool_call.arguments | tojson }}
|
|
{%- endif %}
|
|
{{- '}\n</tool_call>' }}
|
|
{%- endfor %}
|
|
{%- endif %}
|
|
{{- '<|im_end|>\n' }}
|
|
{%- elif message.role == "tool" %}
|
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
|
{{- '<|im_start|>user' }}
|
|
{%- endif %}
|
|
{{- '\n<tool_response>\n' }}
|
|
{{- message.content }}
|
|
{{- '\n</tool_response>' }}
|
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
|
{{- '<|im_end|>\n' }}
|
|
{%- endif %}
|
|
{%- endif %}
|
|
{%- endfor %}
|
|
{%- if add_generation_prompt %}
|
|
{{- '<|im_start|>assistant\n' }}
|
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
|
{{- '<think>\n\n</think>\n\n' }}
|
|
{%- endif %}
|
|
{%- endif %}, example_format: '<|im_start|>system
|
|
You are a helpful assistant<|im_end|>
|
|
<|im_start|>user
|
|
Hello<|im_end|>
|
|
<|im_start|>assistant
|
|
Hi there<|im_end|>
|
|
<|im_start|>user
|
|
How are you?<|im_end|>
|
|
<|im_start|>assistant
|
|
'
|
|
main: server is listening on http://0.0.0.0:8081 - starting the main loop
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: GET /health 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 0 | processing task
|
|
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 362
|
|
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
|
|
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 362, n_tokens = 362, progress = 1.000000
|
|
slot update_slots: id 0 | task 0 | prompt done, n_past = 362, n_tokens = 362
|
|
slot release: id 0 | task 0 | stop processing: n_past = 371, truncated = 0
|
|
slot print_timing: id 0 | task 0 |
|
|
prompt eval time = 270.89 ms / 362 tokens ( 0.75 ms per token, 1336.34 tokens per second)
|
|
eval time = 231.47 ms / 10 tokens ( 23.15 ms per token, 43.20 tokens per second)
|
|
total time = 502.36 ms / 372 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 11 | processing task
|
|
slot update_slots: id 0 | task 11 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2341
|
|
slot update_slots: id 0 | task 11 | kv cache rm [5, end)
|
|
slot update_slots: id 0 | task 11 | prompt processing progress, n_past = 2053, n_tokens = 2048, progress = 0.874840
|
|
slot update_slots: id 0 | task 11 | kv cache rm [2053, end)
|
|
slot update_slots: id 0 | task 11 | prompt processing progress, n_past = 2341, n_tokens = 288, progress = 0.997864
|
|
slot update_slots: id 0 | task 11 | prompt done, n_past = 2341, n_tokens = 288
|
|
slot release: id 0 | task 11 | stop processing: n_past = 2381, truncated = 0
|
|
slot print_timing: id 0 | task 11 |
|
|
prompt eval time = 819.09 ms / 2336 tokens ( 0.35 ms per token, 2851.93 tokens per second)
|
|
eval time = 1127.49 ms / 41 tokens ( 27.50 ms per token, 36.36 tokens per second)
|
|
total time = 1946.58 ms / 2377 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 54 | processing task
|
|
slot update_slots: id 0 | task 54 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 369
|
|
slot update_slots: id 0 | task 54 | kv cache rm [5, end)
|
|
slot update_slots: id 0 | task 54 | prompt processing progress, n_past = 369, n_tokens = 364, progress = 0.986450
|
|
slot update_slots: id 0 | task 54 | prompt done, n_past = 369, n_tokens = 364
|
|
slot release: id 0 | task 54 | stop processing: n_past = 378, truncated = 0
|
|
slot print_timing: id 0 | task 54 |
|
|
prompt eval time = 284.40 ms / 364 tokens ( 0.78 ms per token, 1279.91 tokens per second)
|
|
eval time = 236.35 ms / 10 tokens ( 23.64 ms per token, 42.31 tokens per second)
|
|
total time = 520.75 ms / 374 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 65 | processing task
|
|
slot update_slots: id 0 | task 65 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2770
|
|
slot update_slots: id 0 | task 65 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 65 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.739350
|
|
slot update_slots: id 0 | task 65 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 65 | prompt processing progress, n_past = 2770, n_tokens = 719, progress = 0.998917
|
|
slot update_slots: id 0 | task 65 | prompt done, n_past = 2770, n_tokens = 719
|
|
slot release: id 0 | task 65 | stop processing: n_past = 3091, truncated = 0
|
|
slot print_timing: id 0 | task 65 |
|
|
prompt eval time = 1016.37 ms / 2767 tokens ( 0.37 ms per token, 2722.42 tokens per second)
|
|
eval time = 8133.98 ms / 322 tokens ( 25.26 ms per token, 39.59 tokens per second)
|
|
total time = 9150.35 ms / 3089 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 389 | processing task
|
|
slot update_slots: id 0 | task 389 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 372
|
|
slot update_slots: id 0 | task 389 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 389 | prompt processing progress, n_past = 372, n_tokens = 369, progress = 0.991935
|
|
slot update_slots: id 0 | task 389 | prompt done, n_past = 372, n_tokens = 369
|
|
slot release: id 0 | task 389 | stop processing: n_past = 381, truncated = 0
|
|
slot print_timing: id 0 | task 389 |
|
|
prompt eval time = 106.39 ms / 369 tokens ( 0.29 ms per token, 3468.40 tokens per second)
|
|
eval time = 299.47 ms / 10 tokens ( 29.95 ms per token, 33.39 tokens per second)
|
|
total time = 405.86 ms / 379 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 400 | processing task
|
|
slot update_slots: id 0 | task 400 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 400 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 400 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.738550
|
|
slot update_slots: id 0 | task 400 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 400 | prompt processing progress, n_past = 2773, n_tokens = 722, progress = 0.998918
|
|
slot update_slots: id 0 | task 400 | prompt done, n_past = 2773, n_tokens = 722
|
|
slot release: id 0 | task 400 | stop processing: n_past = 3203, truncated = 0
|
|
slot print_timing: id 0 | task 400 |
|
|
prompt eval time = 1079.61 ms / 2770 tokens ( 0.39 ms per token, 2565.73 tokens per second)
|
|
eval time = 10918.90 ms / 431 tokens ( 25.33 ms per token, 39.47 tokens per second)
|
|
total time = 11998.51 ms / 3201 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 833 | processing task
|
|
slot update_slots: id 0 | task 833 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 362
|
|
slot update_slots: id 0 | task 833 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 833 | prompt processing progress, n_past = 362, n_tokens = 359, progress = 0.991713
|
|
slot update_slots: id 0 | task 833 | prompt done, n_past = 362, n_tokens = 359
|
|
slot release: id 0 | task 833 | stop processing: n_past = 371, truncated = 0
|
|
slot print_timing: id 0 | task 833 |
|
|
prompt eval time = 336.17 ms / 359 tokens ( 0.94 ms per token, 1067.90 tokens per second)
|
|
eval time = 262.12 ms / 10 tokens ( 26.21 ms per token, 38.15 tokens per second)
|
|
total time = 598.29 ms / 369 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 844 | processing task
|
|
slot update_slots: id 0 | task 844 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2341
|
|
slot update_slots: id 0 | task 844 | kv cache rm [5, end)
|
|
slot update_slots: id 0 | task 844 | prompt processing progress, n_past = 2053, n_tokens = 2048, progress = 0.874840
|
|
slot update_slots: id 0 | task 844 | kv cache rm [2053, end)
|
|
slot update_slots: id 0 | task 844 | prompt processing progress, n_past = 2341, n_tokens = 288, progress = 0.997864
|
|
slot update_slots: id 0 | task 844 | prompt done, n_past = 2341, n_tokens = 288
|
|
slot release: id 0 | task 844 | stop processing: n_past = 2381, truncated = 0
|
|
slot print_timing: id 0 | task 844 |
|
|
prompt eval time = 829.68 ms / 2336 tokens ( 0.36 ms per token, 2815.53 tokens per second)
|
|
eval time = 1020.09 ms / 41 tokens ( 24.88 ms per token, 40.19 tokens per second)
|
|
total time = 1849.78 ms / 2377 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 887 | processing task
|
|
slot update_slots: id 0 | task 887 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 369
|
|
slot update_slots: id 0 | task 887 | kv cache rm [5, end)
|
|
slot update_slots: id 0 | task 887 | prompt processing progress, n_past = 369, n_tokens = 364, progress = 0.986450
|
|
slot update_slots: id 0 | task 887 | prompt done, n_past = 369, n_tokens = 364
|
|
slot release: id 0 | task 887 | stop processing: n_past = 378, truncated = 0
|
|
slot print_timing: id 0 | task 887 |
|
|
prompt eval time = 115.08 ms / 364 tokens ( 0.32 ms per token, 3163.04 tokens per second)
|
|
eval time = 287.74 ms / 10 tokens ( 28.77 ms per token, 34.75 tokens per second)
|
|
total time = 402.81 ms / 374 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 898 | processing task
|
|
slot update_slots: id 0 | task 898 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2770
|
|
slot update_slots: id 0 | task 898 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 898 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.739350
|
|
slot update_slots: id 0 | task 898 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 898 | prompt processing progress, n_past = 2770, n_tokens = 719, progress = 0.998917
|
|
slot update_slots: id 0 | task 898 | prompt done, n_past = 2770, n_tokens = 719
|
|
slot release: id 0 | task 898 | stop processing: n_past = 3091, truncated = 0
|
|
slot print_timing: id 0 | task 898 |
|
|
prompt eval time = 1072.94 ms / 2767 tokens ( 0.39 ms per token, 2578.88 tokens per second)
|
|
eval time = 8647.49 ms / 322 tokens ( 26.86 ms per token, 37.24 tokens per second)
|
|
total time = 9720.43 ms / 3089 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 1222 | processing task
|
|
slot update_slots: id 0 | task 1222 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 362
|
|
slot update_slots: id 0 | task 1222 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 1222 | prompt processing progress, n_past = 362, n_tokens = 359, progress = 0.991713
|
|
slot update_slots: id 0 | task 1222 | prompt done, n_past = 362, n_tokens = 359
|
|
slot release: id 0 | task 1222 | stop processing: n_past = 371, truncated = 0
|
|
slot print_timing: id 0 | task 1222 |
|
|
prompt eval time = 285.45 ms / 359 tokens ( 0.80 ms per token, 1257.64 tokens per second)
|
|
eval time = 242.33 ms / 10 tokens ( 24.23 ms per token, 41.27 tokens per second)
|
|
total time = 527.79 ms / 369 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 1233 | processing task
|
|
slot update_slots: id 0 | task 1233 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2341
|
|
slot update_slots: id 0 | task 1233 | kv cache rm [5, end)
|
|
slot update_slots: id 0 | task 1233 | prompt processing progress, n_past = 2053, n_tokens = 2048, progress = 0.874840
|
|
slot update_slots: id 0 | task 1233 | kv cache rm [2053, end)
|
|
slot update_slots: id 0 | task 1233 | prompt processing progress, n_past = 2341, n_tokens = 288, progress = 0.997864
|
|
slot update_slots: id 0 | task 1233 | prompt done, n_past = 2341, n_tokens = 288
|
|
slot release: id 0 | task 1233 | stop processing: n_past = 2381, truncated = 0
|
|
slot print_timing: id 0 | task 1233 |
|
|
prompt eval time = 879.99 ms / 2336 tokens ( 0.38 ms per token, 2654.58 tokens per second)
|
|
eval time = 959.80 ms / 41 tokens ( 23.41 ms per token, 42.72 tokens per second)
|
|
total time = 1839.78 ms / 2377 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 1276 | processing task
|
|
slot update_slots: id 0 | task 1276 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 369
|
|
slot update_slots: id 0 | task 1276 | kv cache rm [5, end)
|
|
slot update_slots: id 0 | task 1276 | prompt processing progress, n_past = 369, n_tokens = 364, progress = 0.986450
|
|
slot update_slots: id 0 | task 1276 | prompt done, n_past = 369, n_tokens = 364
|
|
slot release: id 0 | task 1276 | stop processing: n_past = 378, truncated = 0
|
|
slot print_timing: id 0 | task 1276 |
|
|
prompt eval time = 106.37 ms / 364 tokens ( 0.29 ms per token, 3422.11 tokens per second)
|
|
eval time = 212.27 ms / 10 tokens ( 21.23 ms per token, 47.11 tokens per second)
|
|
total time = 318.64 ms / 374 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 1287 | processing task
|
|
slot update_slots: id 0 | task 1287 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2770
|
|
slot update_slots: id 0 | task 1287 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 1287 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.739350
|
|
slot update_slots: id 0 | task 1287 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 1287 | prompt processing progress, n_past = 2770, n_tokens = 719, progress = 0.998917
|
|
slot update_slots: id 0 | task 1287 | prompt done, n_past = 2770, n_tokens = 719
|
|
slot release: id 0 | task 1287 | stop processing: n_past = 3091, truncated = 0
|
|
slot print_timing: id 0 | task 1287 |
|
|
prompt eval time = 1072.57 ms / 2767 tokens ( 0.39 ms per token, 2579.79 tokens per second)
|
|
eval time = 7776.71 ms / 322 tokens ( 24.15 ms per token, 41.41 tokens per second)
|
|
total time = 8849.27 ms / 3089 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 1611 | processing task
|
|
slot update_slots: id 0 | task 1611 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 372
|
|
slot update_slots: id 0 | task 1611 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 1611 | prompt processing progress, n_past = 372, n_tokens = 369, progress = 0.991935
|
|
slot update_slots: id 0 | task 1611 | prompt done, n_past = 372, n_tokens = 369
|
|
slot release: id 0 | task 1611 | stop processing: n_past = 381, truncated = 0
|
|
slot print_timing: id 0 | task 1611 |
|
|
prompt eval time = 119.55 ms / 369 tokens ( 0.32 ms per token, 3086.70 tokens per second)
|
|
eval time = 231.63 ms / 10 tokens ( 23.16 ms per token, 43.17 tokens per second)
|
|
total time = 351.17 ms / 379 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 1622 | processing task
|
|
slot update_slots: id 0 | task 1622 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 1622 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 1622 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.738550
|
|
slot update_slots: id 0 | task 1622 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 1622 | prompt processing progress, n_past = 2773, n_tokens = 722, progress = 0.998918
|
|
slot update_slots: id 0 | task 1622 | prompt done, n_past = 2773, n_tokens = 722
|
|
slot release: id 0 | task 1622 | stop processing: n_past = 3203, truncated = 0
|
|
slot print_timing: id 0 | task 1622 |
|
|
prompt eval time = 995.24 ms / 2770 tokens ( 0.36 ms per token, 2783.26 tokens per second)
|
|
eval time = 10935.74 ms / 431 tokens ( 25.37 ms per token, 39.41 tokens per second)
|
|
total time = 11930.97 ms / 3201 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 2055 | processing task
|
|
slot update_slots: id 0 | task 2055 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 372
|
|
slot update_slots: id 0 | task 2055 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 2055 | prompt processing progress, n_past = 372, n_tokens = 369, progress = 0.991935
|
|
slot update_slots: id 0 | task 2055 | prompt done, n_past = 372, n_tokens = 369
|
|
slot release: id 0 | task 2055 | stop processing: n_past = 381, truncated = 0
|
|
slot print_timing: id 0 | task 2055 |
|
|
prompt eval time = 98.64 ms / 369 tokens ( 0.27 ms per token, 3740.95 tokens per second)
|
|
eval time = 209.16 ms / 10 tokens ( 20.92 ms per token, 47.81 tokens per second)
|
|
total time = 307.80 ms / 379 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 2066 | processing task
|
|
slot update_slots: id 0 | task 2066 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 2066 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 2066 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.738550
|
|
slot update_slots: id 0 | task 2066 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 2066 | prompt processing progress, n_past = 2773, n_tokens = 722, progress = 0.998918
|
|
slot update_slots: id 0 | task 2066 | prompt done, n_past = 2773, n_tokens = 722
|
|
slot release: id 0 | task 2066 | stop processing: n_past = 3203, truncated = 0
|
|
slot print_timing: id 0 | task 2066 |
|
|
prompt eval time = 1062.14 ms / 2770 tokens ( 0.38 ms per token, 2607.93 tokens per second)
|
|
eval time = 10610.14 ms / 431 tokens ( 24.62 ms per token, 40.62 tokens per second)
|
|
total time = 11672.28 ms / 3201 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 2499 | processing task
|
|
slot update_slots: id 0 | task 2499 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 372
|
|
slot update_slots: id 0 | task 2499 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 2499 | prompt processing progress, n_past = 372, n_tokens = 369, progress = 0.991935
|
|
slot update_slots: id 0 | task 2499 | prompt done, n_past = 372, n_tokens = 369
|
|
slot release: id 0 | task 2499 | stop processing: n_past = 381, truncated = 0
|
|
slot print_timing: id 0 | task 2499 |
|
|
prompt eval time = 108.99 ms / 369 tokens ( 0.30 ms per token, 3385.72 tokens per second)
|
|
eval time = 219.85 ms / 10 tokens ( 21.99 ms per token, 45.49 tokens per second)
|
|
total time = 328.84 ms / 379 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 2510 | processing task
|
|
slot update_slots: id 0 | task 2510 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 2510 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 2510 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.738550
|
|
slot update_slots: id 0 | task 2510 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 2510 | prompt processing progress, n_past = 2773, n_tokens = 722, progress = 0.998918
|
|
slot update_slots: id 0 | task 2510 | prompt done, n_past = 2773, n_tokens = 722
|
|
slot release: id 0 | task 2510 | stop processing: n_past = 3148, truncated = 0
|
|
slot print_timing: id 0 | task 2510 |
|
|
prompt eval time = 1023.49 ms / 2770 tokens ( 0.37 ms per token, 2706.44 tokens per second)
|
|
eval time = 8951.46 ms / 376 tokens ( 23.81 ms per token, 42.00 tokens per second)
|
|
total time = 9974.94 ms / 3146 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 2888 | processing task
|
|
slot update_slots: id 0 | task 2888 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 370
|
|
slot update_slots: id 0 | task 2888 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 2888 | prompt processing progress, n_past = 370, n_tokens = 367, progress = 0.991892
|
|
slot update_slots: id 0 | task 2888 | prompt done, n_past = 370, n_tokens = 367
|
|
slot release: id 0 | task 2888 | stop processing: n_past = 379, truncated = 0
|
|
slot print_timing: id 0 | task 2888 |
|
|
prompt eval time = 102.91 ms / 367 tokens ( 0.28 ms per token, 3566.40 tokens per second)
|
|
eval time = 210.61 ms / 10 tokens ( 21.06 ms per token, 47.48 tokens per second)
|
|
total time = 313.51 ms / 377 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 2899 | processing task
|
|
slot update_slots: id 0 | task 2899 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2771
|
|
slot update_slots: id 0 | task 2899 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 2899 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.739083
|
|
slot update_slots: id 0 | task 2899 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 2899 | prompt processing progress, n_past = 2771, n_tokens = 720, progress = 0.998917
|
|
slot update_slots: id 0 | task 2899 | prompt done, n_past = 2771, n_tokens = 720
|
|
slot release: id 0 | task 2899 | stop processing: n_past = 3201, truncated = 0
|
|
slot print_timing: id 0 | task 2899 |
|
|
prompt eval time = 1001.38 ms / 2768 tokens ( 0.36 ms per token, 2764.19 tokens per second)
|
|
eval time = 10265.77 ms / 431 tokens ( 23.82 ms per token, 41.98 tokens per second)
|
|
total time = 11267.15 ms / 3199 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 3332 | processing task
|
|
slot update_slots: id 0 | task 3332 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 372
|
|
slot update_slots: id 0 | task 3332 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 3332 | prompt processing progress, n_past = 372, n_tokens = 369, progress = 0.991935
|
|
slot update_slots: id 0 | task 3332 | prompt done, n_past = 372, n_tokens = 369
|
|
slot release: id 0 | task 3332 | stop processing: n_past = 381, truncated = 0
|
|
slot print_timing: id 0 | task 3332 |
|
|
prompt eval time = 101.31 ms / 369 tokens ( 0.27 ms per token, 3642.36 tokens per second)
|
|
eval time = 215.08 ms / 10 tokens ( 21.51 ms per token, 46.49 tokens per second)
|
|
total time = 316.38 ms / 379 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 3343 | processing task
|
|
slot update_slots: id 0 | task 3343 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 3343 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 3343 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.738550
|
|
slot update_slots: id 0 | task 3343 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 3343 | prompt processing progress, n_past = 2773, n_tokens = 722, progress = 0.998918
|
|
slot update_slots: id 0 | task 3343 | prompt done, n_past = 2773, n_tokens = 722
|
|
slot release: id 0 | task 3343 | stop processing: n_past = 3187, truncated = 0
|
|
slot print_timing: id 0 | task 3343 |
|
|
prompt eval time = 1024.02 ms / 2770 tokens ( 0.37 ms per token, 2705.02 tokens per second)
|
|
eval time = 10102.62 ms / 415 tokens ( 24.34 ms per token, 41.08 tokens per second)
|
|
total time = 11126.64 ms / 3185 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 3760 | processing task
|
|
slot update_slots: id 0 | task 3760 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 3760 | need to evaluate at least 1 token for each active slot, n_past = 2773, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 3760 | kv cache rm [2772, end)
|
|
slot update_slots: id 0 | task 3760 | prompt processing progress, n_past = 2773, n_tokens = 1, progress = 0.000361
|
|
slot update_slots: id 0 | task 3760 | prompt done, n_past = 2773, n_tokens = 1
|
|
slot release: id 0 | task 3760 | stop processing: n_past = 3187, truncated = 0
|
|
slot print_timing: id 0 | task 3760 |
|
|
prompt eval time = 36.75 ms / 1 tokens ( 36.75 ms per token, 27.21 tokens per second)
|
|
eval time = 10007.68 ms / 415 tokens ( 24.11 ms per token, 41.47 tokens per second)
|
|
total time = 10044.43 ms / 416 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 4176 | processing task
|
|
slot update_slots: id 0 | task 4176 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 4176 | need to evaluate at least 1 token for each active slot, n_past = 2773, n_prompt_tokens = 2773
|
|
slot update_slots: id 0 | task 4176 | kv cache rm [2772, end)
|
|
slot update_slots: id 0 | task 4176 | prompt processing progress, n_past = 2773, n_tokens = 1, progress = 0.000361
|
|
slot update_slots: id 0 | task 4176 | prompt done, n_past = 2773, n_tokens = 1
|
|
slot release: id 0 | task 4176 | stop processing: n_past = 3187, truncated = 0
|
|
slot print_timing: id 0 | task 4176 |
|
|
prompt eval time = 41.05 ms / 1 tokens ( 41.05 ms per token, 24.36 tokens per second)
|
|
eval time = 10475.73 ms / 415 tokens ( 25.24 ms per token, 39.62 tokens per second)
|
|
total time = 10516.78 ms / 416 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 4592 | processing task
|
|
slot update_slots: id 0 | task 4592 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 374
|
|
slot update_slots: id 0 | task 4592 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 4592 | prompt processing progress, n_past = 374, n_tokens = 371, progress = 0.991979
|
|
slot update_slots: id 0 | task 4592 | prompt done, n_past = 374, n_tokens = 371
|
|
slot release: id 0 | task 4592 | stop processing: n_past = 383, truncated = 0
|
|
slot print_timing: id 0 | task 4592 |
|
|
prompt eval time = 105.27 ms / 371 tokens ( 0.28 ms per token, 3524.44 tokens per second)
|
|
eval time = 221.01 ms / 10 tokens ( 22.10 ms per token, 45.25 tokens per second)
|
|
total time = 326.27 ms / 381 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 4603 | processing task
|
|
slot update_slots: id 0 | task 4603 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2775
|
|
slot update_slots: id 0 | task 4603 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 4603 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.738018
|
|
slot update_slots: id 0 | task 4603 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 4603 | prompt processing progress, n_past = 2775, n_tokens = 724, progress = 0.998919
|
|
slot update_slots: id 0 | task 4603 | prompt done, n_past = 2775, n_tokens = 724
|
|
slot release: id 0 | task 4603 | stop processing: n_past = 3189, truncated = 0
|
|
slot print_timing: id 0 | task 4603 |
|
|
prompt eval time = 1084.70 ms / 2772 tokens ( 0.39 ms per token, 2555.55 tokens per second)
|
|
eval time = 10579.66 ms / 415 tokens ( 25.49 ms per token, 39.23 tokens per second)
|
|
total time = 11664.36 ms / 3187 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 5020 | processing task
|
|
slot update_slots: id 0 | task 5020 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2775
|
|
slot update_slots: id 0 | task 5020 | need to evaluate at least 1 token for each active slot, n_past = 2775, n_prompt_tokens = 2775
|
|
slot update_slots: id 0 | task 5020 | kv cache rm [2774, end)
|
|
slot update_slots: id 0 | task 5020 | prompt processing progress, n_past = 2775, n_tokens = 1, progress = 0.000360
|
|
slot update_slots: id 0 | task 5020 | prompt done, n_past = 2775, n_tokens = 1
|
|
slot release: id 0 | task 5020 | stop processing: n_past = 3189, truncated = 0
|
|
slot print_timing: id 0 | task 5020 |
|
|
prompt eval time = 40.07 ms / 1 tokens ( 40.07 ms per token, 24.96 tokens per second)
|
|
eval time = 10282.92 ms / 415 tokens ( 24.78 ms per token, 40.36 tokens per second)
|
|
total time = 10323.00 ms / 416 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 5436 | processing task
|
|
slot update_slots: id 0 | task 5436 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2775
|
|
slot update_slots: id 0 | task 5436 | need to evaluate at least 1 token for each active slot, n_past = 2775, n_prompt_tokens = 2775
|
|
slot update_slots: id 0 | task 5436 | kv cache rm [2774, end)
|
|
slot update_slots: id 0 | task 5436 | prompt processing progress, n_past = 2775, n_tokens = 1, progress = 0.000360
|
|
slot update_slots: id 0 | task 5436 | prompt done, n_past = 2775, n_tokens = 1
|
|
slot release: id 0 | task 5436 | stop processing: n_past = 3189, truncated = 0
|
|
slot print_timing: id 0 | task 5436 |
|
|
prompt eval time = 37.47 ms / 1 tokens ( 37.47 ms per token, 26.69 tokens per second)
|
|
eval time = 10087.63 ms / 415 tokens ( 24.31 ms per token, 41.14 tokens per second)
|
|
total time = 10125.10 ms / 416 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 5852 | processing task
|
|
slot update_slots: id 0 | task 5852 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 377
|
|
slot update_slots: id 0 | task 5852 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 5852 | prompt processing progress, n_past = 377, n_tokens = 374, progress = 0.992042
|
|
slot update_slots: id 0 | task 5852 | prompt done, n_past = 377, n_tokens = 374
|
|
slot release: id 0 | task 5852 | stop processing: n_past = 386, truncated = 0
|
|
slot print_timing: id 0 | task 5852 |
|
|
prompt eval time = 100.83 ms / 374 tokens ( 0.27 ms per token, 3709.18 tokens per second)
|
|
eval time = 222.79 ms / 10 tokens ( 22.28 ms per token, 44.89 tokens per second)
|
|
total time = 323.62 ms / 384 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 5863 | processing task
|
|
slot update_slots: id 0 | task 5863 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2778
|
|
slot update_slots: id 0 | task 5863 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 5863 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.737221
|
|
slot update_slots: id 0 | task 5863 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 5863 | prompt processing progress, n_past = 2778, n_tokens = 727, progress = 0.998920
|
|
slot update_slots: id 0 | task 5863 | prompt done, n_past = 2778, n_tokens = 727
|
|
slot release: id 0 | task 5863 | stop processing: n_past = 3175, truncated = 0
|
|
slot print_timing: id 0 | task 5863 |
|
|
prompt eval time = 1029.85 ms / 2775 tokens ( 0.37 ms per token, 2694.56 tokens per second)
|
|
eval time = 10029.89 ms / 398 tokens ( 25.20 ms per token, 39.68 tokens per second)
|
|
total time = 11059.75 ms / 3173 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 6263 | processing task
|
|
slot update_slots: id 0 | task 6263 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 375
|
|
slot update_slots: id 0 | task 6263 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 6263 | prompt processing progress, n_past = 375, n_tokens = 372, progress = 0.992000
|
|
slot update_slots: id 0 | task 6263 | prompt done, n_past = 375, n_tokens = 372
|
|
slot release: id 0 | task 6263 | stop processing: n_past = 384, truncated = 0
|
|
slot print_timing: id 0 | task 6263 |
|
|
prompt eval time = 109.42 ms / 372 tokens ( 0.29 ms per token, 3399.62 tokens per second)
|
|
eval time = 241.78 ms / 10 tokens ( 24.18 ms per token, 41.36 tokens per second)
|
|
total time = 351.20 ms / 382 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 6274 | processing task
|
|
slot update_slots: id 0 | task 6274 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2776
|
|
slot update_slots: id 0 | task 6274 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 6274 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.737752
|
|
slot update_slots: id 0 | task 6274 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 6274 | prompt processing progress, n_past = 2776, n_tokens = 725, progress = 0.998919
|
|
slot update_slots: id 0 | task 6274 | prompt done, n_past = 2776, n_tokens = 725
|
|
slot release: id 0 | task 6274 | stop processing: n_past = 3206, truncated = 0
|
|
slot print_timing: id 0 | task 6274 |
|
|
prompt eval time = 1088.92 ms / 2773 tokens ( 0.39 ms per token, 2546.57 tokens per second)
|
|
eval time = 10592.22 ms / 431 tokens ( 24.58 ms per token, 40.69 tokens per second)
|
|
total time = 11681.14 ms / 3204 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 6707 | processing task
|
|
slot update_slots: id 0 | task 6707 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 378
|
|
slot update_slots: id 0 | task 6707 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 6707 | prompt processing progress, n_past = 378, n_tokens = 375, progress = 0.992063
|
|
slot update_slots: id 0 | task 6707 | prompt done, n_past = 378, n_tokens = 375
|
|
slot release: id 0 | task 6707 | stop processing: n_past = 387, truncated = 0
|
|
slot print_timing: id 0 | task 6707 |
|
|
prompt eval time = 114.78 ms / 375 tokens ( 0.31 ms per token, 3267.26 tokens per second)
|
|
eval time = 232.75 ms / 10 tokens ( 23.27 ms per token, 42.96 tokens per second)
|
|
total time = 347.52 ms / 385 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 6718 | processing task
|
|
slot update_slots: id 0 | task 6718 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2779
|
|
slot update_slots: id 0 | task 6718 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 6718 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.736956
|
|
slot update_slots: id 0 | task 6718 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 6718 | prompt processing progress, n_past = 2779, n_tokens = 728, progress = 0.998921
|
|
slot update_slots: id 0 | task 6718 | prompt done, n_past = 2779, n_tokens = 728
|
|
slot release: id 0 | task 6718 | stop processing: n_past = 3209, truncated = 0
|
|
slot print_timing: id 0 | task 6718 |
|
|
prompt eval time = 1011.95 ms / 2776 tokens ( 0.36 ms per token, 2743.22 tokens per second)
|
|
eval time = 10591.83 ms / 431 tokens ( 24.58 ms per token, 40.69 tokens per second)
|
|
total time = 11603.77 ms / 3207 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 7151 | processing task
|
|
slot update_slots: id 0 | task 7151 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 375
|
|
slot update_slots: id 0 | task 7151 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 7151 | prompt processing progress, n_past = 375, n_tokens = 372, progress = 0.992000
|
|
slot update_slots: id 0 | task 7151 | prompt done, n_past = 375, n_tokens = 372
|
|
slot release: id 0 | task 7151 | stop processing: n_past = 384, truncated = 0
|
|
slot print_timing: id 0 | task 7151 |
|
|
prompt eval time = 104.59 ms / 372 tokens ( 0.28 ms per token, 3556.61 tokens per second)
|
|
eval time = 216.58 ms / 10 tokens ( 21.66 ms per token, 46.17 tokens per second)
|
|
total time = 321.17 ms / 382 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|
|
srv params_from_: Chat format: Content-only
|
|
slot launch_slot_: id 0 | task 7162 | processing task
|
|
slot update_slots: id 0 | task 7162 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 2776
|
|
slot update_slots: id 0 | task 7162 | kv cache rm [3, end)
|
|
slot update_slots: id 0 | task 7162 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.737752
|
|
slot update_slots: id 0 | task 7162 | kv cache rm [2051, end)
|
|
slot update_slots: id 0 | task 7162 | prompt processing progress, n_past = 2776, n_tokens = 725, progress = 0.998919
|
|
slot update_slots: id 0 | task 7162 | prompt done, n_past = 2776, n_tokens = 725
|
|
slot release: id 0 | task 7162 | stop processing: n_past = 3173, truncated = 0
|
|
slot print_timing: id 0 | task 7162 |
|
|
prompt eval time = 1014.23 ms / 2773 tokens ( 0.37 ms per token, 2734.11 tokens per second)
|
|
eval time = 9567.80 ms / 398 tokens ( 24.04 ms per token, 41.60 tokens per second)
|
|
total time = 10582.02 ms / 3171 tokens
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
|