go crash when trying to use any model panic: runtime error: cgo argument has Go pointer to unpinned Go pointer

[emaayan]

hi... i cleaned my ollama directory , re-installed it
took your ollama.exe and placed in the original ollama directory

, i understand i need to always use setvars. i downloaded the llama 3.2 model in r1 , turned it into ollama model but when i run it (via open web ui on the first reply i get an error in the logs:

time=2025-06-12T15:46:24.312+03:00 level=INFO source=runner.go:403 msg="The model had been load by GenAI, ov_model_path: \tmp\llama-3.2-3b-instruct-int4-ov-npu_latest\llama-3.2-3b-instruct-int4-ov-npu , GPU"
time=2025-06-12T15:46:24.453+03:00 level=INFO source=genaiserver.go:397 msg="llama runner started in 20.31 seconds"
time=2025-06-12T15:46:24.454+03:00 level=INFO source=runner.go:240 msg="Request info :\nPOST /completion HTTP/1.1\r\nHost: 127.0.0.1:32628\r\nAccept-Encoding: gzip\r\nContent-Length: 1106\r\nContent-Type: application/json\r\nUser-Agent: Go-http-client/1.1\r\n\r\n{"cache_prompt":true,"frequency_penalty":0,"image_data":null,"main_gpu":0,"max_new_token":2048,"min_p":0,"mirostat":0,"mirostat_eta":0.1,"mirostat_tau":5,"n_keep":4,"n_predict":-1,"presence_penalty":0,"prompt":"### Task:\nGenerate 1-3 broad tags categorizing the main themes of the chat history, along with 1-3 more specific subtopic tags.\n\n### Guidelines:\n- Start with high-level domains (e.g. Science, Technology, Philosophy, Arts, Politics, Business, Health, Sports, Entertainment, Education)\n- Consider including relevant subfields/subdomains if they are strongly represented throughout the conversation\n- If content is too short (less than 3 messages) or too diverse, use only [\"General\"]\n- Use the chat's primary language; default to English if multilingual\n- Prioritize accuracy over specificity\n\n### Output:\nJSON format: { \"tags\": [\"tag1\", \"tag2\", \"tag3\"] }\n\n### Chat History:\n<chat_history>\nUSER: hi.\nASSISTANT: \n</chat_history>","repeat_last_n":64,"repeat_penalty":1,"seed":-1,"stop":null,"stop_id":null,"stream":true,"temperature":1,"top_k":40,"top_p":1,"typical_p":1}"
time=2025-06-12T15:46:24.454+03:00 level=INFO source=genai.go:161 msg="Sampling Parameters - Temperature: 1.00, TopP: 1.00, TopK: 40, RepeatPenalty: 1.00"
panic: runtime error: cgo argument has Go pointer to unpinned Go pointer

goroutine 52 [running]:
github.com/ollama/ollama/genai.GenerateTextWithMetrics.func3(...)
C:/hongbo/test/ollama_ov/genai/genai.go:221
github.com/ollama/ollama/genai.GenerateTextWithMetrics(0x0, {0xc0001c6600?, 0x7ff6e8183320?}, 0xc0004a24e0, 0xc0002108f0)
C:/hongbo/test/ollama_ov/genai/genai.go:221 +0x1d2
github.com/ollama/ollama/genai/runner.(*Server).processBatch(0xc0002f3880)
C:/hongbo/test/ollama_ov/genai/runner/runner.go:150 +0x1eb
github.com/ollama/ollama/genai/runner.(*Server).run(0xc0002f3880, {0x7ff6e78dd5b0, 0xc0004a59a0})
C:/hongbo/test/ollama_ov/genai/runner/runner.go:230 +0x31
created by github.com/ollama/ollama/genai/runner.Execute in goroutine 1
C:/hongbo/test/ollama_ov/genai/runner/runner.go:454 +0x6eb
[GIN] 2025/06/12 - 15:46:24 | 500 | 20.5961542s | 127.0.0.1 | POST "/api/chat"
time=2025-06-12T15:46:24.462+03:00 level=ERROR source=genaiserver.go:255 msg="llama runner terminated" error="exit status 2"
[GIN] 2025/06/12 - 15:51:22 | 200 | 3.4991ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/06/12 - 15:51:22 | 200 | 0s | 127.0.0.1 | GET "/api/ps"

[zhaohb]

I think you should set GODEBUG=cgocheck env.
https://github.com/openvinotoolkit/openvino_contrib/tree/master/modules/ollama_openvino#start-ollama-1

please try again.

[emaayan]

tried that, at least it's not crashing, now i'm just waiting for it to reply.

I think you should set GODEBUG=cgocheck env. master/modules/ollama_openvino#start-ollama-1

please try again.

time=2025-06-13T10:27:18.270+03:00 level=INFO source=genaiserver.go:239 msg="starting llama server" cmd="C:\Users\exm1110b\AppData\Local\Programs\Ollama\ollama.exe genairunner --model C:\Users\exm1110b\.ollama\models\blobs\sha256-03d7423ac15128f8057b187c7bdeb2538f2697556d99cfae563126e3802ed89d --modelname llama-3.2-3b-instruct-int4-ov-npu:latest --device GPU --parallel 1 --port 32669"
time=2025-06-13T10:27:18.288+03:00 level=INFO source=sched.go:548 msg="loaded runners" count=1
time=2025-06-13T10:27:18.288+03:00 level=INFO source=genaiserver.go:358 msg="waiting for llama runner to start responding"
time=2025-06-13T10:27:18.289+03:00 level=INFO source=genaiserver.go:392 msg="waiting for server to become available" status="llm server error"
time=2025-06-13T10:27:18.349+03:00 level=INFO source=runner.go:441 msg="starting go genairunner"
time=2025-06-13T10:27:18.396+03:00 level=INFO source=runner.go:473 msg="Server listening on 127.0.0.1:32669"
time=2025-06-13T10:27:18.541+03:00 level=INFO source=genaiserver.go:392 msg="waiting for server to become available" status="llm server loading model"
time=2025-06-13T10:27:39.490+03:00 level=INFO source=runner.go:403 msg="The model had been load by GenAI, ov_model_path: \tmp\llama-3.2-3b-instruct-int4-ov-npu_latest\llama-3.2-3b-instruct-int4-ov-npu , GPU"
time=2025-06-13T10:27:39.605+03:00 level=INFO source=genaiserver.go:397 msg="llama runner started in 21.32 seconds"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=runner.go:240 msg="Request info :\nPOST /completion HTTP/1.1\r\nHost: 127.0.0.1:32669\r\nAccept-Encoding: gzip\r\nContent-Length: 357\r\nContent-Type: application/json\r\nUser-Agent: Go-http-client/1.1\r\n\r\n{"cache_prompt":true,"frequency_penalty":0,"image_data":null,"main_gpu":0,"max_new_token":2048,"min_p":0,"mirostat":0,"mirostat_eta":0.1,"mirostat_tau":5,"n_keep":4,"n_predict":-1,"presence_penalty":0,"prompt":"hi.","repeat_last_n":64,"repeat_penalty":1,"seed":-1,"stop":null,"stop_id":null,"stream":true,"temperature":1,"top_k":40,"top_p":1,"typical_p":1}"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:161 msg="Sampling Parameters - Temperature: 1.00, TopP: 1.00, TopK: 40, RepeatPenalty: 1.00"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:120 msg="Genai Metrics info:"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:124 msg="Load time: 0.00"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:129 msg="Generate time: 0.00 ± 0.00 ms"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:134 msg="Tokenization time: 0.00 ± 0.00 ms"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:139 msg="Detokenization time: 0.00 ± 0.00 ms"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:144 msg="TTFT: 0.00 ± 0.00 ms"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:149 msg="TPOT: 0.00 ± 0.00 ms/token"
time=2025-06-13T10:27:39.606+03:00 level=INFO source=genai.go:154 msg="Throughput: 0.00 ± 0.00 tokens/s"
[GIN] 2025/06/13 - 10:27:39 | 200 | 21.3968271s | 127.0.0.1 | POST "/api/chat"
time=2025-06-13T10:27:39.891+03:00 level=INFO source=runner.go:240 msg="Request info :\nPOST /completion HTTP/1.1\r\nHost: 127.0.0.1:32669\r\nAccept-Encoding: gzip\r\nContent-Length: 1313\r\nContent-Type: application/json\r\nUser-Agent: Go-http-client/1.1\r\n\r\n{"cache_prompt":true,"frequency_penalty":0,"image_data":null,"main_gpu":0,"max_new_token":2048,"min_p":0,"mirostat":0,"mirostat_eta":0.1,"mirostat_tau":5,"n_keep":4,"n_predict":-1,"presence_penalty":0,"prompt":"### Task:\nSuggest 3-5 relevant follow-up questions or prompts that the user might naturally ask next in this conversation as a user, based on the chat history, to help continue or deepen the discussion.\n### Guidelines:\n- Write all follow-up questions from the user’s point of view, directed to the assistant.\n- Make questions concise, clear, and directly related to the discussed topic(s).\n- Only suggest follow-ups that make sense given the chat content and do not repeat what was already covered.\n- If the conversation is very short or not specific, suggest more general (but relevant) follow-ups the user might ask.\n- Use the conversation's primary language; default to English if multilingual.\n- Response must be a JSON array of strings, no extra text or formatting.\n### Output:\nJSON format: { \"follow_ups\": [\"Question 1?\", \"Question 2?\", \"Question 3?\"] }\n### Chat History:\n<chat_history>\nUSER: hi.\nASSISTANT: \n</chat_history>","repeat_last_n":64,"repeat_penalty":1,"seed":-1,"stop":null,"stop_id":null,"stream":true,"temperature":1,"top_k":40,"top_p":1,"typical_p":1}"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:161 msg="Sampling Parameters - Temperature: 1.00, TopP: 1.00, TopK: 40, RepeatPenalty: 1.00"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:120 msg="Genai Metrics info:"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:124 msg="Load time: 0.00"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:129 msg="Generate time: 0.00 ± 0.00 ms"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:134 msg="Tokenization time: 0.00 ± 0.00 ms"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:139 msg="Detokenization time: 0.00 ± 0.00 ms"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:144 msg="TTFT: 0.00 ± 0.00 ms"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:149 msg="TPOT: 0.00 ± 0.00 ms/token"
time=2025-06-13T10:27:39.892+03:00 level=INFO source=genai.go:154 msg="Throughput: 0.00 ± 0.00 tokens/s"
[GIN] 2025/06/13 - 10:27:39 | 200 | 9.9998ms | 127.0.0.1 | POST "/api/chat"

[rsj123]

I met too

PS C:\Users\31092\Downloads\Compressed\openvino_genai_windows_2025.3.0.0.dev20250630_x86_64\openvino_genai_windows_2025.3.0.0.dev20250630_x86_64> set GODEBUG=cgocheck=0
PS C:\Users\31092\Downloads\Compressed\openvino_genai_windows_2025.3.0.0.dev20250630_x86_64\openvino_genai_windows_2025.3.0.0.dev20250630_x86_64> ./ollama_npu serve
2025/08/26 16:46:48 routes.go:1390: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-08-26T16:46:48.796+08:00 level=INFO source=images.go:447 msg="total blobs: 10"
time=2025-08-26T16:46:48.797+08:00 level=INFO source=images.go:454 msg="total unused blobs removed: 0"
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.

[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.

• using env: export GIN_MODE=release
• using code: gin.SetMode(gin.ReleaseMode)

[GIN-debug] POST /api/pull --> github.com/ollama/ollama/server.(*Server).PullHandler-fm (5 handlers)
[GIN-debug] POST /api/generate --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (5 handlers)
[GIN-debug] POST /api/chat --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (5 handlers)
[GIN-debug] POST /api/embed --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (5 handlers)
[GIN-debug] POST /api/embeddings --> github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers)
[GIN-debug] POST /api/create --> github.com/ollama/ollama/server.(*Server).CreateHandler-fm (5 handlers)
[GIN-debug] POST /api/push --> github.com/ollama/ollama/server.(*Server).PushHandler-fm (5 handlers)
[GIN-debug] POST /api/copy --> github.com/ollama/ollama/server.(*Server).CopyHandler-fm (5 handlers)
[GIN-debug] DELETE /api/delete --> github.com/ollama/ollama/server.(*Server).DeleteHandler-fm (5 handlers)
[GIN-debug] POST /api/show --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (5 handlers)
[GIN-debug] POST /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers)
[GIN-debug] HEAD /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers)
[GIN-debug] GET /api/ps --> github.com/ollama/ollama/server.(*Server).PsHandler-fm (5 handlers)
[GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
[GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
[GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers)
[GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers)
[GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers)
[GIN-debug] GET / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] GET /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] GET /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
[GIN-debug] HEAD / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] HEAD /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] HEAD /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
time=2025-08-26T16:46:48.800+08:00 level=INFO source=routes.go:1441 msg="Listening on 127.0.0.1:11434 (version 0.0.0)"
time=2025-08-26T16:46:48.800+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-26T16:46:48.800+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-08-26T16:46:48.800+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-08-26T16:46:48.800+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=16 efficiency=10 threads=22
time=2025-08-26T16:46:48.825+08:00 level=INFO source=gpu.go:636 msg="Unable to load NVML management library C:\WINDOWS\System32\nvml.dll: nvml vram init failure: 4"
time=2025-08-26T16:46:48.827+08:00 level=INFO source=gpu.go:636 msg="Unable to load NVML management library c:\Windows\System32\nvml.dll: nvml vram init failure: 4"
time=2025-08-26T16:46:48.851+08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library C:\WINDOWS\System32\nvcuda.dll"
time=2025-08-26T16:46:48.907+08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-08-26T16:46:48.907+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="31.6 GiB" available="4.8 GiB"
time=2025-08-26T16:46:49.387+08:00 level=INFO source=routes.go:1478 msg="GenAI inference device" Device=CPU "Build Number"=2025.3.0-19384-4100aa41368 description=openvino_intel_cpu_plugin
time=2025-08-26T16:46:49.387+08:00 level=INFO source=routes.go:1478 msg="GenAI inference device" Device=GPU "Build Number"=2025.3.0-19384-4100aa41368 description="Intel GPU plugin"
time=2025-08-26T16:46:49.387+08:00 level=INFO source=routes.go:1478 msg="GenAI inference device" Device=NPU "Build Number"=2025.3.0-19384-4100aa41368 description=openvino_intel_npu_plugin
[GIN] 2025/08/26 - 16:46:52 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/08/26 - 16:46:52 | 200 | 4.853ms | 127.0.0.1 | POST "/api/show"
time=2025-08-26T16:46:52.473+08:00 level=INFO source=sched.go:313 msg="loading first openvino model: Qwen3-0.6B-int4-ov:v1"
time=2025-08-26T16:46:52.473+08:00 level=INFO source=genaiserver.go:147 msg="system memory" total="31.6 GiB" free="4.6 GiB" free_swap="16.2 GiB"
time=2025-08-26T16:46:52.552+08:00 level=INFO source=genaiserver.go:270 msg="starting llama server" cmd="C:\Users\31092\Downloads\Compressed\openvino_genai_windows_2025.3.0.0.dev20250630_x86_64\openvino_genai_windows_2025.3.0.0.dev20250630_x86_64\ollama_npu.exe genairunner --model E:\ollama_models\blobs\sha256-cce3a284e123009c714300de3bd38125ca5d20fea6f350273087d940df290ae3 --modelname Qwen3-0.6B-int4-ov:v1 --device GPU --parallel 1 --port 3316"
time=2025-08-26T16:46:52.574+08:00 level=INFO source=sched.go:548 msg="loaded runners" count=1
time=2025-08-26T16:46:52.574+08:00 level=INFO source=genaiserver.go:389 msg="waiting for llama runner to start responding"
time=2025-08-26T16:46:52.575+08:00 level=INFO source=genaiserver.go:423 msg="waiting for server to become available" status="llm server error"
time=2025-08-26T16:46:52.683+08:00 level=INFO source=runner.go:473 msg="starting go genairunner"
time=2025-08-26T16:46:52.717+08:00 level=INFO source=runner.go:413 msg="The model is a OpenVINO IR file."
time=2025-08-26T16:46:52.718+08:00 level=INFO source=runner.go:505 msg="Server listening on 127.0.0.1:3316"
time=2025-08-26T16:46:52.828+08:00 level=INFO source=genaiserver.go:423 msg="waiting for server to become available" status="llm server loading model"
time=2025-08-26T16:47:03.018+08:00 level=INFO source=runner.go:435 msg="The model had been load by GenAI, ov_model_path: \tmp\Qwen3-0.6B-int4-ov_v1\Qwen3-0.6B-int4-ov , GPU"
time=2025-08-26T16:47:03.115+08:00 level=INFO source=genaiserver.go:428 msg="llama runner started in 10.54 seconds"
[GIN] 2025/08/26 - 16:47:03 | 200 | 10.6485102s | 127.0.0.1 | POST "/api/generate"
time=2025-08-26T16:47:05.531+08:00 level=INFO source=runner.go:240 msg="Request info :\nPOST /completion HTTP/1.1\r\nHost: 127.0.0.1:3316\r\nAccept-Encoding: gzip\r\nContent-Length: 360\r\nContent-Type: application/json\r\nUser-Agent: Go-http-client/1.1\r\n\r\n{"cache_prompt":true,"frequency_penalty":0,"image_data":null,"main_gpu":0,"max_new_token":2048,"min_p":0,"mirostat":0,"mirostat_eta":0.1,"mirostat_tau":5,"n_keep":4,"n_predict":-1,"presence_penalty":0,"prompt":"hi","repeat_last_n":64,"repeat_penalty":1,"seed":-1,"stop":null,"stop_id":null,"stream":true,"temperature":0.7,"top_k":40,"top_p":0.8,"typical_p":1}"
time=2025-08-26T16:47:05.531+08:00 level=INFO source=genai.go:253 msg="Sampling Parameters - Temperature: 0.70, TopP: 0.80, TopK: 40, RepeatPenalty: 1.00"
panic: runtime error: cgo argument has Go pointer to unpinned Go pointer

goroutine 16 [running]:
github.com/ollama/ollama/genai.GenerateTextWithMetrics.func3(...)
C:/hongbo/test/openvino_contrib/modules/ollama_openvino/genai/genai.go:313
github.com/ollama/ollama/genai.GenerateTextWithMetrics(0x1e557f4df20, {0xc00046a58c?, 0x7ff7cc295820?}, 0xc000108ae0, 0xc0005b6b60)
C:/hongbo/test/openvino_contrib/modules/ollama_openvino/genai/genai.go:313 +0x1d2
github.com/ollama/ollama/genai/runner.(*Server).processBatch(0xc000306ee0)
C:/hongbo/test/openvino_contrib/modules/ollama_openvino/genai/runner/runner.go:150 +0x1eb
github.com/ollama/ollama/genai/runner.(*Server).run(0xc000306ee0, {0x7ff7cb9ef9d0, 0xc000135cc0})
C:/hongbo/test/openvino_contrib/modules/ollama_openvino/genai/runner/runner.go:230 +0x31
created by github.com/ollama/ollama/genai/runner.Execute in goroutine 1
C:/hongbo/test/openvino_contrib/modules/ollama_openvino/genai/runner/runner.go:486 +0x6eb
[GIN] 2025/08/26 - 16:47:05 | 200 | 179.7286ms | 127.0.0.1 | POST "/api/chat"
time=2025-08-26T16:47:05.730+08:00 level=ERROR source=genaiserver.go:286 msg="llama runner terminated" error="exit status 2"

[zhaohb]

Regarding Go pointer to unpinned Go pointer issue, pls set GODEBUG=cgocheck=0, and will fix that issue.

First, set GODEBUG=cgocheck=0 env:

Linux
export GODEBUG=cgocheck=0
Windows
set GODEBUG=cgocheck=0