377 lines
25 KiB
Plaintext
377 lines
25 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 5090, compute capability 12.0, VMM: yes
|
|
main: setting n_parallel = 4 and kv_unified = true (add -kvu to disable this)
|
|
build: 7212 (ff90508d6) with cc (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0 for x86_64-linux-gnu
|
|
system info: n_threads = 8, n_threads_batch = 8, total_threads = 32
|
|
|
|
system_info: n_threads = 8 (n_threads_batch = 8) / 32 | CUDA : ARCHS = 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 |
|
|
|
|
init: using 31 threads for HTTP server
|
|
start: binding port with default address family
|
|
main: loading model
|
|
srv load_model: loading model '/home/iscas/models/Qwen3-Embedding-4B-Q5_K_M.gguf'
|
|
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 5090) (0000:01:00.0) - 29667 MiB free
|
|
llama_model_loader: loaded meta data with 36 key-value pairs and 398 tensors from /home/iscas/models/Qwen3-Embedding-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 Embedding 4B
|
|
llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding
|
|
llama_model_loader: - kv 4: general.size_label str = 4B
|
|
llama_model_loader: - kv 5: general.license str = apache-2.0
|
|
llama_model_loader: - kv 6: general.base_model.count u32 = 1
|
|
llama_model_loader: - kv 7: general.base_model.0.name str = Qwen3 4B Base
|
|
llama_model_loader: - kv 8: general.base_model.0.organization str = Qwen
|
|
llama_model_loader: - kv 9: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-4B-...
|
|
llama_model_loader: - kv 10: general.tags arr[str,5] = ["transformers", "sentence-transforme...
|
|
llama_model_loader: - kv 11: qwen3.block_count u32 = 36
|
|
llama_model_loader: - kv 12: qwen3.context_length u32 = 40960
|
|
llama_model_loader: - kv 13: qwen3.embedding_length u32 = 2560
|
|
llama_model_loader: - kv 14: qwen3.feed_forward_length u32 = 9728
|
|
llama_model_loader: - kv 15: qwen3.attention.head_count u32 = 32
|
|
llama_model_loader: - kv 16: qwen3.attention.head_count_kv u32 = 8
|
|
llama_model_loader: - kv 17: qwen3.rope.freq_base f32 = 1000000.000000
|
|
llama_model_loader: - kv 18: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
|
|
llama_model_loader: - kv 19: qwen3.attention.key_length u32 = 128
|
|
llama_model_loader: - kv 20: qwen3.attention.value_length u32 = 128
|
|
llama_model_loader: - kv 21: qwen3.pooling_type u32 = 3
|
|
llama_model_loader: - kv 22: tokenizer.ggml.model str = gpt2
|
|
llama_model_loader: - kv 23: tokenizer.ggml.pre str = qwen2
|
|
llama_model_loader: - kv 24: tokenizer.ggml.tokens arr[str,151665] = ["!", "\"", "#", "$", "%", "&", "'", ...
|
|
llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
|
|
llama_model_loader: - kv 26: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
|
|
llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 151643
|
|
llama_model_loader: - kv 28: tokenizer.ggml.padding_token_id u32 = 151643
|
|
llama_model_loader: - kv 29: tokenizer.ggml.eot_token_id u32 = 151645
|
|
llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643
|
|
llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true
|
|
llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false
|
|
llama_model_loader: - kv 33: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
|
|
llama_model_loader: - kv 34: general.quantization_version u32 = 2
|
|
llama_model_loader: - kv 35: 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 = 2.68 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 = 22
|
|
load: token to piece cache size = 0.9310 MB
|
|
print_info: arch = qwen3
|
|
print_info: vocab_only = 0
|
|
print_info: n_ctx_train = 40960
|
|
print_info: n_embd = 2560
|
|
print_info: n_embd_inp = 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: n_expert_groups = 0
|
|
print_info: n_group_used = 0
|
|
print_info: causal attn = 1
|
|
print_info: pooling type = 3
|
|
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 Embedding 4B
|
|
print_info: vocab type = BPE
|
|
print_info: n_vocab = 151665
|
|
print_info: n_merges = 151387
|
|
print_info: BOS token = 151643 '<|endoftext|>'
|
|
print_info: EOS token = 151643 '<|endoftext|>'
|
|
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: CPU_Mapped model buffer size = 303.75 MiB
|
|
load_tensors: CUDA0 model buffer size = 2445.68 MiB
|
|
..........................................................................................
|
|
llama_context: constructing llama_context
|
|
llama_context: n_seq_max = 4
|
|
llama_context: n_ctx = 4096
|
|
llama_context: n_ctx_seq = 4096
|
|
llama_context: n_batch = 2048
|
|
llama_context: n_ubatch = 512
|
|
llama_context: causal_attn = 1
|
|
llama_context: flash_attn = auto
|
|
llama_context: kv_unified = true
|
|
llama_context: freq_base = 1000000.0
|
|
llama_context: freq_scale = 1
|
|
llama_context: n_ctx_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
|
|
llama_context: CPU output buffer size = 2.35 MiB
|
|
llama_kv_cache: CUDA0 KV buffer size = 576.00 MiB
|
|
llama_kv_cache: size = 576.00 MiB ( 4096 cells, 36 layers, 4/1 seqs), K (f16): 288.00 MiB, V (f16): 288.00 MiB
|
|
llama_context: Flash Attention was auto, set to enabled
|
|
llama_context: CUDA0 compute buffer size = 604.96 MiB
|
|
llama_context: CUDA_Host compute buffer size = 13.01 MiB
|
|
llama_context: graph nodes = 1268
|
|
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 = 4096
|
|
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
|
|
srv init: initializing slots, n_slots = 4
|
|
slot init: id 0 | task -1 | new slot, n_ctx = 4096
|
|
slot init: id 1 | task -1 | new slot, n_ctx = 4096
|
|
slot init: id 2 | task -1 | new slot, n_ctx = 4096
|
|
slot init: id 3 | task -1 | new slot, n_ctx = 4096
|
|
srv init: prompt cache is enabled, size limit: 8192 MiB
|
|
srv init: use `--cache-ram 0` to disable the prompt cache
|
|
srv init: for more info see https://github.com/ggml-org/llama.cpp/pull/16391
|
|
srv init: thinking = 0
|
|
init: chat template, chat_template: {%- if tools %}
|
|
{{- '<|im_start|>system\n' }}
|
|
{%- if messages[0]['role'] == 'system' %}
|
|
{{- messages[0]['content'] }}
|
|
{%- else %}
|
|
{{- 'You are a helpful assistant.' }}
|
|
{%- endif %}
|
|
{{- "\n\n# 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' }}
|
|
{%- else %}
|
|
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
|
{%- endif %}
|
|
{%- endif %}
|
|
{%- for message in messages %}
|
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
|
{%- elif message.role == "assistant" %}
|
|
{{- '<|im_start|>' + message.role }}
|
|
{%- if message.content %}
|
|
{{- '\n' + message.content }}
|
|
{%- endif %}
|
|
{%- for tool_call in message.tool_calls %}
|
|
{%- if tool_call.function is defined %}
|
|
{%- set tool_call = tool_call.function %}
|
|
{%- endif %}
|
|
{{- '\n<tool_call>\n{"name": "' }}
|
|
{{- tool_call.name }}
|
|
{{- '", "arguments": ' }}
|
|
{{- tool_call.arguments | tojson }}
|
|
{{- '}\n</tool_call>' }}
|
|
{%- endfor %}
|
|
{{- '<|im_end|>\n' }}
|
|
{%- elif message.role == "tool" %}
|
|
{%- if (loop.index0 == 0) 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' }}
|
|
{%- 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: model loaded
|
|
main: server is listening on http://0.0.0.0:8090
|
|
main: starting the main loop...
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: GET /health 127.0.0.1 200
|
|
slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = -1
|
|
slot launch_slot_: id 3 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 3 | task 0 | processing task
|
|
slot update_slots: id 3 | task 0 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 2
|
|
slot update_slots: id 3 | task 0 | n_tokens = 0, memory_seq_rm [0, end)
|
|
slot update_slots: id 3 | task 0 | prompt processing progress, n_tokens = 2, batch.n_tokens = 2, progress = 1.000000
|
|
slot update_slots: id 3 | task 0 | prompt done, n_tokens = 2, batch.n_tokens = 2
|
|
slot release: id 3 | task 0 | stop processing: n_tokens = 2, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, sim_best = 0.111 (> 0.100 thold), f_keep = 0.500
|
|
slot launch_slot_: id 3 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 3 | task 2 | processing task
|
|
slot update_slots: id 3 | task 2 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 9
|
|
slot update_slots: id 3 | task 2 | n_tokens = 1, memory_seq_rm [1, end)
|
|
slot update_slots: id 3 | task 2 | prompt processing progress, n_tokens = 9, batch.n_tokens = 8, progress = 1.000000
|
|
slot update_slots: id 3 | task 2 | prompt done, n_tokens = 9, batch.n_tokens = 8
|
|
slot release: id 3 | task 2 | stop processing: n_tokens = 9, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, sim_best = 0.583 (> 0.100 thold), f_keep = 0.778
|
|
slot launch_slot_: id 3 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 3 | task 4 | processing task
|
|
slot update_slots: id 3 | task 4 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 12
|
|
slot update_slots: id 3 | task 4 | n_tokens = 7, memory_seq_rm [7, end)
|
|
slot update_slots: id 3 | task 4 | prompt processing progress, n_tokens = 12, batch.n_tokens = 5, progress = 1.000000
|
|
slot update_slots: id 3 | task 4 | prompt done, n_tokens = 12, batch.n_tokens = 5
|
|
slot release: id 3 | task 4 | stop processing: n_tokens = 12, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, sim_best = 0.583 (> 0.100 thold), f_keep = 0.583
|
|
slot launch_slot_: id 3 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 3 | task 6 | processing task
|
|
slot update_slots: id 3 | task 6 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 12
|
|
slot update_slots: id 3 | task 6 | n_tokens = 7, memory_seq_rm [7, end)
|
|
slot update_slots: id 3 | task 6 | prompt processing progress, n_tokens = 12, batch.n_tokens = 5, progress = 1.000000
|
|
slot update_slots: id 3 | task 6 | prompt done, n_tokens = 12, batch.n_tokens = 5
|
|
slot release: id 3 | task 6 | stop processing: n_tokens = 12, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, sim_best = 0.583 (> 0.100 thold), f_keep = 0.583
|
|
slot launch_slot_: id 3 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 3 | task 8 | processing task
|
|
slot update_slots: id 3 | task 8 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 12
|
|
slot update_slots: id 3 | task 8 | n_tokens = 7, memory_seq_rm [7, end)
|
|
slot update_slots: id 3 | task 8 | prompt processing progress, n_tokens = 12, batch.n_tokens = 5, progress = 1.000000
|
|
slot update_slots: id 3 | task 8 | prompt done, n_tokens = 12, batch.n_tokens = 5
|
|
slot release: id 3 | task 8 | stop processing: n_tokens = 12, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = -1
|
|
slot launch_slot_: id 2 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 2 | task 10 | processing task
|
|
slot update_slots: id 2 | task 10 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 10
|
|
slot update_slots: id 2 | task 10 | n_tokens = 0, memory_seq_rm [0, end)
|
|
slot update_slots: id 2 | task 10 | prompt processing progress, n_tokens = 10, batch.n_tokens = 10, progress = 1.000000
|
|
slot update_slots: id 2 | task 10 | prompt done, n_tokens = 10, batch.n_tokens = 10
|
|
slot release: id 2 | task 10 | stop processing: n_tokens = 10, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, sim_best = 0.583 (> 0.100 thold), f_keep = 0.700
|
|
slot launch_slot_: id 2 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 2 | task 12 | processing task
|
|
slot update_slots: id 2 | task 12 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 12
|
|
slot update_slots: id 2 | task 12 | n_tokens = 7, memory_seq_rm [7, end)
|
|
slot update_slots: id 2 | task 12 | prompt processing progress, n_tokens = 12, batch.n_tokens = 5, progress = 1.000000
|
|
slot update_slots: id 2 | task 12 | prompt done, n_tokens = 12, batch.n_tokens = 5
|
|
slot release: id 2 | task 12 | stop processing: n_tokens = 12, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, sim_best = 0.500 (> 0.100 thold), f_keep = 0.583
|
|
slot launch_slot_: id 3 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 3 | task 14 | processing task
|
|
slot update_slots: id 3 | task 14 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 14
|
|
slot update_slots: id 3 | task 14 | n_tokens = 7, memory_seq_rm [7, end)
|
|
slot update_slots: id 3 | task 14 | prompt processing progress, n_tokens = 14, batch.n_tokens = 7, progress = 1.000000
|
|
slot update_slots: id 3 | task 14 | prompt done, n_tokens = 14, batch.n_tokens = 7
|
|
slot release: id 3 | task 14 | stop processing: n_tokens = 14, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = -1
|
|
slot launch_slot_: id 1 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 1 | task 16 | processing task
|
|
slot update_slots: id 1 | task 16 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 17
|
|
slot update_slots: id 1 | task 16 | n_tokens = 0, memory_seq_rm [0, end)
|
|
slot update_slots: id 1 | task 16 | prompt processing progress, n_tokens = 17, batch.n_tokens = 17, progress = 1.000000
|
|
slot update_slots: id 1 | task 16 | prompt done, n_tokens = 17, batch.n_tokens = 17
|
|
slot release: id 1 | task 16 | stop processing: n_tokens = 17, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, sim_best = 0.333 (> 0.100 thold), f_keep = 0.417
|
|
slot launch_slot_: id 2 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 2 | task 18 | processing task
|
|
slot update_slots: id 2 | task 18 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 15
|
|
slot update_slots: id 2 | task 18 | n_tokens = 5, memory_seq_rm [5, end)
|
|
slot update_slots: id 2 | task 18 | prompt processing progress, n_tokens = 15, batch.n_tokens = 10, progress = 1.000000
|
|
slot update_slots: id 2 | task 18 | prompt done, n_tokens = 15, batch.n_tokens = 10
|
|
slot release: id 2 | task 18 | stop processing: n_tokens = 15, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, sim_best = 0.333 (> 0.100 thold), f_keep = 0.400
|
|
slot launch_slot_: id 2 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 2 | task 20 | processing task
|
|
slot update_slots: id 2 | task 20 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 18
|
|
slot update_slots: id 2 | task 20 | n_tokens = 6, memory_seq_rm [6, end)
|
|
slot update_slots: id 2 | task 20 | prompt processing progress, n_tokens = 18, batch.n_tokens = 12, progress = 1.000000
|
|
slot update_slots: id 2 | task 20 | prompt done, n_tokens = 18, batch.n_tokens = 12
|
|
slot release: id 2 | task 20 | stop processing: n_tokens = 18, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, sim_best = 0.267 (> 0.100 thold), f_keep = 0.235
|
|
slot launch_slot_: id 1 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 1 | task 22 | processing task
|
|
slot update_slots: id 1 | task 22 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 15
|
|
slot update_slots: id 1 | task 22 | n_tokens = 4, memory_seq_rm [4, end)
|
|
slot update_slots: id 1 | task 22 | prompt processing progress, n_tokens = 15, batch.n_tokens = 11, progress = 1.000000
|
|
slot update_slots: id 1 | task 22 | prompt done, n_tokens = 15, batch.n_tokens = 11
|
|
slot release: id 1 | task 22 | stop processing: n_tokens = 15, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1
|
|
slot launch_slot_: id 0 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 0 | task 24 | processing task
|
|
slot update_slots: id 0 | task 24 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 34
|
|
slot update_slots: id 0 | task 24 | n_tokens = 0, memory_seq_rm [0, end)
|
|
slot update_slots: id 0 | task 24 | prompt processing progress, n_tokens = 34, batch.n_tokens = 34, progress = 1.000000
|
|
slot update_slots: id 0 | task 24 | prompt done, n_tokens = 34, batch.n_tokens = 34
|
|
slot release: id 0 | task 24 | stop processing: n_tokens = 34, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|
|
slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 284111945431
|
|
slot launch_slot_: id 3 | task -1 | sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
slot launch_slot_: id 3 | task 26 | processing task
|
|
slot update_slots: id 3 | task 26 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 37
|
|
slot update_slots: id 3 | task 26 | n_tokens = 0, memory_seq_rm [0, end)
|
|
slot update_slots: id 3 | task 26 | prompt processing progress, n_tokens = 37, batch.n_tokens = 37, progress = 1.000000
|
|
slot update_slots: id 3 | task 26 | prompt done, n_tokens = 37, batch.n_tokens = 37
|
|
slot release: id 3 | task 26 | stop processing: n_tokens = 37, truncated = 0
|
|
srv update_slots: all slots are idle
|
|
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
|