github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 14:43:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15107] 10 minutes http client timeout is too low when image generation is done on CPU #9678

New Issue
Open
opened 2026-04-12 22:33:50 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 22:33:50 -05:00
Owner
Copy Link

Originally created by @yurivict on GitHub (Mar 27, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15107

What is the issue?

This line sets the 10 minute timeout regardless of the hardware.

This is maybe fine on a GPU, but is certainly too low for a CPU.
The timeout should be at least an hour or more when CPU is used.

Relevant log output

OS

Linux

GPU

No response

CPU

AMD

Ollama version

0.18.3

Originally created by @yurivict on GitHub (Mar 27, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15107 ### What is the issue? [This line](https://github.com/ollama/ollama/blob/main/x/imagegen/server.go#L58) sets the 10 minute timeout regardless of the hardware. This is maybe fine on a GPU, but is certainly too low for a CPU. The timeout should be at least an hour or more when CPU is used. ### Relevant log output ```shell ``` ### OS Linux ### GPU _No response_ ### CPU AMD ### Ollama version 0.18.3
GiteaMirror added the bug label 2026-04-12 22:33:50 -05:00
GiteaMirror commented 2026-04-12 22:33:51 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 27, 2026):

Do you have logs showing a failed generation?

<!-- gh-comment-id:4145862397 --> @rick-github commented on GitHub (Mar 27, 2026): Do you have logs showing a failed generation?
GiteaMirror commented 2026-04-12 22:33:51 -05:00
Author
Owner
Copy Link

@yurivict commented on GitHub (Mar 28, 2026):

Image gen works without this timeout, but with the timeout it fails with this server log:

$ ollama-serve 
time=2026-03-28T02:39:41.185-07:00 level=INFO source=routes.go:1740 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:65536 OLLAMA_DEBUG:INFO OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:/home/yuri/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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 OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2026-03-28T02:39:41.185-07:00 level=INFO source=routes.go:1742 msg="Ollama cloud disabled: false"
time=2026-03-28T02:39:41.219-07:00 level=INFO source=images.go:477 msg="total blobs: 2339"
time=2026-03-28T02:39:41.222-07:00 level=INFO source=images.go:484 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] HEAD   /                         --> github.com/yurivict/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
[GIN-debug] GET    /                         --> github.com/yurivict/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
[GIN-debug] HEAD   /api/version              --> github.com/yurivict/ollama/server.(*Server).GenerateRoutes.func3 (5 handlers)
[GIN-debug] GET    /api/version              --> github.com/yurivict/ollama/server.(*Server).GenerateRoutes.func4 (5 handlers)
[GIN-debug] GET    /api/status               --> github.com/yurivict/ollama/server.(*Server).StatusHandler-fm (5 handlers)
[GIN-debug] POST   /api/pull                 --> github.com/yurivict/ollama/server.(*Server).PullHandler-fm (5 handlers)
[GIN-debug] POST   /api/push                 --> github.com/yurivict/ollama/server.(*Server).PushHandler-fm (5 handlers)
[GIN-debug] HEAD   /api/tags                 --> github.com/yurivict/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] GET    /api/tags                 --> github.com/yurivict/ollama/server.(*Server).ListHandler-fm (5 handlers)
[GIN-debug] POST   /api/show                 --> github.com/yurivict/ollama/server.(*Server).ShowHandler-fm (5 handlers)
[GIN-debug] DELETE /api/delete               --> github.com/yurivict/ollama/server.(*Server).DeleteHandler-fm (5 handlers)
[GIN-debug] POST   /api/me                   --> github.com/yurivict/ollama/server.(*Server).WhoamiHandler-fm (5 handlers)
[GIN-debug] POST   /api/signout              --> github.com/yurivict/ollama/server.(*Server).SignoutHandler-fm (5 handlers)
[GIN-debug] DELETE /api/user/keys/:encodedKey --> github.com/yurivict/ollama/server.(*Server).SignoutHandler-fm (5 handlers)
[GIN-debug] POST   /api/create               --> github.com/yurivict/ollama/server.(*Server).CreateHandler-fm (5 handlers)
[GIN-debug] POST   /api/blobs/:digest        --> github.com/yurivict/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers)
[GIN-debug] HEAD   /api/blobs/:digest        --> github.com/yurivict/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers)
[GIN-debug] POST   /api/copy                 --> github.com/yurivict/ollama/server.(*Server).CopyHandler-fm (5 handlers)
[GIN-debug] POST   /api/experimental/web_search --> github.com/yurivict/ollama/server.(*Server).WebSearchExperimentalHandler-fm (5 handlers)
[GIN-debug] POST   /api/experimental/web_fetch --> github.com/yurivict/ollama/server.(*Server).WebFetchExperimentalHandler-fm (5 handlers)
[GIN-debug] GET    /api/ps                   --> github.com/yurivict/ollama/server.(*Server).PsHandler-fm (5 handlers)
[GIN-debug] POST   /api/generate             --> github.com/yurivict/ollama/server.(*Server).GenerateHandler-fm (5 handlers)
[GIN-debug] POST   /api/chat                 --> github.com/yurivict/ollama/server.(*Server).ChatHandler-fm (5 handlers)
[GIN-debug] POST   /api/embed                --> github.com/yurivict/ollama/server.(*Server).EmbedHandler-fm (5 handlers)
[GIN-debug] POST   /api/embeddings           --> github.com/yurivict/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers)
[GIN-debug] POST   /v1/chat/completions      --> github.com/yurivict/ollama/server.(*Server).ChatHandler-fm (7 handlers)
[GIN-debug] POST   /v1/completions           --> github.com/yurivict/ollama/server.(*Server).GenerateHandler-fm (7 handlers)
[GIN-debug] POST   /v1/embeddings            --> github.com/yurivict/ollama/server.(*Server).EmbedHandler-fm (7 handlers)
[GIN-debug] GET    /v1/models                --> github.com/yurivict/ollama/server.(*Server).ListHandler-fm (6 handlers)
[GIN-debug] GET    /v1/models/:model         --> github.com/yurivict/ollama/server.(*Server).ShowHandler-fm (7 handlers)
[GIN-debug] POST   /v1/responses             --> github.com/yurivict/ollama/server.(*Server).ChatHandler-fm (7 handlers)
[GIN-debug] POST   /v1/images/generations    --> github.com/yurivict/ollama/server.(*Server).GenerateHandler-fm (7 handlers)
[GIN-debug] POST   /v1/images/edits          --> github.com/yurivict/ollama/server.(*Server).GenerateHandler-fm (7 handlers)
[GIN-debug] POST   /v1/messages              --> github.com/yurivict/ollama/server.(*Server).ChatHandler-fm (7 handlers)
time=2026-03-28T02:39:41.222-07:00 level=INFO source=routes.go:1798 msg="Listening on 127.0.0.1:11434 (version 0.18.3)"
time=2026-03-28T02:39:41.222-07:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-03-28T02:39:41.223-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 24959"
time=2026-03-28T02:39:41.243-07:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="61.5 GiB" available="21.8 GiB"
time=2026-03-28T02:39:41.243-07:00 level=INFO source=routes.go:1848 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
[GIN] 2026/03/28 - 02:40:20 | 200 |     128.171µs |       127.0.0.1 | HEAD     "/"
[GIN] 2026/03/28 - 02:40:20 | 200 |   40.320913ms |       127.0.0.1 | POST     "/api/show"
time=2026-03-28T02:40:20.353-07:00 level=INFO source=sched.go:484 msg="system memory" total="61.5 GiB" free="21.7 GiB" free_swap="66.0 GiB"
time=2026-03-28T02:40:20.355-07:00 level=INFO source=server.go:173 msg="starting mlx runner subprocess" model=x/z-image-turbo:latest port=46122
time=2026-03-28T02:40:20.358-07:00 level=INFO source=sched.go:561 msg="loaded runners" count=1
time=2026-03-28T02:40:20.368-07:00 level=WARN source=server.go:166 msg=mlx-runner msg="time=2026-03-28T02:40:20.368-07:00 level=INFO msg=\"starting mlx runner\" model=x/z-image-turbo:latest port=46122 mode=imagegen"
time=2026-03-28T02:40:20.368-07:00 level=WARN source=server.go:166 msg=mlx-runner msg="time=2026-03-28T02:40:20.368-07:00 level=INFO msg=\"MLX library initialized\""
time=2026-03-28T02:40:20.372-07:00 level=WARN source=server.go:166 msg=mlx-runner msg="time=2026-03-28T02:40:20.372-07:00 level=INFO msg=\"detected image model type\" type=ZImagePipeline"
time=2026-03-28T02:40:20.372-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="Loading Z-Image model from manifest: x/z-image-turbo:latest..."
time=2026-03-28T02:40:20.568-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loading tokenizer... ✓"
time=2026-03-28T02:40:29.401-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loading text encoder... ✓"
time=2026-03-28T02:40:45.960-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  (11.3 GB, peak 12.9 GB)"
time=2026-03-28T02:41:03.228-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loading transformer... ✓"
time=2026-03-28T02:41:45.435-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  (41.4 GB, peak 42.9 GB)"
time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loading conv_in... ✓"
time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loading mid block... ✓"
time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loading up blocks... ✓ [4 blocks]"
time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loading conv_norm_out... ✓"
time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loading conv_out... ✓"
time=2026-03-28T02:41:45.789-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  (41.5 GB, peak 42.9 GB)"
time=2026-03-28T02:41:45.789-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Loaded in 85.42s (41.5 GB VRAM)"
time=2026-03-28T02:41:45.790-07:00 level=WARN source=server.go:166 msg=mlx-runner msg="time=2026-03-28T02:41:45.790-07:00 level=INFO msg=\"mlx runner listening\" addr=127.0.0.1:46122"
time=2026-03-28T02:41:45.862-07:00 level=INFO source=server.go:234 msg="mlx runner is ready" port=46122
time=2026-03-28T02:42:10.261-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  TeaCache enabled: threshold=0.15"
time=2026-03-28T02:51:38.117-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Step 1/9: t=1.0000 (567.86s) [41.5 GB active, 45.8 GB peak]"
time=2026-03-28T02:51:38.117-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="    [TeaCache: reusing cached output]"
time=2026-03-28T02:51:38.118-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Step 2/9: t=0.9619 (0.00s) [41.5 GB active, 45.8 GB peak]"
time=2026-03-28T02:51:38.118-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="    [TeaCache: reusing cached output]"
time=2026-03-28T02:51:38.118-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Step 3/9: t=0.9170 (0.00s) [41.5 GB active, 45.8 GB peak]"
time=2026-03-28T03:00:13.237-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Step 4/9: t=0.8633 (515.12s) [41.5 GB active, 45.8 GB peak]"
time=2026-03-28T03:00:13.237-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="    [TeaCache: reusing cached output]"
time=2026-03-28T03:00:13.237-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Step 5/9: t=0.7979 (0.00s) [41.5 GB active, 45.8 GB peak]"
time=2026-03-28T03:09:18.034-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Step 6/9: t=0.7164 (544.80s) [41.5 GB active, 45.8 GB peak]"
time=2026-03-28T03:09:18.034-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="    [TeaCache: reusing cached output]"
time=2026-03-28T03:09:18.035-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Step 7/9: t=0.6123 (0.00s) [41.5 GB active, 45.8 GB peak]"
time=2026-03-28T03:16:58.111-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="  Step 8/9: t=0.4743 (460.08s) [41.5 GB active, 45.8 GB peak]"
time=2026-03-28T03:23:41.316-07:00 level=ERROR source=server.go:346 msg="mlx scanner error" error="unexpected EOF"
[GIN] 2026/03/28 - 03:23:41 | 200 |        43m21s |       127.0.0.1 | POST     "/api/generate"
time=2026-03-28T03:28:41.647-07:00 level=INFO source=server.go:365 msg="stopping mlx runner subprocess" pid=19769

The client exited with exit code 0 (success) without printing any message which is also a problem.

<!-- gh-comment-id:4148364037 --> @yurivict commented on GitHub (Mar 28, 2026): Image gen works without this timeout, but with the timeout it fails with this server log: ``` $ ollama-serve time=2026-03-28T02:39:41.185-07:00 level=INFO source=routes.go:1740 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:65536 OLLAMA_DEBUG:INFO OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:/home/yuri/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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 OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2026-03-28T02:39:41.185-07:00 level=INFO source=routes.go:1742 msg="Ollama cloud disabled: false" time=2026-03-28T02:39:41.219-07:00 level=INFO source=images.go:477 msg="total blobs: 2339" time=2026-03-28T02:39:41.222-07:00 level=INFO source=images.go:484 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] HEAD / --> github.com/yurivict/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers) [GIN-debug] GET / --> github.com/yurivict/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers) [GIN-debug] HEAD /api/version --> github.com/yurivict/ollama/server.(*Server).GenerateRoutes.func3 (5 handlers) [GIN-debug] GET /api/version --> github.com/yurivict/ollama/server.(*Server).GenerateRoutes.func4 (5 handlers) [GIN-debug] GET /api/status --> github.com/yurivict/ollama/server.(*Server).StatusHandler-fm (5 handlers) [GIN-debug] POST /api/pull --> github.com/yurivict/ollama/server.(*Server).PullHandler-fm (5 handlers) [GIN-debug] POST /api/push --> github.com/yurivict/ollama/server.(*Server).PushHandler-fm (5 handlers) [GIN-debug] HEAD /api/tags --> github.com/yurivict/ollama/server.(*Server).ListHandler-fm (5 handlers) [GIN-debug] GET /api/tags --> github.com/yurivict/ollama/server.(*Server).ListHandler-fm (5 handlers) [GIN-debug] POST /api/show --> github.com/yurivict/ollama/server.(*Server).ShowHandler-fm (5 handlers) [GIN-debug] DELETE /api/delete --> github.com/yurivict/ollama/server.(*Server).DeleteHandler-fm (5 handlers) [GIN-debug] POST /api/me --> github.com/yurivict/ollama/server.(*Server).WhoamiHandler-fm (5 handlers) [GIN-debug] POST /api/signout --> github.com/yurivict/ollama/server.(*Server).SignoutHandler-fm (5 handlers) [GIN-debug] DELETE /api/user/keys/:encodedKey --> github.com/yurivict/ollama/server.(*Server).SignoutHandler-fm (5 handlers) [GIN-debug] POST /api/create --> github.com/yurivict/ollama/server.(*Server).CreateHandler-fm (5 handlers) [GIN-debug] POST /api/blobs/:digest --> github.com/yurivict/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers) [GIN-debug] HEAD /api/blobs/:digest --> github.com/yurivict/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers) [GIN-debug] POST /api/copy --> github.com/yurivict/ollama/server.(*Server).CopyHandler-fm (5 handlers) [GIN-debug] POST /api/experimental/web_search --> github.com/yurivict/ollama/server.(*Server).WebSearchExperimentalHandler-fm (5 handlers) [GIN-debug] POST /api/experimental/web_fetch --> github.com/yurivict/ollama/server.(*Server).WebFetchExperimentalHandler-fm (5 handlers) [GIN-debug] GET /api/ps --> github.com/yurivict/ollama/server.(*Server).PsHandler-fm (5 handlers) [GIN-debug] POST /api/generate --> github.com/yurivict/ollama/server.(*Server).GenerateHandler-fm (5 handlers) [GIN-debug] POST /api/chat --> github.com/yurivict/ollama/server.(*Server).ChatHandler-fm (5 handlers) [GIN-debug] POST /api/embed --> github.com/yurivict/ollama/server.(*Server).EmbedHandler-fm (5 handlers) [GIN-debug] POST /api/embeddings --> github.com/yurivict/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers) [GIN-debug] POST /v1/chat/completions --> github.com/yurivict/ollama/server.(*Server).ChatHandler-fm (7 handlers) [GIN-debug] POST /v1/completions --> github.com/yurivict/ollama/server.(*Server).GenerateHandler-fm (7 handlers) [GIN-debug] POST /v1/embeddings --> github.com/yurivict/ollama/server.(*Server).EmbedHandler-fm (7 handlers) [GIN-debug] GET /v1/models --> github.com/yurivict/ollama/server.(*Server).ListHandler-fm (6 handlers) [GIN-debug] GET /v1/models/:model --> github.com/yurivict/ollama/server.(*Server).ShowHandler-fm (7 handlers) [GIN-debug] POST /v1/responses --> github.com/yurivict/ollama/server.(*Server).ChatHandler-fm (7 handlers) [GIN-debug] POST /v1/images/generations --> github.com/yurivict/ollama/server.(*Server).GenerateHandler-fm (7 handlers) [GIN-debug] POST /v1/images/edits --> github.com/yurivict/ollama/server.(*Server).GenerateHandler-fm (7 handlers) [GIN-debug] POST /v1/messages --> github.com/yurivict/ollama/server.(*Server).ChatHandler-fm (7 handlers) time=2026-03-28T02:39:41.222-07:00 level=INFO source=routes.go:1798 msg="Listening on 127.0.0.1:11434 (version 0.18.3)" time=2026-03-28T02:39:41.222-07:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-03-28T02:39:41.223-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 24959" time=2026-03-28T02:39:41.243-07:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="61.5 GiB" available="21.8 GiB" time=2026-03-28T02:39:41.243-07:00 level=INFO source=routes.go:1848 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096 [GIN] 2026/03/28 - 02:40:20 | 200 | 128.171µs | 127.0.0.1 | HEAD "/" [GIN] 2026/03/28 - 02:40:20 | 200 | 40.320913ms | 127.0.0.1 | POST "/api/show" time=2026-03-28T02:40:20.353-07:00 level=INFO source=sched.go:484 msg="system memory" total="61.5 GiB" free="21.7 GiB" free_swap="66.0 GiB" time=2026-03-28T02:40:20.355-07:00 level=INFO source=server.go:173 msg="starting mlx runner subprocess" model=x/z-image-turbo:latest port=46122 time=2026-03-28T02:40:20.358-07:00 level=INFO source=sched.go:561 msg="loaded runners" count=1 time=2026-03-28T02:40:20.368-07:00 level=WARN source=server.go:166 msg=mlx-runner msg="time=2026-03-28T02:40:20.368-07:00 level=INFO msg=\"starting mlx runner\" model=x/z-image-turbo:latest port=46122 mode=imagegen" time=2026-03-28T02:40:20.368-07:00 level=WARN source=server.go:166 msg=mlx-runner msg="time=2026-03-28T02:40:20.368-07:00 level=INFO msg=\"MLX library initialized\"" time=2026-03-28T02:40:20.372-07:00 level=WARN source=server.go:166 msg=mlx-runner msg="time=2026-03-28T02:40:20.372-07:00 level=INFO msg=\"detected image model type\" type=ZImagePipeline" time=2026-03-28T02:40:20.372-07:00 level=INFO source=server.go:159 msg=mlx-runner msg="Loading Z-Image model from manifest: x/z-image-turbo:latest..." time=2026-03-28T02:40:20.568-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loading tokenizer... ✓" time=2026-03-28T02:40:29.401-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loading text encoder... ✓" time=2026-03-28T02:40:45.960-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" (11.3 GB, peak 12.9 GB)" time=2026-03-28T02:41:03.228-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loading transformer... ✓" time=2026-03-28T02:41:45.435-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" (41.4 GB, peak 42.9 GB)" time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loading conv_in... ✓" time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loading mid block... ✓" time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loading up blocks... ✓ [4 blocks]" time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loading conv_norm_out... ✓" time=2026-03-28T02:41:45.788-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loading conv_out... ✓" time=2026-03-28T02:41:45.789-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" (41.5 GB, peak 42.9 GB)" time=2026-03-28T02:41:45.789-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Loaded in 85.42s (41.5 GB VRAM)" time=2026-03-28T02:41:45.790-07:00 level=WARN source=server.go:166 msg=mlx-runner msg="time=2026-03-28T02:41:45.790-07:00 level=INFO msg=\"mlx runner listening\" addr=127.0.0.1:46122" time=2026-03-28T02:41:45.862-07:00 level=INFO source=server.go:234 msg="mlx runner is ready" port=46122 time=2026-03-28T02:42:10.261-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" TeaCache enabled: threshold=0.15" time=2026-03-28T02:51:38.117-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Step 1/9: t=1.0000 (567.86s) [41.5 GB active, 45.8 GB peak]" time=2026-03-28T02:51:38.117-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" [TeaCache: reusing cached output]" time=2026-03-28T02:51:38.118-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Step 2/9: t=0.9619 (0.00s) [41.5 GB active, 45.8 GB peak]" time=2026-03-28T02:51:38.118-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" [TeaCache: reusing cached output]" time=2026-03-28T02:51:38.118-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Step 3/9: t=0.9170 (0.00s) [41.5 GB active, 45.8 GB peak]" time=2026-03-28T03:00:13.237-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Step 4/9: t=0.8633 (515.12s) [41.5 GB active, 45.8 GB peak]" time=2026-03-28T03:00:13.237-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" [TeaCache: reusing cached output]" time=2026-03-28T03:00:13.237-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Step 5/9: t=0.7979 (0.00s) [41.5 GB active, 45.8 GB peak]" time=2026-03-28T03:09:18.034-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Step 6/9: t=0.7164 (544.80s) [41.5 GB active, 45.8 GB peak]" time=2026-03-28T03:09:18.034-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" [TeaCache: reusing cached output]" time=2026-03-28T03:09:18.035-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Step 7/9: t=0.6123 (0.00s) [41.5 GB active, 45.8 GB peak]" time=2026-03-28T03:16:58.111-07:00 level=INFO source=server.go:159 msg=mlx-runner msg=" Step 8/9: t=0.4743 (460.08s) [41.5 GB active, 45.8 GB peak]" time=2026-03-28T03:23:41.316-07:00 level=ERROR source=server.go:346 msg="mlx scanner error" error="unexpected EOF" [GIN] 2026/03/28 - 03:23:41 | 200 | 43m21s | 127.0.0.1 | POST "/api/generate" time=2026-03-28T03:28:41.647-07:00 level=INFO source=server.go:365 msg="stopping mlx runner subprocess" pid=19769 ``` The client exited with exit code 0 (success) without printing any message which is also a problem.
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#9678
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?