github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 21:51:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9349] ollama run org/deepseek-r1-uncensored : Error: Post "http://127.0.0.1:11434/api/generate": EOF #52616

New Issue
Closed
opened 2026-04-28 23:52:43 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 23:52:43 -05:00
Owner
Copy Link

Originally created by @aloeppert on GitHub (Feb 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9349

What is the issue?

I tried:
ollama run org/deepseek-r1-uncensored

The pieces were downloaded and verified, then I get

Error: Post "http://127.0.0.1:11434/api/generate": EOF

Relevant log output

Feb 25 11:01:08 mega ollama[744153]: [GIN] 2025/02/25 - 11:01:08 | 200 |      87.412µs |       127.0.0.1 | HEAD     "/"
Feb 25 11:01:08 mega ollama[744153]: [GIN] 2025/02/25 - 11:01:08 | 200 |     106.083µs |       127.0.0.1 | GET      "/api/ps"
Feb 25 11:08:05 mega ollama[744153]: [GIN] 2025/02/25 - 11:08:05 | 200 |       1h3m30s |       127.0.0.1 | POST     "/api/chat"
Feb 25 11:15:43 mega ollama[744153]: [GIN] 2025/02/25 - 11:15:43 | 200 |      32.341µs |       127.0.0.1 | HEAD     "/"
Feb 25 11:15:43 mega ollama[744153]: [GIN] 2025/02/25 - 11:15:43 | 200 |      23.539µs |       127.0.0.1 | GET      "/api/ps"
Feb 25 11:15:46 mega ollama[744153]: [GIN] 2025/02/25 - 11:15:46 | 200 |      32.908µs |       127.0.0.1 | HEAD     "/"
Feb 25 11:15:46 mega ollama[744153]: [GIN] 2025/02/25 - 11:15:46 | 404 |    1.030807ms |       127.0.0.1 | POST     "/api/show"
Feb 25 11:15:47 mega ollama[744153]: time=2025-02-25T11:15:47.016-08:00 level=INFO source=download.go:176 msg="downloading 40f39b91ba93 in 46 1 GB part(s)"
Feb 25 11:22:30 mega ollama[744153]: time=2025-02-25T11:22:30.578-08:00 level=INFO source=download.go:176 msg="downloading a030c70657da in 47 1 GB part(s)"
Feb 25 11:32:12 mega ollama[744153]: time=2025-02-25T11:32:12.132-08:00 level=INFO source=download.go:176 msg="downloading 65481175e980 in 47 1 GB part(s)"
Feb 25 11:38:58 mega ollama[744153]: time=2025-02-25T11:38:58.618-08:00 level=INFO source=download.go:176 msg="downloading 892b9e7a8201 in 47 1 GB part(s)"
Feb 25 11:44:51 mega ollama[744153]: time=2025-02-25T11:44:51.749-08:00 level=INFO source=download.go:294 msg="892b9e7a8201 part 25 attempt 0 failed: unexpected EOF, retrying in 1s"
Feb 25 11:44:59 mega ollama[744153]: time=2025-02-25T11:44:59.289-08:00 level=INFO source=download.go:294 msg="892b9e7a8201 part 40 attempt 0 failed: unexpected EOF, retrying in 1s"
Feb 25 11:45:46 mega ollama[744153]: time=2025-02-25T11:45:46.057-08:00 level=INFO source=download.go:176 msg="downloading dff704a88236 in 43 1 GB part(s)"
Feb 25 11:52:02 mega ollama[744153]: time=2025-02-25T11:52:02.564-08:00 level=INFO source=download.go:176 msg="downloading 6b62346ff5a3 in 1 389 B part(s)"
Feb 25 11:52:03 mega ollama[744153]: time=2025-02-25T11:52:03.928-08:00 level=INFO source=download.go:176 msg="downloading cf8250e9cc6d in 1 166 B part(s)"
Feb 25 11:52:05 mega ollama[744153]: time=2025-02-25T11:52:05.248-08:00 level=INFO source=download.go:176 msg="downloading 9de92bff51e0 in 1 757 B part(s)"
Feb 25 11:59:37 mega ollama[744153]: [GIN] 2025/02/25 - 11:59:37 | 200 |        43m51s |       127.0.0.1 | POST     "/api/pull"
Feb 25 11:59:37 mega ollama[744153]: [GIN] 2025/02/25 - 11:59:37 | 200 |    1.069336ms |       127.0.0.1 | POST     "/api/show"
Feb 25 11:59:37 mega ollama[744153]: time=2025-02-25T11:59:37.625-08:00 level=INFO source=server.go:100 msg="system memory" total="251.4 GiB" free="246.5 GiB" free_swap="0 B"
Feb 25 11:59:37 mega ollama[744153]: time=2025-02-25T11:59:37.625-08:00 level=WARN source=memory.go:123 msg="model missing blk.0 layer size"
Feb 25 11:59:37 mega ollama[744153]: panic: interface conversion: interface {} is nil, not *llm.array
Feb 25 11:59:37 mega ollama[744153]: goroutine 68 [running]:
Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm.GGML.GraphSize({{0x65273db81120?, 0xc00052e640?}, {0x65273db810a8?, 0xc0006a6808?}}, 0x2000, 0x200, {0x0, 0x0})
Feb 25 11:59:37 mega ollama[744153]:         github.com/ollama/ollama/llm/ggml.go:367 +0x10bf
Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...})
Feb 25 11:59:37 mega ollama[744153]:         github.com/ollama/ollama/llm/memory.go:138 +0x5fa
Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm.NewLlamaServer({0xc000000240, 0x1, 0x1}, {0xc000661500, _}, _, {_, _, _}, {0x0, ...}, ...)
Feb 25 11:59:37 mega ollama[744153]:         github.com/ollama/ollama/llm/server.go:107 +0x2c5
Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server.(*Scheduler).load(0xc000250ae0, 0xc00071e000, 0xc0002de9a0, {0xc000000240, 0x1, 0x1}, 0x4)
Feb 25 11:59:37 mega ollama[744153]:         github.com/ollama/ollama/server/sched.go:420 +0x1c4
Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server.(*Scheduler).processPending(0xc000250ae0, {0x65273db84f40, 0xc0003f65a0})
Feb 25 11:59:37 mega ollama[744153]:         github.com/ollama/ollama/server/sched.go:212 +0xbce
Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server.(*Scheduler).Run.func1()
Feb 25 11:59:37 mega ollama[744153]:         github.com/ollama/ollama/server/sched.go:107 +0x1f
Feb 25 11:59:37 mega ollama[744153]: created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
Feb 25 11:59:37 mega ollama[744153]:         github.com/ollama/ollama/server/sched.go:106 +0xb4
Feb 25 11:59:37 mega systemd[1]: ollama.service: Main process exited, code=exited, status=2/INVALIDARGUMENT
Feb 25 11:59:37 mega systemd[1]: ollama.service: Failed with result 'exit-code'.
Feb 25 11:59:37 mega systemd[1]: ollama.service: Consumed 2d 12h 43min 18.400s CPU time.
Feb 25 11:59:40 mega systemd[1]: ollama.service: Scheduled restart job, restart counter is at 1.
Feb 25 11:59:40 mega systemd[1]: Stopped Ollama Service.
Feb 25 11:59:40 mega systemd[1]: ollama.service: Consumed 2d 12h 43min 18.400s CPU time.
Feb 25 11:59:40 mega systemd[1]: Started Ollama Service.
Feb 25 11:59:40 mega ollama[889670]: 2025/02/25 11:59:40 routes.go:1186: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE: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: http_proxy: https_proxy: no_proxy:]"
Feb 25 11:59:40 mega ollama[889670]: time=2025-02-25T11:59:40.820-08:00 level=INFO source=images.go:432 msg="total blobs: 30"
Feb 25 11:59:40 mega ollama[889670]: time=2025-02-25T11:59:40.821-08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
Feb 25 11:59:40 mega ollama[889670]: time=2025-02-25T11:59:40.829-08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)"
Feb 25 11:59:40 mega ollama[889670]: time=2025-02-25T11:59:40.830-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Feb 25 11:59:43 mega ollama[889670]: time=2025-02-25T11:59:43.534-08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15"
Feb 25 11:59:48 mega ollama[889670]: time=2025-02-25T11:59:48.873-08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
Feb 25 11:59:48 mega ollama[889670]: time=2025-02-25T11:59:48.873-08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="251.4 GiB" available="246.9 GiB"
Feb 25 12:02:23 mega ollama[889670]: [GIN] 2025/02/25 - 12:02:23 | 200 |      87.166µs |       127.0.0.1 | HEAD     "/"
Feb 25 12:02:23 mega ollama[889670]: [GIN] 2025/02/25 - 12:02:23 | 200 |    1.496019ms |       127.0.0.1 | POST     "/api/show"
Feb 25 12:02:23 mega ollama[889670]: time=2025-02-25T12:02:23.615-08:00 level=INFO source=server.go:100 msg="system memory" total="251.4 GiB" free="246.2 GiB" free_swap="0 B"
Feb 25 12:02:23 mega ollama[889670]: time=2025-02-25T12:02:23.615-08:00 level=WARN source=memory.go:123 msg="model missing blk.0 layer size"
Feb 25 12:02:23 mega ollama[889670]: panic: interface conversion: interface {} is nil, not *llm.array
Feb 25 12:02:23 mega ollama[889670]: goroutine 67 [running]:
Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm.GGML.GraphSize({{0x64facefb0120?, 0xc00046c370?}, {0x64facefb00a8?, 0xc0004a4808?}}, 0x2000, 0x200, {0x0, 0x0})
Feb 25 12:02:23 mega ollama[889670]:         github.com/ollama/ollama/llm/ggml.go:367 +0x10bf
Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...})
Feb 25 12:02:23 mega ollama[889670]:         github.com/ollama/ollama/llm/memory.go:138 +0x5fa
Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm.NewLlamaServer({0xc0000200c0, 0x1, 0x1}, {0xc0003ec1c0, _}, _, {_, _, _}, {0x0, ...}, ...)
Feb 25 12:02:23 mega ollama[889670]:         github.com/ollama/ollama/llm/server.go:107 +0x2c5
Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server.(*Scheduler).load(0xc0000dad80, 0xc000696000, 0xc000301820, {0xc0000200c0, 0x1, 0x1}, 0x4)
Feb 25 12:02:23 mega ollama[889670]:         github.com/ollama/ollama/server/sched.go:420 +0x1c4
Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server.(*Scheduler).processPending(0xc0000dad80, {0x64facefb3f40, 0xc00051c050})
Feb 25 12:02:23 mega ollama[889670]:         github.com/ollama/ollama/server/sched.go:212 +0xbce
Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server.(*Scheduler).Run.func1()
Feb 25 12:02:23 mega ollama[889670]:         github.com/ollama/ollama/server/sched.go:107 +0x1f
Feb 25 12:02:23 mega ollama[889670]: created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
Feb 25 12:02:23 mega ollama[889670]:         github.com/ollama/ollama/server/sched.go:106 +0xb4
Feb 25 12:02:23 mega systemd[1]: ollama.service: Main process exited, code=exited, status=2/INVALIDARGUMENT
Feb 25 12:02:23 mega systemd[1]: ollama.service: Failed with result 'exit-code'.
Feb 25 12:02:23 mega systemd[1]: ollama.service: Consumed 8.042s CPU time.
Feb 25 12:02:26 mega systemd[1]: ollama.service: Scheduled restart job, restart counter is at 2.
Feb 25 12:02:26 mega systemd[1]: Stopped Ollama Service.
Feb 25 12:02:26 mega systemd[1]: ollama.service: Consumed 8.042s CPU time.
Feb 25 12:02:26 mega systemd[1]: Started Ollama Service.
Feb 25 12:02:26 mega ollama[889751]: 2025/02/25 12:02:26 routes.go:1186: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE: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: http_proxy: https_proxy: no_proxy:]"
Feb 25 12:02:26 mega ollama[889751]: time=2025-02-25T12:02:26.820-08:00 level=INFO source=images.go:432 msg="total blobs: 30"
Feb 25 12:02:26 mega ollama[889751]: time=2025-02-25T12:02:26.820-08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
Feb 25 12:02:26 mega ollama[889751]: time=2025-02-25T12:02:26.821-08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)"
Feb 25 12:02:26 mega ollama[889751]: time=2025-02-25T12:02:26.821-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Feb 25 12:02:29 mega ollama[889751]: time=2025-02-25T12:02:29.474-08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15"
Feb 25 12:02:34 mega ollama[889751]: time=2025-02-25T12:02:34.868-08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
Feb 25 12:02:34 mega ollama[889751]: time=2025-02-25T12:02:34.868-08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="251.4 GiB" available="246.3 GiB"
Feb 25 12:07:40 mega systemd[1]: Stopping Ollama Service...
Feb 25 12:07:40 mega systemd[1]: ollama.service: Deactivated successfully.
Feb 25 12:07:40 mega systemd[1]: Stopped Ollama Service.
Feb 25 12:07:40 mega systemd[1]: ollama.service: Consumed 8.087s CPU time.
-- Boot d1ee1e1bb9d940a182d963f410aaf72b --
Feb 25 12:10:40 mega systemd[1]: Started Ollama Service.
Feb 25 12:10:40 mega ollama[1189]: 2025/02/25 12:10:40 routes.go:1186: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE: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: http_proxy: https_proxy: no_proxy:]"
Feb 25 12:10:40 mega ollama[1189]: time=2025-02-25T12:10:40.540-08:00 level=INFO source=images.go:432 msg="total blobs: 30"
Feb 25 12:10:40 mega ollama[1189]: time=2025-02-25T12:10:40.541-08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
Feb 25 12:10:40 mega ollama[1189]: time=2025-02-25T12:10:40.542-08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)"
Feb 25 12:10:40 mega ollama[1189]: time=2025-02-25T12:10:40.543-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Feb 25 12:10:43 mega ollama[1189]: time=2025-02-25T12:10:43.435-08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15"
Feb 25 12:10:49 mega ollama[1189]: time=2025-02-25T12:10:49.248-08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
Feb 25 12:10:49 mega ollama[1189]: time=2025-02-25T12:10:49.248-08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="251.4 GiB" available="248.8 GiB"
Feb 25 12:13:46 mega ollama[1189]: [GIN] 2025/02/25 - 12:13:46 | 200 |     238.544µs |       127.0.0.1 | HEAD     "/"
Feb 25 12:13:46 mega ollama[1189]: [GIN] 2025/02/25 - 12:13:46 | 200 |    2.736597ms |       127.0.0.1 | POST     "/api/show"
Feb 25 12:13:46 mega ollama[1189]: time=2025-02-25T12:13:46.052-08:00 level=INFO source=server.go:100 msg="system memory" total="251.4 GiB" free="248.5 GiB" free_swap="0 B"
Feb 25 12:13:46 mega ollama[1189]: time=2025-02-25T12:13:46.052-08:00 level=WARN source=memory.go:123 msg="model missing blk.0 layer size"
Feb 25 12:13:46 mega ollama[1189]: panic: interface conversion: interface {} is nil, not *llm.array
Feb 25 12:13:46 mega ollama[1189]: goroutine 61 [running]:
Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm.GGML.GraphSize({{0x5b7256533120?, 0xc00034a370?}, {0x5b72565330a8?, 0xc000454808?}}, 0x2000, 0x200, {0x0, 0x0})
Feb 25 12:13:46 mega ollama[1189]:         github.com/ollama/ollama/llm/ggml.go:367 +0x10bf
Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...})
Feb 25 12:13:46 mega ollama[1189]:         github.com/ollama/ollama/llm/memory.go:138 +0x5fa
Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm.NewLlamaServer({0xc00021a0c0, 0x1, 0x1}, {0xc0005b5420, _}, _, {_, _, _}, {0x0, ...}, ...)
Feb 25 12:13:46 mega ollama[1189]:         github.com/ollama/ollama/llm/server.go:107 +0x2c5
Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server.(*Scheduler).load(0xc0000f5740, 0xc000016000, 0xc00012f100, {0xc00021a0c0, 0x1, 0x1}, 0x4)
Feb 25 12:13:46 mega ollama[1189]:         github.com/ollama/ollama/server/sched.go:420 +0x1c4
Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server.(*Scheduler).processPending(0xc0000f5740, {0x5b7256536f40, 0xc0004447d0})
Feb 25 12:13:46 mega ollama[1189]:         github.com/ollama/ollama/server/sched.go:212 +0xbce
Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server.(*Scheduler).Run.func1()
Feb 25 12:13:46 mega ollama[1189]:         github.com/ollama/ollama/server/sched.go:107 +0x1f
Feb 25 12:13:46 mega ollama[1189]: created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
Feb 25 12:13:46 mega ollama[1189]:         github.com/ollama/ollama/server/sched.go:106 +0xb4
Feb 25 12:13:46 mega systemd[1]: ollama.service: Main process exited, code=exited, status=2/INVALIDARGUMENT
Feb 25 12:13:46 mega systemd[1]: ollama.service: Failed with result 'exit-code'.
Feb 25 12:13:46 mega systemd[1]: ollama.service: Consumed 8.707s CPU time.
Feb 25 12:13:49 mega systemd[1]: ollama.service: Scheduled restart job, restart counter is at 1.
Feb 25 12:13:49 mega systemd[1]: Stopped Ollama Service.
Feb 25 12:13:49 mega systemd[1]: ollama.service: Consumed 8.707s CPU time.
Feb 25 12:13:49 mega systemd[1]: Started Ollama Service.
Feb 25 12:13:49 mega ollama[1898]: 2025/02/25 12:13:49 routes.go:1186: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE: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: http_proxy: https_proxy: no_proxy:]"
Feb 25 12:13:49 mega ollama[1898]: time=2025-02-25T12:13:49.133-08:00 level=INFO source=images.go:432 msg="total blobs: 30"
Feb 25 12:13:49 mega ollama[1898]: time=2025-02-25T12:13:49.133-08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
Feb 25 12:13:49 mega ollama[1898]: time=2025-02-25T12:13:49.134-08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)"
Feb 25 12:13:49 mega ollama[1898]: time=2025-02-25T12:13:49.134-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Feb 25 12:13:51 mega ollama[1898]: time=2025-02-25T12:13:51.691-08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15"
Feb 25 12:13:56 mega ollama[1898]: time=2025-02-25T12:13:56.755-08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
Feb 25 12:13:56 mega ollama[1898]: time=2025-02-25T12:13:56.755-08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="251.4 GiB" available="248.5 GiB"

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.5.11

Originally created by @aloeppert on GitHub (Feb 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9349 ### What is the issue? I tried: ollama run org/deepseek-r1-uncensored The pieces were downloaded and verified, then I get Error: Post "http://127.0.0.1:11434/api/generate": EOF ### Relevant log output ```shell Feb 25 11:01:08 mega ollama[744153]: [GIN] 2025/02/25 - 11:01:08 | 200 | 87.412µs | 127.0.0.1 | HEAD "/" Feb 25 11:01:08 mega ollama[744153]: [GIN] 2025/02/25 - 11:01:08 | 200 | 106.083µs | 127.0.0.1 | GET "/api/ps" Feb 25 11:08:05 mega ollama[744153]: [GIN] 2025/02/25 - 11:08:05 | 200 | 1h3m30s | 127.0.0.1 | POST "/api/chat" Feb 25 11:15:43 mega ollama[744153]: [GIN] 2025/02/25 - 11:15:43 | 200 | 32.341µs | 127.0.0.1 | HEAD "/" Feb 25 11:15:43 mega ollama[744153]: [GIN] 2025/02/25 - 11:15:43 | 200 | 23.539µs | 127.0.0.1 | GET "/api/ps" Feb 25 11:15:46 mega ollama[744153]: [GIN] 2025/02/25 - 11:15:46 | 200 | 32.908µs | 127.0.0.1 | HEAD "/" Feb 25 11:15:46 mega ollama[744153]: [GIN] 2025/02/25 - 11:15:46 | 404 | 1.030807ms | 127.0.0.1 | POST "/api/show" Feb 25 11:15:47 mega ollama[744153]: time=2025-02-25T11:15:47.016-08:00 level=INFO source=download.go:176 msg="downloading 40f39b91ba93 in 46 1 GB part(s)" Feb 25 11:22:30 mega ollama[744153]: time=2025-02-25T11:22:30.578-08:00 level=INFO source=download.go:176 msg="downloading a030c70657da in 47 1 GB part(s)" Feb 25 11:32:12 mega ollama[744153]: time=2025-02-25T11:32:12.132-08:00 level=INFO source=download.go:176 msg="downloading 65481175e980 in 47 1 GB part(s)" Feb 25 11:38:58 mega ollama[744153]: time=2025-02-25T11:38:58.618-08:00 level=INFO source=download.go:176 msg="downloading 892b9e7a8201 in 47 1 GB part(s)" Feb 25 11:44:51 mega ollama[744153]: time=2025-02-25T11:44:51.749-08:00 level=INFO source=download.go:294 msg="892b9e7a8201 part 25 attempt 0 failed: unexpected EOF, retrying in 1s" Feb 25 11:44:59 mega ollama[744153]: time=2025-02-25T11:44:59.289-08:00 level=INFO source=download.go:294 msg="892b9e7a8201 part 40 attempt 0 failed: unexpected EOF, retrying in 1s" Feb 25 11:45:46 mega ollama[744153]: time=2025-02-25T11:45:46.057-08:00 level=INFO source=download.go:176 msg="downloading dff704a88236 in 43 1 GB part(s)" Feb 25 11:52:02 mega ollama[744153]: time=2025-02-25T11:52:02.564-08:00 level=INFO source=download.go:176 msg="downloading 6b62346ff5a3 in 1 389 B part(s)" Feb 25 11:52:03 mega ollama[744153]: time=2025-02-25T11:52:03.928-08:00 level=INFO source=download.go:176 msg="downloading cf8250e9cc6d in 1 166 B part(s)" Feb 25 11:52:05 mega ollama[744153]: time=2025-02-25T11:52:05.248-08:00 level=INFO source=download.go:176 msg="downloading 9de92bff51e0 in 1 757 B part(s)" Feb 25 11:59:37 mega ollama[744153]: [GIN] 2025/02/25 - 11:59:37 | 200 | 43m51s | 127.0.0.1 | POST "/api/pull" Feb 25 11:59:37 mega ollama[744153]: [GIN] 2025/02/25 - 11:59:37 | 200 | 1.069336ms | 127.0.0.1 | POST "/api/show" Feb 25 11:59:37 mega ollama[744153]: time=2025-02-25T11:59:37.625-08:00 level=INFO source=server.go:100 msg="system memory" total="251.4 GiB" free="246.5 GiB" free_swap="0 B" Feb 25 11:59:37 mega ollama[744153]: time=2025-02-25T11:59:37.625-08:00 level=WARN source=memory.go:123 msg="model missing blk.0 layer size" Feb 25 11:59:37 mega ollama[744153]: panic: interface conversion: interface {} is nil, not *llm.array Feb 25 11:59:37 mega ollama[744153]: goroutine 68 [running]: Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm.GGML.GraphSize({{0x65273db81120?, 0xc00052e640?}, {0x65273db810a8?, 0xc0006a6808?}}, 0x2000, 0x200, {0x0, 0x0}) Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm/ggml.go:367 +0x10bf Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...}) Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm/memory.go:138 +0x5fa Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm.NewLlamaServer({0xc000000240, 0x1, 0x1}, {0xc000661500, _}, _, {_, _, _}, {0x0, ...}, ...) Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/llm/server.go:107 +0x2c5 Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server.(*Scheduler).load(0xc000250ae0, 0xc00071e000, 0xc0002de9a0, {0xc000000240, 0x1, 0x1}, 0x4) Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server/sched.go:420 +0x1c4 Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server.(*Scheduler).processPending(0xc000250ae0, {0x65273db84f40, 0xc0003f65a0}) Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server/sched.go:212 +0xbce Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server.(*Scheduler).Run.func1() Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server/sched.go:107 +0x1f Feb 25 11:59:37 mega ollama[744153]: created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 Feb 25 11:59:37 mega ollama[744153]: github.com/ollama/ollama/server/sched.go:106 +0xb4 Feb 25 11:59:37 mega systemd[1]: ollama.service: Main process exited, code=exited, status=2/INVALIDARGUMENT Feb 25 11:59:37 mega systemd[1]: ollama.service: Failed with result 'exit-code'. Feb 25 11:59:37 mega systemd[1]: ollama.service: Consumed 2d 12h 43min 18.400s CPU time. Feb 25 11:59:40 mega systemd[1]: ollama.service: Scheduled restart job, restart counter is at 1. Feb 25 11:59:40 mega systemd[1]: Stopped Ollama Service. Feb 25 11:59:40 mega systemd[1]: ollama.service: Consumed 2d 12h 43min 18.400s CPU time. Feb 25 11:59:40 mega systemd[1]: Started Ollama Service. Feb 25 11:59:40 mega ollama[889670]: 2025/02/25 11:59:40 routes.go:1186: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE: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: http_proxy: https_proxy: no_proxy:]" Feb 25 11:59:40 mega ollama[889670]: time=2025-02-25T11:59:40.820-08:00 level=INFO source=images.go:432 msg="total blobs: 30" Feb 25 11:59:40 mega ollama[889670]: time=2025-02-25T11:59:40.821-08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" Feb 25 11:59:40 mega ollama[889670]: time=2025-02-25T11:59:40.829-08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)" Feb 25 11:59:40 mega ollama[889670]: time=2025-02-25T11:59:40.830-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Feb 25 11:59:43 mega ollama[889670]: time=2025-02-25T11:59:43.534-08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15" Feb 25 11:59:48 mega ollama[889670]: time=2025-02-25T11:59:48.873-08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" Feb 25 11:59:48 mega ollama[889670]: time=2025-02-25T11:59:48.873-08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="251.4 GiB" available="246.9 GiB" Feb 25 12:02:23 mega ollama[889670]: [GIN] 2025/02/25 - 12:02:23 | 200 | 87.166µs | 127.0.0.1 | HEAD "/" Feb 25 12:02:23 mega ollama[889670]: [GIN] 2025/02/25 - 12:02:23 | 200 | 1.496019ms | 127.0.0.1 | POST "/api/show" Feb 25 12:02:23 mega ollama[889670]: time=2025-02-25T12:02:23.615-08:00 level=INFO source=server.go:100 msg="system memory" total="251.4 GiB" free="246.2 GiB" free_swap="0 B" Feb 25 12:02:23 mega ollama[889670]: time=2025-02-25T12:02:23.615-08:00 level=WARN source=memory.go:123 msg="model missing blk.0 layer size" Feb 25 12:02:23 mega ollama[889670]: panic: interface conversion: interface {} is nil, not *llm.array Feb 25 12:02:23 mega ollama[889670]: goroutine 67 [running]: Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm.GGML.GraphSize({{0x64facefb0120?, 0xc00046c370?}, {0x64facefb00a8?, 0xc0004a4808?}}, 0x2000, 0x200, {0x0, 0x0}) Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm/ggml.go:367 +0x10bf Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...}) Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm/memory.go:138 +0x5fa Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm.NewLlamaServer({0xc0000200c0, 0x1, 0x1}, {0xc0003ec1c0, _}, _, {_, _, _}, {0x0, ...}, ...) Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/llm/server.go:107 +0x2c5 Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server.(*Scheduler).load(0xc0000dad80, 0xc000696000, 0xc000301820, {0xc0000200c0, 0x1, 0x1}, 0x4) Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server/sched.go:420 +0x1c4 Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server.(*Scheduler).processPending(0xc0000dad80, {0x64facefb3f40, 0xc00051c050}) Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server/sched.go:212 +0xbce Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server.(*Scheduler).Run.func1() Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server/sched.go:107 +0x1f Feb 25 12:02:23 mega ollama[889670]: created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 Feb 25 12:02:23 mega ollama[889670]: github.com/ollama/ollama/server/sched.go:106 +0xb4 Feb 25 12:02:23 mega systemd[1]: ollama.service: Main process exited, code=exited, status=2/INVALIDARGUMENT Feb 25 12:02:23 mega systemd[1]: ollama.service: Failed with result 'exit-code'. Feb 25 12:02:23 mega systemd[1]: ollama.service: Consumed 8.042s CPU time. Feb 25 12:02:26 mega systemd[1]: ollama.service: Scheduled restart job, restart counter is at 2. Feb 25 12:02:26 mega systemd[1]: Stopped Ollama Service. Feb 25 12:02:26 mega systemd[1]: ollama.service: Consumed 8.042s CPU time. Feb 25 12:02:26 mega systemd[1]: Started Ollama Service. Feb 25 12:02:26 mega ollama[889751]: 2025/02/25 12:02:26 routes.go:1186: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE: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: http_proxy: https_proxy: no_proxy:]" Feb 25 12:02:26 mega ollama[889751]: time=2025-02-25T12:02:26.820-08:00 level=INFO source=images.go:432 msg="total blobs: 30" Feb 25 12:02:26 mega ollama[889751]: time=2025-02-25T12:02:26.820-08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" Feb 25 12:02:26 mega ollama[889751]: time=2025-02-25T12:02:26.821-08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)" Feb 25 12:02:26 mega ollama[889751]: time=2025-02-25T12:02:26.821-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Feb 25 12:02:29 mega ollama[889751]: time=2025-02-25T12:02:29.474-08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15" Feb 25 12:02:34 mega ollama[889751]: time=2025-02-25T12:02:34.868-08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" Feb 25 12:02:34 mega ollama[889751]: time=2025-02-25T12:02:34.868-08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="251.4 GiB" available="246.3 GiB" Feb 25 12:07:40 mega systemd[1]: Stopping Ollama Service... Feb 25 12:07:40 mega systemd[1]: ollama.service: Deactivated successfully. Feb 25 12:07:40 mega systemd[1]: Stopped Ollama Service. Feb 25 12:07:40 mega systemd[1]: ollama.service: Consumed 8.087s CPU time. -- Boot d1ee1e1bb9d940a182d963f410aaf72b -- Feb 25 12:10:40 mega systemd[1]: Started Ollama Service. Feb 25 12:10:40 mega ollama[1189]: 2025/02/25 12:10:40 routes.go:1186: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE: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: http_proxy: https_proxy: no_proxy:]" Feb 25 12:10:40 mega ollama[1189]: time=2025-02-25T12:10:40.540-08:00 level=INFO source=images.go:432 msg="total blobs: 30" Feb 25 12:10:40 mega ollama[1189]: time=2025-02-25T12:10:40.541-08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" Feb 25 12:10:40 mega ollama[1189]: time=2025-02-25T12:10:40.542-08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)" Feb 25 12:10:40 mega ollama[1189]: time=2025-02-25T12:10:40.543-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Feb 25 12:10:43 mega ollama[1189]: time=2025-02-25T12:10:43.435-08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15" Feb 25 12:10:49 mega ollama[1189]: time=2025-02-25T12:10:49.248-08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" Feb 25 12:10:49 mega ollama[1189]: time=2025-02-25T12:10:49.248-08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="251.4 GiB" available="248.8 GiB" Feb 25 12:13:46 mega ollama[1189]: [GIN] 2025/02/25 - 12:13:46 | 200 | 238.544µs | 127.0.0.1 | HEAD "/" Feb 25 12:13:46 mega ollama[1189]: [GIN] 2025/02/25 - 12:13:46 | 200 | 2.736597ms | 127.0.0.1 | POST "/api/show" Feb 25 12:13:46 mega ollama[1189]: time=2025-02-25T12:13:46.052-08:00 level=INFO source=server.go:100 msg="system memory" total="251.4 GiB" free="248.5 GiB" free_swap="0 B" Feb 25 12:13:46 mega ollama[1189]: time=2025-02-25T12:13:46.052-08:00 level=WARN source=memory.go:123 msg="model missing blk.0 layer size" Feb 25 12:13:46 mega ollama[1189]: panic: interface conversion: interface {} is nil, not *llm.array Feb 25 12:13:46 mega ollama[1189]: goroutine 61 [running]: Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm.GGML.GraphSize({{0x5b7256533120?, 0xc00034a370?}, {0x5b72565330a8?, 0xc000454808?}}, 0x2000, 0x200, {0x0, 0x0}) Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm/ggml.go:367 +0x10bf Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, _, {_, _, _}, {{0x2000, 0x200, 0xffffffffffffffff, ...}, ...}) Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm/memory.go:138 +0x5fa Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm.NewLlamaServer({0xc00021a0c0, 0x1, 0x1}, {0xc0005b5420, _}, _, {_, _, _}, {0x0, ...}, ...) Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/llm/server.go:107 +0x2c5 Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server.(*Scheduler).load(0xc0000f5740, 0xc000016000, 0xc00012f100, {0xc00021a0c0, 0x1, 0x1}, 0x4) Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server/sched.go:420 +0x1c4 Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server.(*Scheduler).processPending(0xc0000f5740, {0x5b7256536f40, 0xc0004447d0}) Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server/sched.go:212 +0xbce Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server.(*Scheduler).Run.func1() Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server/sched.go:107 +0x1f Feb 25 12:13:46 mega ollama[1189]: created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 Feb 25 12:13:46 mega ollama[1189]: github.com/ollama/ollama/server/sched.go:106 +0xb4 Feb 25 12:13:46 mega systemd[1]: ollama.service: Main process exited, code=exited, status=2/INVALIDARGUMENT Feb 25 12:13:46 mega systemd[1]: ollama.service: Failed with result 'exit-code'. Feb 25 12:13:46 mega systemd[1]: ollama.service: Consumed 8.707s CPU time. Feb 25 12:13:49 mega systemd[1]: ollama.service: Scheduled restart job, restart counter is at 1. Feb 25 12:13:49 mega systemd[1]: Stopped Ollama Service. Feb 25 12:13:49 mega systemd[1]: ollama.service: Consumed 8.707s CPU time. Feb 25 12:13:49 mega systemd[1]: Started Ollama Service. Feb 25 12:13:49 mega ollama[1898]: 2025/02/25 12:13:49 routes.go:1186: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE: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: http_proxy: https_proxy: no_proxy:]" Feb 25 12:13:49 mega ollama[1898]: time=2025-02-25T12:13:49.133-08:00 level=INFO source=images.go:432 msg="total blobs: 30" Feb 25 12:13:49 mega ollama[1898]: time=2025-02-25T12:13:49.133-08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" Feb 25 12:13:49 mega ollama[1898]: time=2025-02-25T12:13:49.134-08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.11)" Feb 25 12:13:49 mega ollama[1898]: time=2025-02-25T12:13:49.134-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Feb 25 12:13:51 mega ollama[1898]: time=2025-02-25T12:13:51.691-08:00 level=INFO source=gpu.go:602 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15" Feb 25 12:13:56 mega ollama[1898]: time=2025-02-25T12:13:56.755-08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" Feb 25 12:13:56 mega ollama[1898]: time=2025-02-25T12:13:56.755-08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="251.4 GiB" available="248.5 GiB" ``` ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.5.11
GiteaMirror added the bug label 2026-04-28 23:52:43 -05:00
GiteaMirror commented 2026-04-28 23:52:45 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Feb 26, 2025):

@aloeppert thank you for reporting, I'm looking into the specific reason.

That being said, this is not a model uploaded by us. It's a community uploaded model. May I ask how you found the model?

<!-- gh-comment-id:2683596258 --> @mchiang0610 commented on GitHub (Feb 26, 2025): @aloeppert thank you for reporting, I'm looking into the specific reason. That being said, this is not a model uploaded by us. It's a community uploaded model. May I ask how you found the model?
GiteaMirror commented 2026-04-28 23:52:45 -05:00
Author
Owner
Copy Link

@aloeppert commented on GitHub (Feb 26, 2025):

@aloeppert thank you for reporting, I'm looking into the specific reason.

That being said, this is not a model uploaded by us. It's a community uploaded model. May I ask how you found the model?

I was poking around on the model website:
https://ollama.com/search

<!-- gh-comment-id:2683612367 --> @aloeppert commented on GitHub (Feb 26, 2025): > [@aloeppert](https://github.com/aloeppert) thank you for reporting, I'm looking into the specific reason. > > That being said, this is not a model uploaded by us. It's a community uploaded model. May I ask how you found the model? I was poking around on the model website: https://ollama.com/search
GiteaMirror commented 2026-04-28 23:52:45 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 9, 2026):

It looks like org took the shards from https://hf.co/unsloth/r1-1776-GGUF:Q2_K_XL and just listed them in a Modelfile. Ollama doesn't currently support sharded models (#5245), and will now log an error for this type of model:

ollama  | llama_model_load: error loading model: illegal split file idx: 4 (file: /root/.ollama/models/blobs/sha256-dff704a88236d692cf56a46b2972d5885d238ca46c846b43842d8b654097676f), model must be loaded with the first split
ollama  | llama_model_load_from_file_impl: failed to load model
<!-- gh-comment-id:3873192492 --> @rick-github commented on GitHub (Feb 9, 2026): It looks like org took the shards from [https://hf.co/unsloth/r1-1776-GGUF:Q2_K_XL](https://huggingface.co/unsloth/r1-1776-GGUF/tree/main/Q2_K_L) and just listed them in a Modelfile. Ollama doesn't currently support sharded models (#5245), and will now log an error for this type of model: ``` ollama | llama_model_load: error loading model: illegal split file idx: 4 (file: /root/.ollama/models/blobs/sha256-dff704a88236d692cf56a46b2972d5885d238ca46c846b43842d8b654097676f), model must be loaded with the first split ollama | llama_model_load_from_file_impl: failed to load model ```
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#52616
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?