github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13066] After upgrading Ollama from version 0.12.1 to 0.12.10, the PotPlayer subtitle translation plugin request timed out with status code 500. #8653

New Issue
Open
opened 2026-04-12 21:24:34 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 21:24:34 -05:00
Owner
Copy Link

Originally created by @ABC-0101 on GitHub (Nov 13, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13066

What is the issue?

win11 25h2 16G RAW i711800h cpu 3060laptop 6G VRAW GPU
ollama serve &
time=2025-11-11T19:01:41.043+08:00 level=INFO source=routes.go:1525 msg="server config" env="map[CUDA_VISIBLE_DEVICES:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:E:\Ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-11-11T19:01:41.058+08:00 level=INFO source=images.go:522 msg="total blobs: 22"
time=2025-11-11T19:01:41.060+08:00 level=INFO source=images.go:529 msg="total unused已移除 blob：0"
time=2025-11-11T19:01:41.062+08:00 level=INFO source=routes.go:1578 msg="正在监听 [::]:11434 (版本 0.12.10)"
time=2025-11-11T19:01:41.063+08:00 level=INFO source=runner.go:67 msg="正在发现可用 GPU..."
time=2025-11-11T19:01:41.076+08:00 level=INFO source=server.go:400 msg="正在启动 runner" cmd="E:\Ollama\ollama.exe runner --ollama-engine --port 6092"
time=2025-11-11T19:01:41.337+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="E:\Ollama\ollama.exe runner --ollama-engine --port 6099"
time=2025-11-11T19:01:41.577+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="E:\Ollama\ollama.exe runner --ollama-engine --port 6107"
time=2025-11-11T19:01:42.193+08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3060 笔记本电脑 GPU" libdirs=ollama,cuda_v12 driver=13.0 pci_id=0000:01:00.0 type=discrete total="6.0 GiB" available="5.0 GiB"
time=2025-11-11T19:01:42.195+08:00 level=INFO source=routes.go:1619 msg="进入低显存模式" "总显存"="6.0 GiB" threshold="20.0 GiB"
time=2025-11-11T19:01:45.311+08:00 level=INFO source=server.go:400 msg="启动运行程序" cmd="E:\Ollama\ollama.exe runner --ollama-engine --port 6115"
time=2025-11-11T19:01:45.524+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-11-11T19:01:45.524+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=8 efficiency=0 threads=16
time=2025-11-11T19:01:45.591+08:00 level=INFO source=server.go:215 msg="启用闪存注意力"
time=2025-11-11T19:01:45.592+08:00 level=INFO source=server.go:400 msg="启动运行程序" cmd="E:\Ollama\ollama.exe runner --ollama-engine --model E:\Ollama\models\blobs\sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f --port 6122"
time=2025-11-11T19:01:45.612+08:00 level=INFO source=server.go:653 msg="正在加载模型" "模型层数"=37 requested=-1
time=2025-11-11T19:01:45.612+08:00 level=INFO source=server.go:658 msg="系统内存" total="15.8 GiB" free="4.9 GiB" free_swap="6.0 GiB"
time=2025-11-11T19:01:45.612+08:00 level=INFO source=server.go:665 msg="GPU内存" id=GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 library=CUDA available="4.6 GiB" free="5.0 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-11-11T19:01:45.656+08:00 level=INFO source=runner.go:1349 msg="启动 Ollama 引擎"
time=2025-11-11T19:01:45.667+08:00 level=INFO source=runner.go:1384 msg="服务器正在监听 127.0.0.1:6122"
time=2025-11-11T19:01:45.678+08:00 level=INFO source=runner.go:1222 msg=加载请求="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-11T19:01:45.703+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3 file_type=Q4_K_M name="Qwen3 8B" description="" num_tensors=399 num_key_values=29
load_backend: loaded CPU backend from E:\Ollama\lib\ollama\ggml-cpu-icelake.dll
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS：否
ggml_cuda_init：找到 1 个 CUDA 设备：
设备 0：NVIDIA GeForce RTX 3060 笔记本电脑 GPU，计算能力 8.6，VMM：是，ID：GPU-52b31a98-e414-b31b-363a-f98b19c51bb6
load_backend：已从 E:\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll 加载 CUDA 后端
time=2025-11-11T19:01:45.816+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-11-11T19:01:46.044+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:8 GPULayers:34[ID:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 Layers:34(2..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-11T19:01:46.082+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:8 GPULayers:34[ID:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 Layers:34(2..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:8 GPULayers:34[ID:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 Layers:34(2..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=ggml.go:482 msg="将 34 个重复层卸载到 GPU"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=ggml.go:486 msg="将输出层卸载到 CPU"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=ggml.go:494 msg="已将 34/37 层卸载到 GPU"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:212 msg="模型权重" device=CUDA0 size="3.8 GiB"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:217 msg="模型权重" device=CPU size="1.0 GiB"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:223 msg="键值缓存" device=CUDA0 size="544.0 MiB"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:228 msg="kv cache" device=CPU size="32.0 MiB"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:234 msg="compute graph" device=CUDA0 size="185.0 MiB"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:239 msg="compute graph" device=CPU size="8.0 MiB"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:244 msg="总内存" size="5.6 GiB"
time=2025-11-11T19:01:46.322+08:00 level=INFO source=sched.go:500 msg="已加载的运行器" count=1
time=2025-11-11T19:01:46.322+08:00 level=INFO source=server.go:1251 msg="等待 Llama 运行器开始响应"
time=2025-11-11T19:01:46.323+08:00 level=INFO source=server.go:1285 msg="等待服务器可用" status="llm 服务器正在加载模型"
time=2025-11-11T19:01:48.827+08:00 level=INFO source=server.go:1289 msg="llama runner 启动于 3.22 秒"
[GIN] 2025/11/11 - 19:01:53 | 500 | 8.0343688s | 127.0.0.1 | POST "/v1/chat/completions"
[GIN] 2025/11/11 - 19:02:01 | 500 | 8.0124622s | 127.0.0.1 | POST "/v1/chat/completions"

Image Image Image

curl -X POST http://localhost:11434/v1/chat/completions ^ -H "Content-Type: application/json" ^ -d "{"model":
"qwen3:8b", "messages": [{"role": "user", "content": "Hello world"}]}"
{"id":"chatcmpl-915","object":"chat.completion","created":1762864706,"model":"qwen3:8b","system_fingerprint":"fp_ollama","choices":[{"index":0,"message":{"role":"assistant","content":"你好！😊 今天有什么可以帮到您的吗？无论您有疑问、需要帮助，还是只是想聊聊天，我都随时为您服务！","re​​asoning":"好的，用户刚刚说了“Hello world”。这是一个常见的问候语，也许他们正在测试是否我正在工作或者只是想开始一段对话。我应该以友好开放的方式回应。\n\n让我想想该怎么回复。我需要表现得热情友好，并邀请他们提问或分享他们需要帮助的地方。也许可以这样说：“你好！今天有什么可以帮到您的吗？”这样既直接又鼓励他们详细说明。\n\n等等，我应该更个性化一些吗？也许加个笑脸表情符号让气氛轻松一些。嗯，这样会让回复感觉更平易近人。就这么办吧。另外，确保语气积极向上，乐于助人。好的，应该可以了。\n"},"finish_reason":"stop"}],"usage":{"prompt_tokens":12,"completion_tokens":183,"total_tokens":195}}

--------PotPlayer's AngelScript console--------
Model information retrieved successfully
Parameters:
stop "<|im_start|>"
stop "<|im_end|>"
temperature 0.6
top_k 20
top_p 0.95
repeat_penalty 1
Model Info:
general.architecture: qwen3
general.basename: Qwen3
general.file_type: 15
general.license: apache-2.0
general.parameter_count: 8.19074e+09
general.quantization_version: 2
general.size_label: 8B
general.type: model
qwen3.attention.head_count: 32
qwen3.attention.head_count_kv: 8
qwen3.attention.key_length: 128
qwen3.attention.layer_norm_rms_epsilon: 1e-06
qwen3.attention.value_length: 128
qwen3.block_count: 36
qwen3.context_length: 40960
qwen3.embedding_length: 4096
qwen3.feed_forward_length: 12288
qwen3.rope.freq_base: 1000000
tokenizer.ggml.add_bos_token: false
tokenizer.ggml.bos_token_id: 151643
tokenizer.ggml.eos_token_id: 151645
tokenizer.ggml.merges: null
tokenizer.ggml.model: gpt2
tokenizer.ggml.padding_token_id: 151643
tokenizer.ggml.pre: qwen2
tokenizer.ggml.token_type: null
tokenizer.ggml.tokens: null

Successfully configured Ollama translation plugin

Model: qwen3:8b

Native thinking support: Yes

The script was aborted before it could finish. Probably it timed out.

Image

Relevant log output

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.10

Originally created by @ABC-0101 on GitHub (Nov 13, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13066 ### What is the issue? win11 25h2 16G RAW i711800h cpu 3060laptop 6G VRAW GPU ollama serve & time=2025-11-11T19:01:41.043+08:00 level=INFO source=routes.go:1525 msg="server config" env="map[CUDA_VISIBLE_DEVICES:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:E:\Ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-11-11T19:01:41.058+08:00 level=INFO source=images.go:522 msg="total blobs: 22" time=2025-11-11T19:01:41.060+08:00 level=INFO source=images.go:529 msg="total unused已移除 blob：0" time=2025-11-11T19:01:41.062+08:00 level=INFO source=routes.go:1578 msg="正在监听 [::]:11434 (版本 0.12.10)" time=2025-11-11T19:01:41.063+08:00 level=INFO source=runner.go:67 msg="正在发现可用 GPU..." time=2025-11-11T19:01:41.076+08:00 level=INFO source=server.go:400 msg="正在启动 runner" cmd="E:\Ollama\ollama.exe runner --ollama-engine --port 6092" time=2025-11-11T19:01:41.337+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="E:\Ollama\ollama.exe runner --ollama-engine --port 6099" time=2025-11-11T19:01:41.577+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="E:\Ollama\ollama.exe runner --ollama-engine --port 6107" time=2025-11-11T19:01:42.193+08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3060 笔记本电脑 GPU" libdirs=ollama,cuda_v12 driver=13.0 pci_id=0000:01:00.0 type=discrete total="6.0 GiB" available="5.0 GiB" time=2025-11-11T19:01:42.195+08:00 level=INFO source=routes.go:1619 msg="进入低显存模式" "总显存"="6.0 GiB" threshold="20.0 GiB" time=2025-11-11T19:01:45.311+08:00 level=INFO source=server.go:400 msg="启动运行程序" cmd="E:\Ollama\ollama.exe runner --ollama-engine --port 6115" time=2025-11-11T19:01:45.524+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-11-11T19:01:45.524+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=8 efficiency=0 threads=16 time=2025-11-11T19:01:45.591+08:00 level=INFO source=server.go:215 msg="启用闪存注意力" time=2025-11-11T19:01:45.592+08:00 level=INFO source=server.go:400 msg="启动运行程序" cmd="E:\Ollama\ollama.exe runner --ollama-engine --model E:\Ollama\models\blobs\sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f --port 6122" time=2025-11-11T19:01:45.612+08:00 level=INFO source=server.go:653 msg="正在加载模型" "模型层数"=37 requested=-1 time=2025-11-11T19:01:45.612+08:00 level=INFO source=server.go:658 msg="系统内存" total="15.8 GiB" free="4.9 GiB" free_swap="6.0 GiB" time=2025-11-11T19:01:45.612+08:00 level=INFO source=server.go:665 msg="GPU内存" id=GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 library=CUDA available="4.6 GiB" free="5.0 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-11-11T19:01:45.656+08:00 level=INFO source=runner.go:1349 msg="启动 Ollama 引擎" time=2025-11-11T19:01:45.667+08:00 level=INFO source=runner.go:1384 msg="服务器正在监听 127.0.0.1:6122" time=2025-11-11T19:01:45.678+08:00 level=INFO source=runner.go:1222 msg=加载请求="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-11T19:01:45.703+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3 file_type=Q4_K_M name="Qwen3 8B" description="" num_tensors=399 num_key_values=29 load_backend: loaded CPU backend from E:\Ollama\lib\ollama\ggml-cpu-icelake.dll ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS：否 ggml_cuda_init：找到 1 个 CUDA 设备： 设备 0：NVIDIA GeForce RTX 3060 笔记本电脑 GPU，计算能力 8.6，VMM：是，ID：GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 load_backend：已从 E:\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll 加载 CUDA 后端 time=2025-11-11T19:01:45.816+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-11-11T19:01:46.044+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:8 GPULayers:34[ID:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 Layers:34(2..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-11T19:01:46.082+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:8 GPULayers:34[ID:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 Layers:34(2..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-11T19:01:46.322+08:00 level=INFO source=runner.go:1222 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:8 GPULayers:34[ID:GPU-52b31a98-e414-b31b-363a-f98b19c51bb6 Layers:34(2..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-11T19:01:46.322+08:00 level=INFO source=ggml.go:482 msg="将 34 个重复层卸载到 GPU" time=2025-11-11T19:01:46.322+08:00 level=INFO source=ggml.go:486 msg="将输出层卸载到 CPU" time=2025-11-11T19:01:46.322+08:00 level=INFO source=ggml.go:494 msg="已将 34/37 层卸载到 GPU" time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:212 msg="模型权重" device=CUDA0 size="3.8 GiB" time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:217 msg="模型权重" device=CPU size="1.0 GiB" time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:223 msg="键值缓存" device=CUDA0 size="544.0 MiB" time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:228 msg="kv cache" device=CPU size="32.0 MiB" time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:234 msg="compute graph" device=CUDA0 size="185.0 MiB" time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:239 msg="compute graph" device=CPU size="8.0 MiB" time=2025-11-11T19:01:46.322+08:00 level=INFO source=device.go:244 msg="总内存" size="5.6 GiB" time=2025-11-11T19:01:46.322+08:00 level=INFO source=sched.go:500 msg="已加载的运行器" count=1 time=2025-11-11T19:01:46.322+08:00 level=INFO source=server.go:1251 msg="等待 Llama 运行器开始响应" time=2025-11-11T19:01:46.323+08:00 level=INFO source=server.go:1285 msg="等待服务器可用" status="llm 服务器正在加载模型" time=2025-11-11T19:01:48.827+08:00 level=INFO source=server.go:1289 msg="llama runner 启动于 3.22 秒" [GIN] 2025/11/11 - 19:01:53 | 500 | 8.0343688s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/11/11 - 19:02:01 | 500 | 8.0124622s | 127.0.0.1 | POST "/v1/chat/completions" <img width="2560" height="1080" alt="Image" src="https://github.com/user-attachments/assets/d8301a7d-7ffb-4bf1-adda-bba9b36dc8af" /> <img width="869" height="90" alt="Image" src="https://github.com/user-attachments/assets/25fd54d7-64a1-4b3c-8f1b-cbe951dc7867" /> <img width="1174" height="355" alt="Image" src="https://github.com/user-attachments/assets/5091fcb9-28ed-4cee-b31d-1d4c584e8144" /> curl -X POST http://localhost:11434/v1/chat/completions ^ -H "Content-Type: application/json" ^ -d "{"model": "qwen3:8b", "messages": [{"role": "user", "content": "Hello world"}]}" {"id":"chatcmpl-915","object":"chat.completion","created":1762864706,"model":"qwen3:8b","system_fingerprint":"fp_ollama","choices":[{"index":0,"message":{"role":"assistant","content":"你好！😊 今天有什么可以帮到您的吗？无论您有疑问、需要帮助，还是只是想聊聊天，我都随时为您服务！","re​​asoning":"好的，用户刚刚说了“Hello world”。这是一个常见的问候语，也许他们正在测试是否我正在工作或者只是想开始一段对话。我应该以友好开放的方式回应。\n\n让我想想该怎么回复。我需要表现得热情友好，并邀请他们提问或分享他们需要帮助的地方。也许可以这样说：“你好！今天有什么可以帮到您的吗？”这样既直接又鼓励他们详细说明。\n\n等等，我应该更个性化一些吗？也许加个笑脸表情符号让气氛轻松一些。嗯，这样会让回复感觉更平易近人。就这么办吧。另外，确保语气积极向上，乐于助人。好的，应该可以了。\n"},"finish_reason":"stop"}],"usage":{"prompt_tokens":12,"completion_tokens":183,"total_tokens":195}} --------PotPlayer's AngelScript console-------- Model information retrieved successfully Parameters: stop "<|im_start|>" stop "<|im_end|>" temperature 0.6 top_k 20 top_p 0.95 repeat_penalty 1 Model Info: general.architecture: qwen3 general.basename: Qwen3 general.file_type: 15 general.license: apache-2.0 general.parameter_count: 8.19074e+09 general.quantization_version: 2 general.size_label: 8B general.type: model qwen3.attention.head_count: 32 qwen3.attention.head_count_kv: 8 qwen3.attention.key_length: 128 qwen3.attention.layer_norm_rms_epsilon: 1e-06 qwen3.attention.value_length: 128 qwen3.block_count: 36 qwen3.context_length: 40960 qwen3.embedding_length: 4096 qwen3.feed_forward_length: 12288 qwen3.rope.freq_base: 1000000 tokenizer.ggml.add_bos_token: false tokenizer.ggml.bos_token_id: 151643 tokenizer.ggml.eos_token_id: 151645 tokenizer.ggml.merges: null tokenizer.ggml.model: gpt2 tokenizer.ggml.padding_token_id: 151643 tokenizer.ggml.pre: qwen2 tokenizer.ggml.token_type: null tokenizer.ggml.tokens: null Successfully configured Ollama translation plugin Model: qwen3:8b Native thinking support: Yes The script was aborted before it could finish. Probably it timed out. <img width="1235" height="718" alt="Image" src="https://github.com/user-attachments/assets/b1d8043b-5e95-4713-9802-adcca156cd67" /> ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.10
GiteaMirror added the bug label 2026-04-12 21:24:34 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8653
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?