state/agent/legacy-engine.log

[local-llama] staging: 4.49 GiB bucket -> local SSD
[local-llama] staged: 4.49 GiB in 17.0s
[local-llama] loading: llama.cpp · threads=2 · ctx=65536 · KV=q8_0/q8_0
[local-llama] /opt/llama/bin/llama-server --model /tmp/local-agent-models/Ling-3.0-tiny-Q4_K_M.gguf --host 127.0.0.1 --port 43126 --ctx-size 65536 --threads 2 --threads-batch 2 --parallel 1 --cont-batching --flash-attn auto --jinja --cache-type-k q8_0 --cache-type-v q8_0 --gpu-layers 0
warning: no usable GPU found, --gpu-layers option will be ignored
warning: one possible reason is that llama.cpp was compiled without GPU support
warning: consult docs/build.md for compilation instructions
0.00.004.092 I cmn  common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg)
0.00.004.920 W srv  llama_server: -----------------
0.00.004.927 W srv  llama_server: CORS is set to allow all origins ('*') and no API key is set
0.00.004.927 W srv  llama_server: this can be a security risk (cross-origin attacks)
0.00.004.928 W srv  llama_server: more info: https://github.com/ggml-org/llama.cpp/pull/25655
0.00.004.928 W srv  llama_server: -----------------
0.00.006.263 I srv    load_model: loading model '/tmp/local-agent-models/Ling-3.0-tiny-Q4_K_M.gguf'
0.00.929.373 W load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
0.05.230.756 I cmn          init: llama threadpool init, n_threads = 2
0.05.596.580 I srv    load_model: initializing, n_slots = 1, n_ctx_slot = 65536, kv_unified = 'false'
0.05.620.286 W srv          init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve)
0.05.620.306 I srv  llama_server: model loaded
0.05.620.311 I srv  llama_server: listening on http://127.0.0.1:43126
[local-llama] ready
3.15.413.290 I slot get_availabl: id  0 | task -1 | selected slot by LRU, t_last = -1
3.15.418.737 I slot launch_slot_: id  0 | task 0 | processing task, is_child = 0
4.44.798.962 I slot print_timing: id  0 | task 0 | prompt processing, n_tokens =   2048, progress = 0.10, t =  89.38 s / 22.91 tokens per second
6.28.101.309 I slot print_timing: id  0 | task 0 | prompt processing, n_tokens =   4096, progress = 0.21, t = 192.68 s / 21.26 tokens per second
8.59.015.578 I slot print_timing: id  0 | task 0 | prompt processing, n_tokens =   6144, progress = 0.31, t = 343.60 s / 17.88 tokens per second
11.43.219.502 I slot print_timing: id  0 | task 0 | prompt processing, n_tokens =   8192, progress = 0.41, t = 507.80 s / 16.13 tokens per second
15.09.870.172 I slot print_timing: id  0 | task 0 | prompt processing, n_tokens =  10240, progress = 0.52, t = 714.45 s / 14.33 tokens per second