huangfu/DronePlanning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

新增拍照节点,删除安全检查

Browse Source
This commit is contained in:
huangfu
2025-12-06 13:47:05 +08:00
parent c08cdfb339
commit 8945e922d5
1999 changed files with 1923 additions and 1797 deletions
Download Patch File Download Diff File Expand all files Collapse all files

190
logs/embedding_model.log
View File

@@ -2,17 +2,17 @@ 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
build: 6912 (961660b8c) with cc (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0 for x86_64-linux-gnu
system info: n_threads = 6, n_threads_batch = 6, 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 |
system_info: n_threads = 6 (n_threads_batch = 6) / 16 | 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 |
main: binding port with default address family
main: HTTP server is listening, hostname: 0.0.0.0, port: 8090, http threads: 15
main: loading model
srv load_model: loading model '/home/huangfukk/models/gguf/Qwen/Qwen3-Embedding-4B/Qwen3-Embedding-4B-Q4_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 36 key-value pairs and 398 tensors from /home/huangfukk/models/gguf/Qwen/Qwen3-Embedding-4B/Qwen3-Embedding-4B-Q4_K_M.gguf (version GGUF V3 (latest))
srv load_model: loading model '/home/huangfukk/models/gguf/Qwen3/Qwen3-Embedding-4B/Qwen3-Embedding-4B-Q5_K_M.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4060 Ti) (0000:01:00.0) - 13681 MiB free
llama_model_loader: loaded meta data with 36 key-value pairs and 398 tensors from /home/huangfukk/models/gguf/Qwen3/Qwen3-Embedding-4B/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
@@ -49,13 +49,13 @@ llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool
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 = 15
llama_model_loader: - kv 35: general.file_type u32 = 17
llama_model_loader: - type f32: 145 tensors
llama_model_loader: - type q4_K: 216 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 = Q4_K - Medium
print_info: file size = 2.32 GiB (4.95 BPW)
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|>')
@@ -88,6 +88,8 @@ 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
@@ -122,9 +124,9 @@ 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 = 2071.62 MiB
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 = 1
llama_context: n_ctx = 4096
@@ -132,17 +134,18 @@ llama_context: n_ctx_per_seq = 4096
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: flash_attn = auto
llama_context: kv_unified = false
llama_context: freq_base = 1000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_context: CPU output buffer size = 0.59 MiB
llama_kv_cache_unified: CUDA0 KV buffer size = 576.00 MiB
llama_kv_cache_unified: size = 576.00 MiB ( 4096 cells, 36 layers, 1/1 seqs), K (f16): 288.00 MiB, V (f16): 288.00 MiB
llama_kv_cache: CUDA0 KV buffer size = 576.00 MiB
llama_kv_cache: size = 576.00 MiB ( 4096 cells, 36 layers, 1/1 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 = 17.01 MiB
llama_context: graph nodes = 1411
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
@@ -153,6 +156,10 @@ 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 = 1
slot init: id 0 | task -1 | new slot n_ctx_slot = 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
main: model loaded
main: chat template, chat_template: {%- if tools %}
{{- '<|im_start|>system\n' }}
@@ -221,139 +228,28 @@ How are you?<|im_end|>
main: server is listening on http://0.0.0.0:8090 - 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 0 | task -1 | selected slot by LRU, t_last = -1
slot launch_slot_: id 0 | task 0 | processing task
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 2
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 2, n_tokens = 2, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_past = 2, n_tokens = 2
slot release: id 0 | task 0 | stop processing: n_past = 2, truncated = 0
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 41
slot update_slots: id 0 | task 0 | n_tokens = 0, memory_seq_rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_tokens = 41, batch.n_tokens = 41, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_tokens = 41, batch.n_tokens = 41
slot release: id 0 | task 0 | stop processing: n_tokens = 41, 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 LCP similarity, sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
slot launch_slot_: id 0 | task 2 | processing task
slot update_slots: id 0 | task 2 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 9
slot update_slots: id 0 | task 2 | kv cache rm [1, end)
slot update_slots: id 0 | task 2 | prompt processing progress, n_past = 9, n_tokens = 8, progress = 0.888889
slot update_slots: id 0 | task 2 | prompt done, n_past = 9, n_tokens = 8
slot release: id 0 | task 2 | stop processing: n_past = 9, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 4 | processing task
slot update_slots: id 0 | task 4 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 12
slot update_slots: id 0 | task 4 | kv cache rm [7, end)
slot update_slots: id 0 | task 4 | prompt processing progress, n_past = 12, n_tokens = 5, progress = 0.416667
slot update_slots: id 0 | task 4 | prompt done, n_past = 12, n_tokens = 5
slot release: id 0 | task 4 | stop processing: n_past = 12, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 6 | processing task
slot update_slots: id 0 | task 6 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 2
slot update_slots: id 0 | task 6 | kv cache rm [1, end)
slot update_slots: id 0 | task 6 | prompt processing progress, n_past = 2, n_tokens = 1, progress = 0.500000
slot update_slots: id 0 | task 6 | prompt done, n_past = 2, n_tokens = 1
slot release: id 0 | task 6 | stop processing: n_past = 2, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 8 | processing task
slot update_slots: id 0 | task 8 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 9
slot update_slots: id 0 | task 8 | kv cache rm [1, end)
slot update_slots: id 0 | task 8 | prompt processing progress, n_past = 9, n_tokens = 8, progress = 0.888889
slot update_slots: id 0 | task 8 | prompt done, n_past = 9, n_tokens = 8
slot release: id 0 | task 8 | stop processing: n_past = 9, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 10 | processing task
slot update_slots: id 0 | task 10 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 2
slot update_slots: id 0 | task 10 | kv cache rm [1, end)
slot update_slots: id 0 | task 10 | prompt processing progress, n_past = 2, n_tokens = 1, progress = 0.500000
slot update_slots: id 0 | task 10 | prompt done, n_past = 2, n_tokens = 1
slot release: id 0 | task 10 | stop processing: n_past = 2, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 12 | processing task
slot update_slots: id 0 | task 12 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 9
slot update_slots: id 0 | task 12 | kv cache rm [1, end)
slot update_slots: id 0 | task 12 | prompt processing progress, n_past = 9, n_tokens = 8, progress = 0.888889
slot update_slots: id 0 | task 12 | prompt done, n_past = 9, n_tokens = 8
slot release: id 0 | task 12 | stop processing: n_past = 9, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 14 | processing task
slot update_slots: id 0 | task 14 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 12
slot update_slots: id 0 | task 14 | kv cache rm [7, end)
slot update_slots: id 0 | task 14 | prompt processing progress, n_past = 12, n_tokens = 5, progress = 0.416667
slot update_slots: id 0 | task 14 | prompt done, n_past = 12, n_tokens = 5
slot release: id 0 | task 14 | stop processing: n_past = 12, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 16 | processing task
slot update_slots: id 0 | task 16 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 12
slot update_slots: id 0 | task 16 | kv cache rm [7, end)
slot update_slots: id 0 | task 16 | prompt processing progress, n_past = 12, n_tokens = 5, progress = 0.416667
slot update_slots: id 0 | task 16 | prompt done, n_past = 12, n_tokens = 5
slot release: id 0 | task 16 | stop processing: n_past = 12, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 18 | processing task
slot update_slots: id 0 | task 18 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 12
slot update_slots: id 0 | task 18 | kv cache rm [7, end)
slot update_slots: id 0 | task 18 | prompt processing progress, n_past = 12, n_tokens = 5, progress = 0.416667
slot update_slots: id 0 | task 18 | prompt done, n_past = 12, n_tokens = 5
slot release: id 0 | task 18 | stop processing: n_past = 12, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 20 | processing task
slot update_slots: id 0 | task 20 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 10
slot update_slots: id 0 | task 20 | kv cache rm [0, end)
slot update_slots: id 0 | task 20 | prompt processing progress, n_past = 10, n_tokens = 10, progress = 1.000000
slot update_slots: id 0 | task 20 | prompt done, n_past = 10, n_tokens = 10
slot release: id 0 | task 20 | stop processing: n_past = 10, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 22 | processing task
slot update_slots: id 0 | task 22 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 12
slot update_slots: id 0 | task 22 | kv cache rm [7, end)
slot update_slots: id 0 | task 22 | prompt processing progress, n_past = 12, n_tokens = 5, progress = 0.416667
slot update_slots: id 0 | task 22 | prompt done, n_past = 12, n_tokens = 5
slot release: id 0 | task 22 | stop processing: n_past = 12, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
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, n_prompt_tokens = 14
slot update_slots: id 0 | task 24 | kv cache rm [0, end)
slot update_slots: id 0 | task 24 | prompt processing progress, n_past = 14, n_tokens = 14, progress = 1.000000
slot update_slots: id 0 | task 24 | prompt done, n_past = 14, n_tokens = 14
slot release: id 0 | task 24 | stop processing: n_past = 14, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 26 | processing task
slot update_slots: id 0 | task 26 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 17
slot update_slots: id 0 | task 26 | kv cache rm [1, end)
slot update_slots: id 0 | task 26 | prompt processing progress, n_past = 17, n_tokens = 16, progress = 0.941176
slot update_slots: id 0 | task 26 | prompt done, n_past = 17, n_tokens = 16
slot release: id 0 | task 26 | stop processing: n_past = 17, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 28 | processing task
slot update_slots: id 0 | task 28 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 15
slot update_slots: id 0 | task 28 | kv cache rm [0, end)
slot update_slots: id 0 | task 28 | prompt processing progress, n_past = 15, n_tokens = 15, progress = 1.000000
slot update_slots: id 0 | task 28 | prompt done, n_past = 15, n_tokens = 15
slot release: id 0 | task 28 | stop processing: n_past = 15, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 30 | processing task
slot update_slots: id 0 | task 30 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 18
slot update_slots: id 0 | task 30 | kv cache rm [6, end)
slot update_slots: id 0 | task 30 | prompt processing progress, n_past = 18, n_tokens = 12, progress = 0.666667
slot update_slots: id 0 | task 30 | prompt done, n_past = 18, n_tokens = 12
slot release: id 0 | task 30 | stop processing: n_past = 18, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot launch_slot_: id 0 | task 32 | processing task
slot update_slots: id 0 | task 32 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 15
slot update_slots: id 0 | task 32 | kv cache rm [0, end)
slot update_slots: id 0 | task 32 | prompt processing progress, n_past = 15, n_tokens = 15, progress = 1.000000
slot update_slots: id 0 | task 32 | prompt done, n_past = 15, n_tokens = 15
slot release: id 0 | task 32 | stop processing: n_past = 15, truncated = 0
slot update_slots: id 0 | task 2 | new prompt, n_ctx_slot = 4096, n_keep = 0, task.n_tokens = 41
slot update_slots: id 0 | task 2 | need to evaluate at least 1 token for each active slot (n_past = 41, task.n_tokens() = 41)
slot update_slots: id 0 | task 2 | n_past was set to 40
slot update_slots: id 0 | task 2 | n_tokens = 40, memory_seq_rm [40, end)
slot update_slots: id 0 | task 2 | prompt processing progress, n_tokens = 41, batch.n_tokens = 1, progress = 1.000000
slot update_slots: id 0 | task 2 | prompt done, n_tokens = 41, batch.n_tokens = 1
slot release: id 0 | task 2 | stop processing: n_tokens = 41, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
srv operator(): operator(): cleaning up before exit...
llama_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted |
llama_memory_breakdown_print: | - CUDA0 (RTX 4060 Ti) | 15944 = 5959 + (3626 = 2445 + 576 + 604) + 6358 |
llama_memory_breakdown_print: | - Host | 316 = 303 + 0 + 13 |
Received second interrupt, terminating immediately.

1017
logs/fastapi.log
View File

File diff suppressed because it is too large Load Diff

618
logs/inference_model.log
View File

@@ -2,17 +2,17 @@ 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
build: 6912 (961660b8c) with cc (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0 for x86_64-linux-gnu
system info: n_threads = 6, n_threads_batch = 6, 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 |
system_info: n_threads = 6 (n_threads_batch = 6) / 16 | 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 |
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))
srv load_model: loading model '/home/huangfukk/models/gguf/Qwen3/Qwen3-4B/Qwen3-4B-Q5_K_M.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4060 Ti) (0000:01:00.0) - 13681 MiB free
llama_model_loader: loaded meta data with 28 key-value pairs and 398 tensors from /home/huangfukk/models/gguf/Qwen3/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
@@ -80,6 +80,8 @@ 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 = -1
print_info: rope type = 2
@@ -114,8 +116,8 @@ 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
load_tensors: CUDA0 model buffer size = 2445.68 MiB
..........................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
@@ -124,17 +126,18 @@ 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: flash_attn = auto
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_kv_cache: CUDA0 KV buffer size = 1152.00 MiB
llama_kv_cache: size = 1152.00 MiB ( 8192 cells, 36 layers, 1/1 seqs), K (f16): 576.00 MiB, V (f16): 576.00 MiB
llama_context: Flash Attention was auto, set to enabled
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: CUDA_Host compute buffer size = 21.01 MiB
llama_context: graph nodes = 1267
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
@@ -145,6 +148,10 @@ 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
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
main: model loaded
main: chat template, chat_template: {%- if tools %}
{{- '<|im_start|>system\n' }}
@@ -244,534 +251,89 @@ 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 get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1
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 update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 8192, n_keep = 0, task.n_tokens = 375
slot update_slots: id 0 | task 0 | n_tokens = 0, memory_seq_rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_tokens = 375, batch.n_tokens = 375, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_tokens = 375, batch.n_tokens = 375
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
prompt eval time = 111.12 ms / 375 tokens ( 0.30 ms per token, 3374.64 tokens per second)
eval time = 207.35 ms / 10 tokens ( 20.73 ms per token, 48.23 tokens per second)
total time = 318.47 ms / 385 tokens
slot release: id 0 | task 0 | stop processing: n_tokens = 384, truncated = 0
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 get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 237472165130
srv get_availabl: updating prompt cache
srv prompt_save: - saving prompt with length 384, total state size = 54.005 MiB
srv load: - looking for better prompt, base f_keep = 0.008, sim = 0.001
srv update: - cache state: 1 prompts, 54.005 MiB (limits: 8192.000 MiB, 8192 tokens, 58248 est)
srv update: - prompt 0x63c2bba5e140: 384 tokens, checkpoints: 0, 54.005 MiB
srv get_availabl: prompt cache update took 22.38 ms
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 update_slots: id 0 | task 11 | new prompt, n_ctx_slot = 8192, n_keep = 0, task.n_tokens = 2554
slot update_slots: id 0 | task 11 | n_tokens = 3, memory_seq_rm [3, end)
slot update_slots: id 0 | task 11 | prompt processing progress, n_tokens = 2051, batch.n_tokens = 2048, progress = 0.803054
slot update_slots: id 0 | task 11 | n_tokens = 2051, memory_seq_rm [2051, end)
slot update_slots: id 0 | task 11 | prompt processing progress, n_tokens = 2554, batch.n_tokens = 503, progress = 1.000000
slot update_slots: id 0 | task 11 | prompt done, n_tokens = 2554, batch.n_tokens = 503
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
prompt eval time = 608.76 ms / 2551 tokens ( 0.24 ms per token, 4190.45 tokens per second)
eval time = 9337.00 ms / 409 tokens ( 22.83 ms per token, 43.80 tokens per second)
total time = 9945.76 ms / 2960 tokens
slot release: id 0 | task 11 | stop processing: n_tokens = 2962, truncated = 0
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
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 237482215959
srv get_availabl: updating prompt cache
srv prompt_save: - saving prompt with length 2962, total state size = 416.566 MiB
srv load: - looking for better prompt, base f_keep = 0.001, sim = 0.008
srv load: - found better prompt with f_keep = 0.977, sim = 1.000
srv update: - cache state: 1 prompts, 416.566 MiB (limits: 8192.000 MiB, 8192 tokens, 58249 est)
srv update: - prompt 0x63c2bba9e270: 2962 tokens, checkpoints: 0, 416.566 MiB
srv get_availabl: prompt cache update took 162.15 ms
slot launch_slot_: id 0 | task 422 | processing task
slot update_slots: id 0 | task 422 | new prompt, n_ctx_slot = 8192, n_keep = 0, task.n_tokens = 375
slot update_slots: id 0 | task 422 | need to evaluate at least 1 token for each active slot (n_past = 375, task.n_tokens() = 375)
slot update_slots: id 0 | task 422 | n_past was set to 374
slot update_slots: id 0 | task 422 | n_tokens = 374, memory_seq_rm [374, end)
slot update_slots: id 0 | task 422 | prompt processing progress, n_tokens = 375, batch.n_tokens = 1, progress = 1.000000
slot update_slots: id 0 | task 422 | prompt done, n_tokens = 375, batch.n_tokens = 1
slot print_timing: id 0 | task 422 |
prompt eval time = 30.72 ms / 1 tokens ( 30.72 ms per token, 32.55 tokens per second)
eval time = 196.03 ms / 10 tokens ( 19.60 ms per token, 51.01 tokens per second)
total time = 226.75 ms / 11 tokens
slot release: id 0 | task 422 | stop processing: n_tokens = 384, truncated = 0
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
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 237485582368
srv get_availabl: updating prompt cache
srv prompt_save: - saving prompt with length 384, total state size = 54.005 MiB
srv load: - looking for better prompt, base f_keep = 0.008, sim = 0.001
srv load: - found better prompt with f_keep = 0.862, sim = 1.000
srv update: - cache state: 1 prompts, 54.005 MiB (limits: 8192.000 MiB, 8192 tokens, 58248 est)
srv update: - prompt 0x63c2bf15ea60: 384 tokens, checkpoints: 0, 54.005 MiB
srv get_availabl: prompt cache update took 76.62 ms
slot launch_slot_: id 0 | task 433 | processing task
slot update_slots: id 0 | task 433 | new prompt, n_ctx_slot = 8192, n_keep = 0, task.n_tokens = 2554
slot update_slots: id 0 | task 433 | need to evaluate at least 1 token for each active slot (n_past = 2554, task.n_tokens() = 2554)
slot update_slots: id 0 | task 433 | n_past was set to 2553
slot update_slots: id 0 | task 433 | n_tokens = 2553, memory_seq_rm [2553, end)
slot update_slots: id 0 | task 433 | prompt processing progress, n_tokens = 2554, batch.n_tokens = 1, progress = 1.000000
slot update_slots: id 0 | task 433 | prompt done, n_tokens = 2554, batch.n_tokens = 1
slot print_timing: id 0 | task 433 |
prompt eval time = 37.62 ms / 1 tokens ( 37.62 ms per token, 26.58 tokens per second)
eval time = 9680.67 ms / 409 tokens ( 23.67 ms per token, 42.25 tokens per second)
total time = 9718.29 ms / 410 tokens
slot release: id 0 | task 433 | stop processing: n_tokens = 2962, truncated = 0
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
srv operator(): operator(): cleaning up before exit...
llama_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted |
llama_memory_breakdown_print: | - CUDA0 (RTX 4060 Ti) | 15944 = 5959 + (4203 = 2445 + 1152 + 606) + 5781 |
llama_memory_breakdown_print: | - Host | 325 = 304 + 0 + 21 |
Received second interrupt, terminating immediately.

3
logs/services.pid
View File

@@ -1,3 +0,0 @@
19618
19619
19713