huangfu/DronePlanning
2
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: 添加 .gitignore，从版本控制中移除 logs、vector_store、测试结果、生成图片

Browse Source 
Made-with: Cursor
This commit is contained in:
huangfu
2026-02-26 20:02:16 +08:00
parent c7f6a0da17
commit fa5e5e7c23
153 changed files with 34 additions and 3682 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitignore vendored Normal file
View File

@@ -0,0 +1,34 @@
# ============ 日志 ============
logs/
# ============ 向量库（RAG 检索用） ============
**/vector_store/
vector_store/
# ============ 测试脚本的测试结果 ============
tools/test_validate/validation/
# ============ 生成的图片 ============
backend_service/generated_visualizations/
tools/test_validate/validation/**/*.png
tools/test_validate/validation/**/*.jpg
# ============ Python ============
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
venv/
.venv/
env/
.env/
# ============ 其他常见忽略 ============
*.log
.DS_Store
.idea/
.vscode/
*.swp
*.swo
*~

BIN
backend_service/generated_visualizations/py_tree.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 69 KiB

256
logs/embedding_model.log
View File

@@ -1,256 +0,0 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4060 Ti, compute capability 8.9, VMM: yes
build: 6097 (9515c613) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
system info: n_threads = 8, n_threads_batch = 8, total_threads = 16
system_info: n_threads = 8 (n_threads_batch = 8) / 16 | CUDA : ARCHS = 500,610,700,750,800,860,890 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
main: binding port with default address family
main: HTTP server is listening, hostname: 0.0.0.0, port: 8090, http threads: 15
main: loading model
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) - 15225 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
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_layer = 36
print_info: n_head = 32
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 4
print_info: n_embd_k_gqa = 1024
print_info: n_embd_v_gqa = 1024
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-06
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: f_attn_scale = 0.0e+00
print_info: n_ff = 9728
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 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: CUDA0 model buffer size = 2445.68 MiB
load_tensors: CPU_Mapped model buffer size = 303.75 MiB
..........................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 4096
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: 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_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: 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 = 1
slot init: id 0 | task -1 | new slot n_ctx_slot = 4096
main: model loaded
main: 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: 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 launch_slot_: id 0 | task 1 | processing task
slot update_slots: id 0 | task 1 | new prompt, n_ctx_slot = 4096, n_keep = 0, n_prompt_tokens = 9
slot update_slots: id 0 | task 1 | kv cache rm [0, end)
slot update_slots: id 0 | task 1 | prompt processing progress, n_past = 9, n_tokens = 9, progress = 1.000000
slot update_slots: id 0 | task 1 | prompt done, n_past = 9, n_tokens = 9
slot release: id 0 | task 1 | stop processing: n_past = 9, truncated = 0
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 = 9
slot update_slots: id 0 | task 0 | need to evaluate at least 1 token for each active slot, n_past = 9, n_prompt_tokens = 9
slot update_slots: id 0 | task 0 | kv cache rm [8, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 9, n_tokens = 1, progress = 0.111111
slot update_slots: id 0 | task 0 | prompt done, n_past = 9, n_tokens = 1
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot release: id 0 | task 0 | 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 = 9
slot update_slots: id 0 | task 4 | need to evaluate at least 1 token for each active slot, n_past = 9, n_prompt_tokens = 9
slot update_slots: id 0 | task 4 | kv cache rm [8, end)
slot update_slots: id 0 | task 4 | prompt processing progress, n_past = 9, n_tokens = 1, progress = 0.111111
slot update_slots: id 0 | task 4 | prompt done, n_past = 9, n_tokens = 1
slot release: id 0 | task 4 | stop processing: n_past = 9, truncated = 0
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 = 9
slot update_slots: id 0 | task 6 | need to evaluate at least 1 token for each active slot, n_past = 9, n_prompt_tokens = 9
slot update_slots: id 0 | task 6 | kv cache rm [8, end)
slot update_slots: id 0 | task 6 | prompt processing progress, n_past = 9, n_tokens = 1, progress = 0.111111
slot update_slots: id 0 | task 6 | prompt done, n_past = 9, n_tokens = 1
srv log_server_r: request: POST /v1/embeddings 127.0.0.1 200
slot release: id 0 | task 6 | 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

107
logs/fastapi.log
View File

@@ -1,107 +0,0 @@
2026-02-26 19:00:57,073 - INFO - Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.
2026-02-26 19:00:57,211 - INFO - 成功找到节点定义JSON代码块
2026-02-26 19:00:57,211 - INFO - 成功解析出动作节点: ['approach_target', 'deliver_payload', 'fly_sequence', 'fly_to_waypoint', 'land', 'loiter', 'manual_confirmation', 'move_direction', 'object_detect', 'return_emergency', 'rotate', 'rotate_search', 'search_pattern', 'system_checks', 'take_photos', 'takeoff', 'track_object']
2026-02-26 19:00:57,211 - INFO - 成功解析出条件节点: ['at_waypoint', 'object_detected']
INFO: Started server process [26111]
INFO: Waiting for application startup.
2026-02-26 19:00:57,217 - INFO - WebSocket event loop configured.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
INFO: 127.0.0.1:46065 - "GET /docs HTTP/1.1" 200 OK
2026-02-26 19:01:05,074 - INFO - ========== [Stage 1] Task Understanding ==========
2026-02-26 19:01:05,881 - INFO - HTTP Request: POST http://localhost:8081/v1/chat/completions "HTTP/1.1 200 OK"
2026-02-26 19:01:05,886 - INFO - Task Understanding Results: mode=scene1, state=in_air, intent=generic_mission, risks=[]
INFO: 127.0.0.1:46071 - "POST /debug_stage HTTP/1.1" 200 OK
2026-02-26 19:01:23,412 - INFO - ========== [Stage 1] Task Understanding ==========
2026-02-26 19:01:23,780 - INFO - HTTP Request: POST http://localhost:8081/v1/chat/completions "HTTP/1.1 200 OK"
2026-02-26 19:01:23,780 - INFO - Task Understanding Results: mode=scene1, state=in_air, intent=generic_mission, risks=[]
INFO: 127.0.0.1:44329 - "POST /debug_stage HTTP/1.1" 200 OK
2026-02-26 19:01:36,748 - INFO - ========== [Stage 1] Task Understanding ==========
2026-02-26 19:01:37,168 - INFO - HTTP Request: POST http://localhost:8081/v1/chat/completions "HTTP/1.1 200 OK"
2026-02-26 19:01:37,169 - INFO - Task Understanding Results: mode=scene1, state=in_air, intent=generic_mission, risks=[]
INFO: 127.0.0.1:44483 - "POST /debug_stage HTTP/1.1" 200 OK
2026-02-26 19:15:34,050 - INFO - ========== [Stage 1] Task Understanding ==========
2026-02-26 19:15:34,569 - INFO - HTTP Request: POST http://localhost:8081/v1/chat/completions "HTTP/1.1 200 OK"
2026-02-26 19:15:34,570 - INFO - Task Understanding Results: mode=scene1, state=in_air, intent=generic_mission, risks=[]
2026-02-26 19:15:34,570 - INFO - ========== [Stage 2] Context Binding ==========
2026-02-26 19:15:34,799 - INFO - Context Binding Results: Required Actions=['Selector', 'Sequence', 'fly_to_waypoint', 'land', 'move_direction', 'object_detect', 'object_detected', 'rotate_search', 'take_photos', 'takeoff'], RAG Scopes=['location', 'pattern']
INFO: 127.0.0.1:47143 - "POST /debug_stage HTTP/1.1" 200 OK
2026-02-26 19:18:26,812 - INFO - ========== [Stage 1] Task Understanding ==========
2026-02-26 19:18:27,220 - INFO - HTTP Request: POST http://localhost:8081/v1/chat/completions "HTTP/1.1 200 OK"
2026-02-26 19:18:27,220 - INFO - Task Understanding Results: mode=scene1, state=in_air, intent=generic_mission, risks=[]
2026-02-26 19:18:27,220 - INFO - ========== [Stage 2] Context Binding ==========
2026-02-26 19:18:27,276 - INFO - Context Binding Results: Required Actions=['Selector', 'Sequence', 'fly_to_waypoint', 'land', 'move_direction', 'object_detect', 'object_detected', 'rotate_search', 'take_photos', 'takeoff'], RAG Scopes=['location', 'pattern']
2026-02-26 19:18:27,276 - INFO - ========== [Stage 3] Macro Planning (Round 1) ==========
2026-02-26 19:18:27,278 - INFO - [Round 1] System Prompt Preview (first 500 chars):
任务：根据用户的自然语言指令，规划无人机的宏观执行流程结构，并提取执行该流程所需的外部参数。
你现在是第一阶段“宏观规划与意图提取”AI。你只需要做两件事：
1. 分析意图并排出正确的骨架树（不需要填充任何 parameters/params）。
2. 从用户指令中提取出需要查询确切位置或目标属性的实体清单（如地标、方向、距离、识别目标）。
**严格约束**：仅输出符合以下 JSON 格式的数据，**禁止**包含任何外部分析、Markdown 标记外的纯文本，或者多余的字段。
输出格式约定：
```json
{
"macro_tree": { ... 纯结构树 ... },
"parameter_requests": [
{
"node": "节点名称",
"intent": "对该节点意图的简短描述",
"extracted_entities": {
"实体key": "实体value"
}
}
]
}
```
## 一、核心节点定义（裁剪后）
#### 1. 可用节点定义 (必须遵守...
2026-02-26 19:18:27,278 - INFO - [Round 1] User Prompt:
飞到广场东边50米
---
参考知识：
【地点知识】
{"property": "location", "information": {"name": "广场", "coordinates": {"x": 100, "y": 260, "z": 0}}}
{"property": "location", "information": {"name": "飞行场地", "coordinates": {"x": 0, "y": 0, "z": 0}}}
{"property": "location", "information": {"name": "大楼外围四个点东南天坐标系坐标", "coordinates": {"A": {"x": -24.0, "y": 241.8, "z": 0}, "B": {"x": -108.5, "y": 241.8, "z": 0}, "C": {"x": -108.5, "y": 289.8, "z": 0}, "D": {"x": -24.0, "y": 292.8, "z": 0}}}}
【任务模式】
无人机当前在空中，往广场西边飞200米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。
无人机当前在地面，去研究所正大门，搜索扎辫子女子，找到后拍照。
地面起飞后到面前大楼约12米高度，沿外围巡查打开窗户；如发现窗户则拍照回传。
---
2026-02-26 19:18:36,039 - INFO - HTTP Request: POST http://localhost:8081/v1/chat/completions "HTTP/1.1 200 OK"
2026-02-26 19:18:36,039 - INFO - [Round 1] Output Macro Tree:
{
"root": {
"type": "Sequence",
"name": "FlyToSquareEast50",
"children": [
{
"type": "action",
"name": "fly_to_waypoint"
}
]
}
}
2026-02-26 19:18:36,039 - INFO - [Round 1] Output Parameter Requests:
[
{
"node": "fly_to_waypoint",
"intent": "前往广场东边50米",
"extracted_entities": {
"landmark": "广场",
"direction": "东",
"distance": 50.0
}
}
]
INFO: 127.0.0.1:46185 - "POST /debug_stage HTTP/1.1" 200 OK

480
logs/inference_model.log
View File

@@ -1,480 +0,0 @@
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4060 Ti, compute capability 8.9, VMM: yes
build: 6097 (9515c613) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
system info: n_threads = 8, n_threads_batch = 8, total_threads = 16
system_info: n_threads = 8 (n_threads_batch = 8) / 16 | CUDA : ARCHS = 500,610,700,750,800,860,890 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
main: binding port with default address family
main: HTTP server is listening, hostname: 0.0.0.0, port: 8081, http threads: 15
main: loading model
srv load_model: loading model '/home/huangfukk/models/gguf/Qwen3/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/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
llama_model_loader: - kv 2: general.name str = Qwen3 4B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Qwen3
llama_model_loader: - kv 5: general.size_label str = 4B
llama_model_loader: - kv 6: qwen3.block_count u32 = 36
llama_model_loader: - kv 7: qwen3.context_length u32 = 40960
llama_model_loader: - kv 8: qwen3.embedding_length u32 = 2560
llama_model_loader: - kv 9: qwen3.feed_forward_length u32 = 9728
llama_model_loader: - kv 10: qwen3.attention.head_count u32 = 32
llama_model_loader: - kv 11: qwen3.attention.head_count_kv u32 = 8
llama_model_loader: - kv 12: qwen3.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 13: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 14: qwen3.attention.key_length u32 = 128
llama_model_loader: - kv 15: qwen3.attention.value_length u32 = 128
llama_model_loader: - kv 16: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 17: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 19: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 20: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 21: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 25: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 26: general.quantization_version u32 = 2
llama_model_loader: - kv 27: general.file_type u32 = 17
llama_model_loader: - type f32: 145 tensors
llama_model_loader: - type q5_K: 216 tensors
llama_model_loader: - type q6_K: 37 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q5_K - Medium
print_info: file size = 2.69 GiB (5.73 BPW)
load: printing all EOG tokens:
load: - 151643 ('<|endoftext|>')
load: - 151645 ('<|im_end|>')
load: - 151662 ('<|fim_pad|>')
load: - 151663 ('<|repo_name|>')
load: - 151664 ('<|file_sep|>')
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen3
print_info: vocab_only = 0
print_info: n_ctx_train = 40960
print_info: n_embd = 2560
print_info: n_layer = 36
print_info: n_head = 32
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 4
print_info: n_embd_k_gqa = 1024
print_info: n_embd_v_gqa = 1024
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-06
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: f_attn_scale = 0.0e+00
print_info: n_ff = 9728
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = -1
print_info: rope type = 2
print_info: rope scaling = linear
print_info: freq_base_train = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 40960
print_info: rope_finetuned = unknown
print_info: model type = 4B
print_info: model params = 4.02 B
print_info: general.name = Qwen3 4B Instruct
print_info: vocab type = BPE
print_info: n_vocab = 151936
print_info: n_merges = 151387
print_info: BOS token = 151643 '<|endoftext|>'
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151643 '<|endoftext|>'
print_info: LF token = 198 'Ċ'
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
print_info: FIM MID token = 151660 '<|fim_middle|>'
print_info: FIM PAD token = 151662 '<|fim_pad|>'
print_info: FIM REP token = 151663 '<|repo_name|>'
print_info: FIM SEP token = 151664 '<|file_sep|>'
print_info: EOG token = 151643 '<|endoftext|>'
print_info: EOG token = 151645 '<|im_end|>'
print_info: EOG token = 151662 '<|fim_pad|>'
print_info: EOG token = 151663 '<|repo_name|>'
print_info: EOG token = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 36 repeating layers to GPU
load_tensors: offloaded 36/37 layers to GPU
load_tensors: CUDA0 model buffer size = 2445.68 MiB
load_tensors: CPU_Mapped model buffer size = 304.29 MiB
..........................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 16384
llama_context: n_ctx_per_seq = 16384
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: kv_unified = false
llama_context: freq_base = 1000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (16384) < 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 = 2304.00 MiB
llama_kv_cache_unified: size = 2304.00 MiB ( 16384 cells, 36 layers, 1/1 seqs), K (f16): 1152.00 MiB, V (f16): 1152.00 MiB
llama_context: CUDA0 compute buffer size = 1086.01 MiB
llama_context: CUDA_Host compute buffer size = 41.01 MiB
llama_context: graph nodes = 1410
llama_context: graph splits = 4 (with bs=512), 3 (with bs=1)
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 16384
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 = 16384
main: model loaded
main: chat template, chat_template: {%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for index in range(ns.last_query_index, -1, -1) %}
{%- set message = messages[index] %}
{%- if ns.multi_step_tool and message.role == "user" and not('<tool_response>' in message.content and '</tool_response>' in message.content) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set content = message.content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in message.content %}
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}, example_format: '<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Hello<|im_end|>
<|im_start|>assistant
Hi there<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
'
main: server is listening on http://0.0.0.0:8081 - starting the main loop
srv update_slots: all slots are idle
srv log_server_r: request: GET /health 127.0.0.1 200
srv params_from_: Chat format: Content-only
slot launch_slot_: id 0 | task 0 | processing task
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 423
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 423, n_tokens = 423, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_past = 423, n_tokens = 423
slot release: id 0 | task 0 | stop processing: n_past = 429, truncated = 0
slot print_timing: id 0 | task 0 |
prompt eval time = 534.22 ms / 423 tokens ( 1.26 ms per token, 791.81 tokens per second)
eval time = 155.33 ms / 7 tokens ( 22.19 ms per token, 45.07 tokens per second)
total time = 689.55 ms / 430 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 8 | processing task
slot update_slots: id 0 | task 8 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 423
slot update_slots: id 0 | task 8 | kv cache rm [409, end)
slot update_slots: id 0 | task 8 | prompt processing progress, n_past = 423, n_tokens = 14, progress = 0.033097
slot update_slots: id 0 | task 8 | prompt done, n_past = 423, n_tokens = 14
slot release: id 0 | task 8 | stop processing: n_past = 429, truncated = 0
slot print_timing: id 0 | task 8 |
prompt eval time = 214.36 ms / 14 tokens ( 15.31 ms per token, 65.31 tokens per second)
eval time = 146.82 ms / 7 tokens ( 20.97 ms per token, 47.68 tokens per second)
total time = 361.19 ms / 21 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 16 | processing task
slot update_slots: id 0 | task 16 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 423
slot update_slots: id 0 | task 16 | kv cache rm [408, end)
slot update_slots: id 0 | task 16 | prompt processing progress, n_past = 423, n_tokens = 15, progress = 0.035461
slot update_slots: id 0 | task 16 | prompt done, n_past = 423, n_tokens = 15
slot release: id 0 | task 16 | stop processing: n_past = 429, truncated = 0
slot print_timing: id 0 | task 16 |
prompt eval time = 270.02 ms / 15 tokens ( 18.00 ms per token, 55.55 tokens per second)
eval time = 144.12 ms / 7 tokens ( 20.59 ms per token, 48.57 tokens per second)
total time = 414.14 ms / 22 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 24 | processing task
slot update_slots: id 0 | task 24 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 422
slot update_slots: id 0 | task 24 | kv cache rm [400, end)
slot update_slots: id 0 | task 24 | prompt processing progress, n_past = 422, n_tokens = 22, progress = 0.052133
slot update_slots: id 0 | task 24 | prompt done, n_past = 422, n_tokens = 22
slot release: id 0 | task 24 | stop processing: n_past = 596, truncated = 0
slot print_timing: id 0 | task 24 |
prompt eval time = 399.30 ms / 22 tokens ( 18.15 ms per token, 55.10 tokens per second)
eval time = 3861.49 ms / 175 tokens ( 22.07 ms per token, 45.32 tokens per second)
total time = 4260.79 ms / 197 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 200 | processing task
slot update_slots: id 0 | task 200 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 426
slot update_slots: id 0 | task 200 | kv cache rm [417, end)
slot update_slots: id 0 | task 200 | prompt processing progress, n_past = 426, n_tokens = 9, progress = 0.021127
slot update_slots: id 0 | task 200 | prompt done, n_past = 426, n_tokens = 9
slot release: id 0 | task 200 | stop processing: n_past = 436, truncated = 0
slot print_timing: id 0 | task 200 |
prompt eval time = 253.59 ms / 9 tokens ( 28.18 ms per token, 35.49 tokens per second)
eval time = 234.29 ms / 11 tokens ( 21.30 ms per token, 46.95 tokens per second)
total time = 487.87 ms / 20 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 212 | processing task
slot update_slots: id 0 | task 212 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 426
slot update_slots: id 0 | task 212 | need to evaluate at least 1 token for each active slot, n_past = 426, n_prompt_tokens = 426
slot update_slots: id 0 | task 212 | kv cache rm [425, end)
slot update_slots: id 0 | task 212 | prompt processing progress, n_past = 426, n_tokens = 1, progress = 0.002347
slot update_slots: id 0 | task 212 | prompt done, n_past = 426, n_tokens = 1
slot release: id 0 | task 212 | stop processing: n_past = 436, truncated = 0
slot print_timing: id 0 | task 212 |
prompt eval time = 24.00 ms / 1 tokens ( 24.00 ms per token, 41.67 tokens per second)
eval time = 234.10 ms / 11 tokens ( 21.28 ms per token, 46.99 tokens per second)
total time = 258.10 ms / 12 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 224 | processing task
slot update_slots: id 0 | task 224 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 426
slot update_slots: id 0 | task 224 | need to evaluate at least 1 token for each active slot, n_past = 426, n_prompt_tokens = 426
slot update_slots: id 0 | task 224 | kv cache rm [425, end)
slot update_slots: id 0 | task 224 | prompt processing progress, n_past = 426, n_tokens = 1, progress = 0.002347
slot update_slots: id 0 | task 224 | prompt done, n_past = 426, n_tokens = 1
slot release: id 0 | task 224 | stop processing: n_past = 436, truncated = 0
slot print_timing: id 0 | task 224 |
prompt eval time = 42.68 ms / 1 tokens ( 42.68 ms per token, 23.43 tokens per second)
eval time = 369.06 ms / 11 tokens ( 33.55 ms per token, 29.81 tokens per second)
total time = 411.74 ms / 12 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 236 | processing task
slot update_slots: id 0 | task 236 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 426
slot update_slots: id 0 | task 236 | need to evaluate at least 1 token for each active slot, n_past = 426, n_prompt_tokens = 426
slot update_slots: id 0 | task 236 | kv cache rm [425, end)
slot update_slots: id 0 | task 236 | prompt processing progress, n_past = 426, n_tokens = 1, progress = 0.002347
slot update_slots: id 0 | task 236 | prompt done, n_past = 426, n_tokens = 1
slot release: id 0 | task 236 | stop processing: n_past = 436, truncated = 0
slot print_timing: id 0 | task 236 |
prompt eval time = 35.69 ms / 1 tokens ( 35.69 ms per token, 28.02 tokens per second)
eval time = 272.33 ms / 11 tokens ( 24.76 ms per token, 40.39 tokens per second)
total time = 308.02 ms / 12 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 248 | processing task
slot update_slots: id 0 | task 248 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 426
slot update_slots: id 0 | task 248 | need to evaluate at least 1 token for each active slot, n_past = 426, n_prompt_tokens = 426
slot update_slots: id 0 | task 248 | kv cache rm [425, end)
slot update_slots: id 0 | task 248 | prompt processing progress, n_past = 426, n_tokens = 1, progress = 0.002347
slot update_slots: id 0 | task 248 | prompt done, n_past = 426, n_tokens = 1
slot release: id 0 | task 248 | stop processing: n_past = 436, truncated = 0
slot print_timing: id 0 | task 248 |
prompt eval time = 333.94 ms / 1 tokens ( 333.94 ms per token, 2.99 tokens per second)
eval time = 222.91 ms / 11 tokens ( 20.26 ms per token, 49.35 tokens per second)
total time = 556.85 ms / 12 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 260 | processing task
slot update_slots: id 0 | task 260 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 426
slot update_slots: id 0 | task 260 | need to evaluate at least 1 token for each active slot, n_past = 426, n_prompt_tokens = 426
slot update_slots: id 0 | task 260 | kv cache rm [425, end)
slot update_slots: id 0 | task 260 | prompt processing progress, n_past = 426, n_tokens = 1, progress = 0.002347
slot update_slots: id 0 | task 260 | prompt done, n_past = 426, n_tokens = 1
slot release: id 0 | task 260 | stop processing: n_past = 436, truncated = 0
slot print_timing: id 0 | task 260 |
prompt eval time = 24.23 ms / 1 tokens ( 24.23 ms per token, 41.27 tokens per second)
eval time = 232.33 ms / 11 tokens ( 21.12 ms per token, 47.35 tokens per second)
total time = 256.56 ms / 12 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 272 | processing task
slot update_slots: id 0 | task 272 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 426
slot update_slots: id 0 | task 272 | need to evaluate at least 1 token for each active slot, n_past = 426, n_prompt_tokens = 426
slot update_slots: id 0 | task 272 | kv cache rm [425, end)
slot update_slots: id 0 | task 272 | prompt processing progress, n_past = 426, n_tokens = 1, progress = 0.002347
slot update_slots: id 0 | task 272 | prompt done, n_past = 426, n_tokens = 1
slot release: id 0 | task 272 | stop processing: n_past = 436, truncated = 0
slot print_timing: id 0 | task 272 |
prompt eval time = 32.14 ms / 1 tokens ( 32.14 ms per token, 31.11 tokens per second)
eval time = 225.34 ms / 11 tokens ( 20.49 ms per token, 48.82 tokens per second)
total time = 257.48 ms / 12 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 284 | processing task
slot update_slots: id 0 | task 284 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 180
slot update_slots: id 0 | task 284 | kv cache rm [4, end)
slot update_slots: id 0 | task 284 | prompt processing progress, n_past = 180, n_tokens = 176, progress = 0.977778
slot update_slots: id 0 | task 284 | prompt done, n_past = 180, n_tokens = 176
slot release: id 0 | task 284 | stop processing: n_past = 189, truncated = 0
slot print_timing: id 0 | task 284 |
prompt eval time = 62.74 ms / 176 tokens ( 0.36 ms per token, 2805.14 tokens per second)
eval time = 217.64 ms / 10 tokens ( 21.76 ms per token, 45.95 tokens per second)
total time = 280.39 ms / 186 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 295 | processing task
slot update_slots: id 0 | task 295 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 180
slot update_slots: id 0 | task 295 | need to evaluate at least 1 token for each active slot, n_past = 180, n_prompt_tokens = 180
slot update_slots: id 0 | task 295 | kv cache rm [179, end)
slot update_slots: id 0 | task 295 | prompt processing progress, n_past = 180, n_tokens = 1, progress = 0.005556
slot update_slots: id 0 | task 295 | prompt done, n_past = 180, n_tokens = 1
slot release: id 0 | task 295 | stop processing: n_past = 189, truncated = 0
slot print_timing: id 0 | task 295 |
prompt eval time = 24.62 ms / 1 tokens ( 24.62 ms per token, 40.62 tokens per second)
eval time = 215.17 ms / 10 tokens ( 21.52 ms per token, 46.47 tokens per second)
total time = 239.79 ms / 11 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: Hermes 2 Pro
slot launch_slot_: id 0 | task 306 | processing task
slot update_slots: id 0 | task 306 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 180
slot update_slots: id 0 | task 306 | kv cache rm [164, end)
slot update_slots: id 0 | task 306 | prompt processing progress, n_past = 180, n_tokens = 16, progress = 0.088889
slot update_slots: id 0 | task 306 | prompt done, n_past = 180, n_tokens = 16
slot release: id 0 | task 306 | stop processing: n_past = 189, truncated = 0
slot print_timing: id 0 | task 306 |
prompt eval time = 44.44 ms / 16 tokens ( 2.78 ms per token, 360.08 tokens per second)
eval time = 210.16 ms / 10 tokens ( 21.02 ms per token, 47.58 tokens per second)
total time = 254.60 ms / 26 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 317 | processing task
slot update_slots: id 0 | task 317 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 423
slot update_slots: id 0 | task 317 | kv cache rm [4, end)
slot update_slots: id 0 | task 317 | prompt processing progress, n_past = 423, n_tokens = 419, progress = 0.990544
slot update_slots: id 0 | task 317 | prompt done, n_past = 423, n_tokens = 419
slot release: id 0 | task 317 | stop processing: n_past = 429, truncated = 0
slot print_timing: id 0 | task 317 |
prompt eval time = 316.01 ms / 419 tokens ( 0.75 ms per token, 1325.92 tokens per second)
eval time = 141.87 ms / 7 tokens ( 20.27 ms per token, 49.34 tokens per second)
total time = 457.88 ms / 426 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 325 | processing task
slot update_slots: id 0 | task 325 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 423
slot update_slots: id 0 | task 325 | need to evaluate at least 1 token for each active slot, n_past = 423, n_prompt_tokens = 423
slot update_slots: id 0 | task 325 | kv cache rm [422, end)
slot update_slots: id 0 | task 325 | prompt processing progress, n_past = 423, n_tokens = 1, progress = 0.002364
slot update_slots: id 0 | task 325 | prompt done, n_past = 423, n_tokens = 1
slot release: id 0 | task 325 | stop processing: n_past = 429, truncated = 0
slot print_timing: id 0 | task 325 |
prompt eval time = 256.66 ms / 1 tokens ( 256.66 ms per token, 3.90 tokens per second)
eval time = 143.27 ms / 7 tokens ( 20.47 ms per token, 48.86 tokens per second)
total time = 399.92 ms / 8 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 333 | processing task
slot update_slots: id 0 | task 333 | new prompt, n_ctx_slot = 16384, n_keep = 0, n_prompt_tokens = 7547
slot update_slots: id 0 | task 333 | kv cache rm [3, end)
slot update_slots: id 0 | task 333 | prompt processing progress, n_past = 2051, n_tokens = 2048, progress = 0.271366
slot update_slots: id 0 | task 333 | kv cache rm [2051, end)
slot update_slots: id 0 | task 333 | prompt processing progress, n_past = 4099, n_tokens = 2048, progress = 0.542732
slot update_slots: id 0 | task 333 | kv cache rm [4099, end)
slot update_slots: id 0 | task 333 | prompt processing progress, n_past = 6147, n_tokens = 2048, progress = 0.814098
slot update_slots: id 0 | task 333 | kv cache rm [6147, end)
slot update_slots: id 0 | task 333 | prompt processing progress, n_past = 7547, n_tokens = 1400, progress = 0.999602
slot update_slots: id 0 | task 333 | prompt done, n_past = 7547, n_tokens = 1400
slot release: id 0 | task 333 | stop processing: n_past = 7680, truncated = 0
slot print_timing: id 0 | task 333 |
prompt eval time = 4829.54 ms / 7544 tokens ( 0.64 ms per token, 1562.05 tokens per second)
eval time = 3913.28 ms / 134 tokens ( 29.20 ms per token, 34.24 tokens per second)
total time = 8742.83 ms / 7678 tokens
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200

3
logs/services.pid
View File

@@ -1,3 +0,0 @@
26023
26024
26109

2
logs/services_vllm.pid
View File

@@ -1,2 +0,0 @@
43538
43539

150
logs/vllm_inference_model.log
View File

@@ -1,150 +0,0 @@
[DEBUG] conda_env=VLLM
[DEBUG] CONDA_PREFIX=/home/huangfukk/miniconda3/envs/VLLM
[DEBUG] which python: /home/huangfukk/miniconda3/envs/VLLM/bin/python
[DEBUG] which vllm: /home/huangfukk/miniconda3/envs/VLLM/bin/vllm
0.13.0
[DEBUG] python: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:16:04) [GCC 11.2.0]
[DEBUG] torch: 2.9.0+cu128 cuda: 12.8 available: True
(APIServer pid=43538) INFO 01-20 16:25:05 [api_server.py:1351] vLLM API server version 0.13.0
(APIServer pid=43538) INFO 01-20 16:25:05 [utils.py:253] non-default args: {'model_tag': '/home/huangfukk/models/AWQ/Qwen3-4B-Instruct-2507', 'host': '0.0.0.0', 'port': 8081, 'uvicorn_log_level': 'debug', 'chat_template': '/home/huangfukk/DronePlanning/tools/vllm_templates/qwen3_xml_tool.jinja', 'chat_template_content_format': 'string', 'enable_auto_tool_choice': True, 'tool_call_parser': 'qwen3_xml', 'model': '/home/huangfukk/models/AWQ/Qwen3-4B-Instruct-2507', 'trust_remote_code': True, 'max_model_len': 16384, 'served_model_name': ['local-model'], 'max_parallel_loading_workers': 4, 'gpu_memory_utilization': 0.5, 'max_num_seqs': 1}
(APIServer pid=43538) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
(APIServer pid=43538) INFO 01-20 16:25:05 [model.py:514] Resolved architecture: Qwen3ForCausalLM
(APIServer pid=43538) INFO 01-20 16:25:05 [model.py:1661] Using max model len 16384
(APIServer pid=43538) INFO 01-20 16:25:05 [awq_marlin.py:162] The model is convertible to awq_marlin during runtime. Using awq_marlin kernel.
(APIServer pid=43538) WARNING 01-20 16:25:05 [parallel.py:595] max_parallel_loading_workers is currently not supported and will be ignored.
(APIServer pid=43538) INFO 01-20 16:25:05 [scheduler.py:230] Chunked prefill is enabled with max_num_batched_tokens=2048.
(APIServer pid=43538) WARNING 01-20 16:25:06 [interface.py:465] Using 'pin_memory=False' as WSL is detected. This may slow down the performance.
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:10 [core.py:93] Initializing a V1 LLM engine (v0.13.0) with config: model='/home/huangfukk/models/AWQ/Qwen3-4B-Instruct-2507', speculative_config=None, tokenizer='/home/huangfukk/models/AWQ/Qwen3-4B-Instruct-2507', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=16384, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=awq_marlin, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False), seed=0, served_model_name=local-model, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::kda_attention', 'vllm::sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'compile_ranges_split_points': [2048], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': True, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 2, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False}, 'local_cache_dir': None}
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:11 [parallel_state.py:1203] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://192.168.31.62:43504 backend=nccl
[W120 16:25:21.543804205 socket.cpp:209] [c10d] The hostname of the client socket cannot be retrieved. err=-3
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:21 [parallel_state.py:1411] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0
(EngineCore_DP0 pid=43785) WARNING 01-20 16:25:21 [interface.py:465] Using 'pin_memory=False' as WSL is detected. This may slow down the performance.
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:22 [gpu_model_runner.py:3562] Starting to load model /home/huangfukk/models/AWQ/Qwen3-4B-Instruct-2507...
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:22 [cuda.py:351] Using FLASH_ATTN attention backend out of potential backends: ('FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION')
(EngineCore_DP0 pid=43785)
Loading safetensors checkpoint shards: 0% Completed | 0/1 [00:00<?, ?it/s]
(EngineCore_DP0 pid=43785)
Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:03<00:00, 3.71s/it]
(EngineCore_DP0 pid=43785)
Loading safetensors checkpoint shards: 100% Completed | 1/1 [00:03<00:00, 3.71s/it]
(EngineCore_DP0 pid=43785)
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:26 [default_loader.py:308] Loading weights took 2.68 seconds
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:27 [gpu_model_runner.py:3659] Model loading took 2.5630 GiB memory and 3.642749 seconds
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:34 [backends.py:643] Using cache directory: /home/huangfukk/.cache/vllm/torch_compile_cache/d651665fcd/rank_0_0/backbone for vLLM's torch.compile
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:34 [backends.py:703] Dynamo bytecode transform time: 7.23 s
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:39 [backends.py:226] Directly load the compiled graph(s) for compile range (1, 2048) from the cache, took 1.264 s
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:39 [monitor.py:34] torch.compile takes 8.49 s in total
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:40 [gpu_worker.py:375] Available KV cache memory: 5.26 GiB
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:40 [kv_cache_utils.py:1291] GPU KV cache size: 38,288 tokens
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:40 [kv_cache_utils.py:1296] Maximum concurrency for 16,384 tokens per request: 2.34x
(EngineCore_DP0 pid=43785)
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 0%| | 0/2 [00:00<?, ?it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|██████████| 2/2 [00:00<00:00, 21.01it/s]
(EngineCore_DP0 pid=43785)
Capturing CUDA graphs (decode, FULL): 0%| | 0/1 [00:00<?, ?it/s]
Capturing CUDA graphs (decode, FULL): 100%|██████████| 1/1 [00:00<00:00, 12.71it/s]
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:40 [gpu_model_runner.py:4587] Graph capturing finished in 1 secs, took 0.02 GiB
(EngineCore_DP0 pid=43785) INFO 01-20 16:25:40 [core.py:259] init engine (profile, create kv cache, warmup model) took 13.61 seconds
(APIServer pid=43538) INFO 01-20 16:25:41 [api_server.py:1099] Supported tasks: ['generate']
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] Using supplied chat template: {%- if tools %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_start|>system
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- if messages[0].role == 'system' -%}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {{ messages[0].content }}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- else -%}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] You are a helpful assistant.
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- endif -%}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312]
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] # Tools
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] You may call one or more functions to assist with the user query.
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] The function signatures are provided below:
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <tools>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- for tool in tools %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {{ tool | tojson }}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- endfor %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] </tools>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312]
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] When you need to call a tool, respond with XML tags in this exact format:
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <tool_call>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <function=tool_name>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <parameter=param1>value1</parameter>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <parameter=param2>value2</parameter>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] </function>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] </tool_call>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_end|>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- else %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- if messages[0].role == 'system' -%}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_start|>system
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {{ messages[0].content }}<|im_end|>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- endif -%}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- endif %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312]
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- for message in messages %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_start|>{{ message.role }}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {{ message.content }}<|im_end|>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- elif message.role == "assistant" %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_start|>assistant
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- if message.content %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {{ message.content }}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- endif %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_end|>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- elif message.role == "tool" %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_start|>user
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <tool_response>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {{ message.content }}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] </tool_response>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_end|>
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- endif %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- endfor %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312]
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- if add_generation_prompt %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] <|im_start|>assistant
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] {%- endif %}
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312]
(APIServer pid=43538) WARNING 01-20 16:25:42 [utils.py:312] It is different from official chat template '/home/huangfukk/models/AWQ/Qwen3-4B-Instruct-2507'. This discrepancy may lead to performance degradation.
(APIServer pid=43538) WARNING 01-20 16:25:42 [model.py:1487] Default sampling parameters have been overridden by the model's Hugging Face generation config recommended from the model creator. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.
(APIServer pid=43538) INFO 01-20 16:25:42 [serving_responses.py:201] Using default chat sampling params from model: {'temperature': 0.7, 'top_k': 20, 'top_p': 0.8}
(APIServer pid=43538) INFO 01-20 16:25:42 [serving_engine.py:270] "auto" tool choice has been enabled.
(APIServer pid=43538) INFO 01-20 16:25:42 [serving_engine.py:270] "auto" tool choice has been enabled.
(APIServer pid=43538) INFO 01-20 16:25:42 [serving_chat.py:137] Using default chat sampling params from model: {'temperature': 0.7, 'top_k': 20, 'top_p': 0.8}
(APIServer pid=43538) INFO 01-20 16:25:42 [serving_completion.py:77] Using default completion sampling params from model: {'temperature': 0.7, 'top_k': 20, 'top_p': 0.8}
(APIServer pid=43538) INFO 01-20 16:25:42 [serving_engine.py:270] "auto" tool choice has been enabled.
(APIServer pid=43538) INFO 01-20 16:25:42 [serving_chat.py:137] Using default chat sampling params from model: {'temperature': 0.7, 'top_k': 20, 'top_p': 0.8}
(APIServer pid=43538) INFO 01-20 16:25:42 [api_server.py:1425] Starting vLLM API server 0 on http://0.0.0.0:8081
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:38] Available routes are:
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /openapi.json, Methods: GET, HEAD
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /docs, Methods: GET, HEAD
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: GET, HEAD
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /redoc, Methods: GET, HEAD
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /scale_elastic_ep, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /is_scaling_elastic_ep, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /tokenize, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /detokenize, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /inference/v1/generate, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /pause, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /resume, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /is_paused, Methods: GET
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /metrics, Methods: GET
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /health, Methods: GET
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /load, Methods: GET
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/models, Methods: GET
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /version, Methods: GET
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/responses, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/responses/{response_id}, Methods: GET
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/responses/{response_id}/cancel, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/messages, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/chat/completions, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/completions, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/audio/transcriptions, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/audio/translations, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /ping, Methods: GET
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /ping, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /invocations, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /classify, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/embeddings, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /score, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/score, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /rerank, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v1/rerank, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /v2/rerank, Methods: POST
(APIServer pid=43538) INFO 01-20 16:25:42 [launcher.py:46] Route: /pooling, Methods: POST

BIN
tools/rag/vector_store/432998d6-0171-48e2-b1dd-888168f2549f/data_level0.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/432998d6-0171-48e2-b1dd-888168f2549f/header.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/432998d6-0171-48e2-b1dd-888168f2549f/length.bin
View File

Binary file not shown.

0
tools/rag/vector_store/432998d6-0171-48e2-b1dd-888168f2549f/link_lists.bin
View File

BIN
tools/rag/vector_store/93a1b605-dd3b-4cf6-b2f6-60c3e3cca5cb/data_level0.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/93a1b605-dd3b-4cf6-b2f6-60c3e3cca5cb/header.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/93a1b605-dd3b-4cf6-b2f6-60c3e3cca5cb/length.bin
View File

Binary file not shown.

0
tools/rag/vector_store/93a1b605-dd3b-4cf6-b2f6-60c3e3cca5cb/link_lists.bin
View File

BIN
tools/rag/vector_store/cb34653b-ced6-4028-80bd-cb20ec5d8251/data_level0.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/cb34653b-ced6-4028-80bd-cb20ec5d8251/header.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/cb34653b-ced6-4028-80bd-cb20ec5d8251/length.bin
View File

Binary file not shown.

0
tools/rag/vector_store/cb34653b-ced6-4028-80bd-cb20ec5d8251/link_lists.bin
View File

BIN
tools/rag/vector_store/ce707eb5-3cab-4107-9c61-f56f4c6f6efb/data_level0.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/ce707eb5-3cab-4107-9c61-f56f4c6f6efb/header.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/ce707eb5-3cab-4107-9c61-f56f4c6f6efb/length.bin
View File

Binary file not shown.

0
tools/rag/vector_store/ce707eb5-3cab-4107-9c61-f56f4c6f6efb/link_lists.bin
View File

BIN
tools/rag/vector_store/chroma.sqlite3
View File

Binary file not shown.

BIN
tools/rag/vector_store/eb012611-c2fa-46d6-9b5a-234ffcd5a720/data_level0.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/eb012611-c2fa-46d6-9b5a-234ffcd5a720/header.bin
View File

Binary file not shown.

BIN
tools/rag/vector_store/eb012611-c2fa-46d6-9b5a-234ffcd5a720/length.bin
View File

Binary file not shown.

0
tools/rag/vector_store/eb012611-c2fa-46d6-9b5a-234ffcd5a720/link_lists.bin
View File

10
tools/test_validate/validation/20260203224629/instructions_backup.txt
View File

@@ -1,10 +0,0 @@
无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。
无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。
无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。
无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。
无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。
无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。
无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。
无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。
无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。

11
tools/test_validate/validation/20260203224629/test_details.csv
View File

@@ -1,11 +0,0 @@
instruction,run_id,success,latency,error
无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。,1,True,13.293935775756836,
无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。,1,True,10.266583442687988,
无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。,1,True,11.274949550628662,
无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。,1,True,1.6364917755126953,
无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。,1,True,10.27147102355957,
无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。,1,True,13.89813232421875,
无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。,1,True,3.24064302444458,
无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。,1,True,19.873026847839355,
无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。,1,True,13.099174499511719,
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。,1,True,8.792617082595825,
1 instruction run_id success latency error
2 无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。 1 True 13.293935775756836
3 无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。 1 True 10.266583442687988
4 无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。 1 True 11.274949550628662
5 无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。 1 True 1.6364917755126953
6 无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。 1 True 10.27147102355957
7 无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。 1 True 13.89813232421875
8 无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。 1 True 3.24064302444458
9 无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。 1 True 19.873026847839355
10 无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。 1 True 13.099174499511719
11 无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。 1 True 8.792617082595825

11
tools/test_validate/validation/20260203224629/test_summary.csv
View File

@@ -1,11 +0,0 @@
Instruction,Total Runs,Success Runs,Success Rate,Avg Latency
无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。,1,1,100.0%,13.29s
无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。,1,1,100.0%,10.27s
无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。,1,1,100.0%,11.27s
无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。,1,1,100.0%,1.64s
无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。,1,1,100.0%,10.27s
无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。,1,1,100.0%,13.90s
无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。,1,1,100.0%,3.24s
无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。,1,1,100.0%,19.87s
无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。,1,1,100.0%,13.10s
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。,1,1,100.0%,8.79s
1 Instruction Total Runs Success Runs Success Rate Avg Latency
2 无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。 1 1 100.0% 13.29s
3 无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。 1 1 100.0% 10.27s
4 无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。 1 1 100.0% 11.27s
5 无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。 1 1 100.0% 1.64s
6 无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。 1 1 100.0% 10.27s
7 无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。 1 1 100.0% 13.90s
8 无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。 1 1 100.0% 3.24s
9 无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。 1 1 100.0% 19.87s
10 无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。 1 1 100.0% 13.10s
11 无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。 1 1 100.0% 8.79s

68
tools/test_validate/validation/20260203224629/无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 65 KiB

14
tools/test_validate/validation/20260203224629/无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 10 KiB

15
tools/test_validate/validation/20260203224629/无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 9.9 KiB

63
tools/test_validate/validation/20260203224629/无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 91 KiB

52
tools/test_validate/validation/20260203224629/无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 67 KiB

45
tools/test_validate/validation/20260203224629/无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 45 KiB

74
tools/test_validate/validation/20260203224629/无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 87 KiB

47
tools/test_validate/validation/20260203224629/无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 55 KiB

36
tools/test_validate/validation/20260203224629/无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203224629/无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 29 KiB

3
tools/test_validate/validation/20260203224629/无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。/1.json
View File

@@ -1,3 +0,0 @@
{
"error": "在3次尝试后，仍未能生成一个有效的Pytree。"
}

10
tools/test_validate/validation/20260203225625/instructions_backup.txt
View File

@@ -1,10 +0,0 @@
无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。
无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。
无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。
无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。
无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。
无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。
无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。
无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。
无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。

11
tools/test_validate/validation/20260203225625/test_details.csv
View File

@@ -1,11 +0,0 @@
instruction,run_id,success,latency,error
无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。,1,True,14.206302165985107,
无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。,1,True,9.870139360427856,
无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。,1,True,11.775025844573975,
无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。,1,True,10.768753051757812,
无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。,1,True,10.050657749176025,
无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。,1,True,13.982521057128906,
无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。,1,True,12.104306697845459,
无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。,1,True,21.10497808456421,
无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。,1,True,11.49827790260315,
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。,1,True,9.288247346878052,
1 instruction run_id success latency error
2 无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。 1 True 14.206302165985107
3 无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。 1 True 9.870139360427856
4 无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。 1 True 11.775025844573975
5 无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。 1 True 10.768753051757812
6 无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。 1 True 10.050657749176025
7 无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。 1 True 13.982521057128906
8 无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。 1 True 12.104306697845459
9 无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。 1 True 21.10497808456421
10 无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。 1 True 11.49827790260315
11 无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。 1 True 9.288247346878052

11
tools/test_validate/validation/20260203225625/test_summary.csv
View File

@@ -1,11 +0,0 @@
Instruction,Total Runs,Success Runs,Success Rate,Avg Latency
无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。,1,1,100.0%,14.21s
无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。,1,1,100.0%,9.87s
无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。,1,1,100.0%,11.78s
无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。,1,1,100.0%,10.77s
无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。,1,1,100.0%,10.05s
无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。,1,1,100.0%,13.98s
无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。,1,1,100.0%,12.10s
无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。,1,1,100.0%,21.10s
无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。,1,1,100.0%,11.50s
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。,1,1,100.0%,9.29s
1 Instruction Total Runs Success Runs Success Rate Avg Latency
2 无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。 1 1 100.0% 14.21s
3 无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。 1 1 100.0% 9.87s
4 无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。 1 1 100.0% 11.78s
5 无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。 1 1 100.0% 10.77s
6 无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。 1 1 100.0% 10.05s
7 无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。 1 1 100.0% 13.98s
8 无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。 1 1 100.0% 12.10s
9 无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。 1 1 100.0% 21.10s
10 无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。 1 1 100.0% 11.50s
11 无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。 1 1 100.0% 9.29s

68
tools/test_validate/validation/20260203225625/无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 65 KiB

59
tools/test_validate/validation/20260203225625/无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 56 KiB

68
tools/test_validate/validation/20260203225625/无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 63 KiB

63
tools/test_validate/validation/20260203225625/无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 91 KiB

52
tools/test_validate/validation/20260203225625/无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 67 KiB

45
tools/test_validate/validation/20260203225625/无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 45 KiB

74
tools/test_validate/validation/20260203225625/无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 87 KiB

47
tools/test_validate/validation/20260203225625/无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 55 KiB

36
tools/test_validate/validation/20260203225625/无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260203225625/无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 29 KiB

3
tools/test_validate/validation/20260203225625/无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。/1.json
View File

@@ -1,3 +0,0 @@
{
"error": "在3次尝试后，仍未能生成一个有效的Pytree。"
}

10
tools/test_validate/validation/20260221090219/instructions_backup.txt
View File

@@ -1,10 +0,0 @@
无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。
无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。
无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。
无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。
无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。
无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。
无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。
无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。
无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。

65
tools/test_validate/validation/20260221090219/无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260221090219/无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 86 KiB

10
tools/test_validate/validation/20260224120937/instructions_backup.txt
View File

@@ -1,10 +0,0 @@
无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。
无人机当前在空中，回到飞行场地，对戴帽子的人进行拍照。
无人机当前在空中，去飞行场地西边50米，对过往穿红色衣服的人拍张照，然后返航。
无人机当前在地面，到飞行场地查找长头发的人，看见了拍个照片。
无人机当前在空中，搜索穿红色衣服的人，搜索到了拍张照，我确认后再决定要不要返航。
无人机当前在空中，往飞行场地西边飞50米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。
无人机当前在地面，到飞行场地，发现未带帽子的飞近后拍照。
无人机当前在空中，紧急回到飞行场地，看见了树之后直接降落。
无人机当前在地面，快速去往东边30米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。

65
tools/test_validate/validation/20260224120937/无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224120937/无人机当前在地面，到飞行场地查找穿红色衣服的男子，找到后近距离拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 86 KiB

9
tools/test_validate/validation/20260224121211/instructions_backup.txt
View File

@@ -1,9 +0,0 @@
无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有打开的窗户，发现则进行拍照。
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有打开的窗户并拍照。
无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有打开的窗户，看到了就拍照传回来。
无人机当前在地面，去面前大楼的12米高处，绕着外围巡视杂物堆积现象，发现则进行拍照。
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的杂物堆积并拍照。
无人机当前在空中，往下飞3米，接着绕这栋楼外围侦察有没有杂物堆积，看到了就拍照传回来。
无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有人，发现则进行拍照。
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的人并拍照。
无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有人，看到了就拍照传回来。

10
tools/test_validate/validation/20260224121211/test_details.csv
View File

@@ -1,10 +0,0 @@
instruction,run_id,success,latency,error
无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有打开的窗户，发现则进行拍照。,1,True,16.063878774642944,
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有打开的窗户并拍照。,1,False,16.235912084579468,500 Server Error: Internal Server Error for url: http://127.0.0.1:8000/generate_plan
无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有打开的窗户，看到了就拍照传回来。,1,True,11.32945990562439,
无人机当前在地面，去面前大楼的12米高处，绕着外围巡视杂物堆积现象，发现则进行拍照。,1,False,18.68914246559143,500 Server Error: Internal Server Error for url: http://127.0.0.1:8000/generate_plan
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的杂物堆积并拍照。,1,True,14.857678651809692,
无人机当前在空中，往下飞3米，接着绕这栋楼外围侦察有没有杂物堆积，看到了就拍照传回来。,1,True,11.974151134490967,
无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有人，发现则进行拍照。,1,True,15.218279838562012,
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的人并拍照。,1,True,15.252280473709106,
无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有人，看到了就拍照传回来。,1,True,12.335286378860474,
1 instruction run_id success latency error
2 无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有打开的窗户，发现则进行拍照。 1 True 16.063878774642944
3 无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有打开的窗户并拍照。 1 False 16.235912084579468 500 Server Error: Internal Server Error for url: http://127.0.0.1:8000/generate_plan
4 无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有打开的窗户，看到了就拍照传回来。 1 True 11.32945990562439
5 无人机当前在地面，去面前大楼的12米高处，绕着外围巡视杂物堆积现象，发现则进行拍照。 1 False 18.68914246559143 500 Server Error: Internal Server Error for url: http://127.0.0.1:8000/generate_plan
6 无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的杂物堆积并拍照。 1 True 14.857678651809692
7 无人机当前在空中，往下飞3米，接着绕这栋楼外围侦察有没有杂物堆积，看到了就拍照传回来。 1 True 11.974151134490967
8 无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有人，发现则进行拍照。 1 True 15.218279838562012
9 无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的人并拍照。 1 True 15.252280473709106
10 无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有人，看到了就拍照传回来。 1 True 12.335286378860474

10
tools/test_validate/validation/20260224121211/test_summary.csv
View File

@@ -1,10 +0,0 @@
Instruction,Total Runs,Success Runs,Success Rate,Avg Latency
无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有打开的窗户，发现则进行拍照。,1,1,100.0%,16.06s
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有打开的窗户并拍照。,1,0,0.0%,0.00s
无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有打开的窗户，看到了就拍照传回来。,1,1,100.0%,11.33s
无人机当前在地面，去面前大楼的12米高处，绕着外围巡视杂物堆积现象，发现则进行拍照。,1,0,0.0%,0.00s
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的杂物堆积并拍照。,1,1,100.0%,14.86s
无人机当前在空中，往下飞3米，接着绕这栋楼外围侦察有没有杂物堆积，看到了就拍照传回来。,1,1,100.0%,11.97s
无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有人，发现则进行拍照。,1,1,100.0%,15.22s
无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的人并拍照。,1,1,100.0%,15.25s
无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有人，看到了就拍照传回来。,1,1,100.0%,12.34s
1 Instruction Total Runs Success Runs Success Rate Avg Latency
2 无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有打开的窗户，发现则进行拍照。 1 1 100.0% 16.06s
3 无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有打开的窗户并拍照。 1 0 0.0% 0.00s
4 无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有打开的窗户，看到了就拍照传回来。 1 1 100.0% 11.33s
5 无人机当前在地面，去面前大楼的12米高处，绕着外围巡视杂物堆积现象，发现则进行拍照。 1 0 0.0% 0.00s
6 无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的杂物堆积并拍照。 1 1 100.0% 14.86s
7 无人机当前在空中，往下飞3米，接着绕这栋楼外围侦察有没有杂物堆积，看到了就拍照传回来。 1 1 100.0% 11.97s
8 无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有人，发现则进行拍照。 1 1 100.0% 15.22s
9 无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的人并拍照。 1 1 100.0% 15.25s
10 无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有人，看到了就拍照传回来。 1 1 100.0% 12.34s

74
tools/test_validate/validation/20260224121211/无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的人并拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224121211/无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的人并拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 65 KiB

74
tools/test_validate/validation/20260224121211/无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的杂物堆积并拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224121211/无人机当前在地面，去面前大楼的12米高处，沿着外围查找所有的杂物堆积并拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 67 KiB

74
tools/test_validate/validation/20260224121211/无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有人，发现则进行拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224121211/无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有人，发现则进行拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 65 KiB

74
tools/test_validate/validation/20260224121211/无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有打开的窗户，发现则进行拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224121211/无人机当前在地面，去面前大楼的12米高处，绕着外围看有没有打开的窗户，发现则进行拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 67 KiB

50
tools/test_validate/validation/20260224121211/无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有人，看到了就拍照传回来。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224121211/无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有人，看到了就拍照传回来。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 61 KiB

45
tools/test_validate/validation/20260224121211/无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有打开的窗户，看到了就拍照传回来。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224121211/无人机当前在空中，再往上飞3米，接着绕这栋楼外围侦察有没有打开的窗户，看到了就拍照传回来。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 52 KiB

46
tools/test_validate/validation/20260224121211/无人机当前在空中，往下飞3米，接着绕这栋楼外围侦察有没有杂物堆积，看到了就拍照传回来。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224121211/无人机当前在空中，往下飞3米，接着绕这栋楼外围侦察有没有杂物堆积，看到了就拍照传回来。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 53 KiB

11
tools/test_validate/validation/20260224125506/instructions_backup.txt
View File

@@ -1,11 +0,0 @@
无人机当前在地面，到广场查找穿红色衣服的人，找到后近距离拍照。
无人机当前在空中，回到广场，对戴帽子的人进行拍照。
无人机当前在空中，去广场南边40米，对过往的公交车拍张照，然后返航。
无人机当前在地面，到广场查找绿色公交车，看见了拍个照片。
无人机当前在空中，搜索小汽车，搜索到了我确认后再决定要不要拍照。
无人机当前在空中，搜索小汽车，搜索到了拍张照，我确认后再决定要不要返航。
无人机当前在空中，往广场南边飞40米，持续监控5分钟，发现人就拍照告诉我，到时间可以返航。
无人机当前在地面，到广场边上的施工区域内，发现有没带安全帽的飞近后拍照。
无人机当前在空中，紧急回到广场，看见了红绿灯之后直接降落。
无人机当前在地面，快速去往东边60米，有身穿白色衣服，头戴帽子的男子在挟持他人，对其进行拍照。
无人机当前在空中，离白色衣服戴帽子的人太远了照片看不清，贴近到3米距离拍，拍完可以直接返航。

65
tools/test_validate/validation/20260224125506/无人机当前在地面，到广场查找穿红色衣服的人，找到后近距离拍照。/1.json
View File

File diff suppressed because one or more lines are too long

BIN
tools/test_validate/validation/20260224125506/无人机当前在地面，到广场查找穿红色衣服的人，找到后近距离拍照。/1.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 69 KiB

57
tools/test_validate/validation/20260224125506/无人机当前在空中，去广场南边40米，对过往的公交车拍张照，然后返航。/1.json
View File

File diff suppressed because one or more lines are too long

Some files were not shown because too many files have changed in this diff Show More