github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12026] Ollama Service Killed During ’converting model‘ When Adding Fine-Tuned Model on Linux #33745

New Issue
Closed
opened 2026-04-22 16:43:11 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 16:43:11 -05:00
Owner
Copy Link

Originally created by @Paul-Grant2000 on GitHub (Aug 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12026

What is the issue?

Hello everyone, I encountered a strange issue while using Ollama on a Linux server. When I used the command 'ollama create model' to add a Safetensors format model that I had fine-tuned myself to Ollama, the Ollama service was unexpectedly killed during the console output "converting model." This fine-tuned model could be added normally on the Windows version of Ollama. Strangely, when I used the same command to add a downloaded GGUF format model, it was added successfully. I am unsure where the problem lies and would appreciate any insights from experts who might know about this issue.

Relevant log output

(base) root:~/merge_output/Qwen_coder_7B_2100# ollama create qwencoder
gathering model components 
copying file sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa 100% 
copying file sha256:88512721805f73b6e813946b9fc056170ffde78ef1738a6f9a283170d6be10f9 100% 
copying file sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa 100% 
copying file sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b 100% 
copying file sha256:5aa6e5cbe642377fd441fb4e60e83cca96b2bcd9820e245b9ea06d94653f17f2 100% 
copying file sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b 100% 
copying file sha256:0962ca6631df3dbf813431f098c5baa203b1b870b0ff158796740719208065c2 100% 
copying file sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 100% 
copying file sha256:20db9a065d1a2e4ed9e1158bf6bcbeb37b7fb5b739db536f62a649b54a7be16e 100% 
copying file sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 100% 
copying file sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb 100% 
copying file sha256:fcdef8bc02ee7f055a80503a0b57074013fc697c7cc6ca6d38457cd6f05e0a58 100% 
copying file sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710 100% 
copying file sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd 100% 
copying file sha256:d63855fa35c986f08a50bd48a500668d1e896917f0966a45e9a5168d715dab6f 100% 
copying file sha256:fcdef8bc02ee7f055a80503a0b57074013fc697c7cc6ca6d38457cd6f05e0a58 100% 
copying file sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd 100% 
copying file sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb 100% 
copying file sha256:20db9a065d1a2e4ed9e1158bf6bcbeb37b7fb5b739db536f62a649b54a7be16e 100% 
copying file sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710 100% 
converting model 
(base) root:~/merge_output/Qwen_coder_7B_2100# 


(base) root:~# ollama serve
time=2025-08-22T14:18:20.884+08:00 level=INFO source=routes.go:1318 msg="server config" env="map[CUDA_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://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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NEW_ESTIMATES: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_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-08-22T14:18:20.885+08:00 level=INFO source=images.go:477 msg="total blobs: 14"
time=2025-08-22T14:18:20.886+08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 12"
time=2025-08-22T14:18:20.886+08:00 level=INFO source=routes.go:1371 msg="Listening on 127.0.0.1:11434 (version 0.11.6)"
time=2025-08-22T14:18:20.886+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-22T14:18:21.096+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d4046a26-9f69-36f8-3fa5-3fabd5c52864 library=cuda variant=v12 compute=8.0 driver=12.2 name="NVIDIA A800-SXM4-80GB" total="79.3 GiB" available="78.9 GiB"
[GIN] 2025/08/22 - 14:19:44 | 200 |      39.641µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/22 - 14:19:50 | 201 |    1.430265ms |       127.0.0.1 | POST     "/api/blobs/sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd"
[GIN] 2025/08/22 - 14:19:50 | 201 |     420.744µs |       127.0.0.1 | POST     "/api/blobs/sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b"
[GIN] 2025/08/22 - 14:19:50 | 201 |    1.504626ms |       127.0.0.1 | POST     "/api/blobs/sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b"
[GIN] 2025/08/22 - 14:19:50 | 201 |     930.731µs |       127.0.0.1 | POST     "/api/blobs/sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd"
[GIN] 2025/08/22 - 14:19:50 | 200 |     826.309µs |       127.0.0.1 | POST     "/api/blobs/sha256:20db9a065d1a2e4ed9e1158bf6bcbeb37b7fb5b739db536f62a649b54a7be16e"
[GIN] 2025/08/22 - 14:19:50 | 201 |     661.029µs |       127.0.0.1 | POST     "/api/blobs/sha256:20db9a065d1a2e4ed9e1158bf6bcbeb37b7fb5b739db536f62a649b54a7be16e"
[GIN] 2025/08/22 - 14:19:50 | 201 |     1.73941ms |       127.0.0.1 | POST     "/api/blobs/sha256:fcdef8bc02ee7f055a80503a0b57074013fc697c7cc6ca6d38457cd6f05e0a58"
[GIN] 2025/08/22 - 14:19:50 | 201 |    1.729821ms |       127.0.0.1 | POST     "/api/blobs/sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710"
[GIN] 2025/08/22 - 14:19:50 | 201 |    1.664407ms |       127.0.0.1 | POST     "/api/blobs/sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710"
[GIN] 2025/08/22 - 14:19:50 | 201 |     914.385µs |       127.0.0.1 | POST     "/api/blobs/sha256:fcdef8bc02ee7f055a80503a0b57074013fc697c7cc6ca6d38457cd6f05e0a58"
[GIN] 2025/08/22 - 14:19:50 | 201 |     2.26517ms |       127.0.0.1 | POST     "/api/blobs/sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb"
[GIN] 2025/08/22 - 14:19:50 | 201 |    2.146527ms |       127.0.0.1 | POST     "/api/blobs/sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb"
[GIN] 2025/08/22 - 14:19:50 | 201 |   17.842599ms |       127.0.0.1 | POST     "/api/blobs/sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa"
[GIN] 2025/08/22 - 14:19:50 | 201 |    5.070885ms |       127.0.0.1 | POST     "/api/blobs/sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"
[GIN] 2025/08/22 - 14:19:50 | 201 |    4.795032ms |       127.0.0.1 | POST     "/api/blobs/sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"
[GIN] 2025/08/22 - 14:19:50 | 201 |   17.843664ms |       127.0.0.1 | POST     "/api/blobs/sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa"
[GIN] 2025/08/22 - 14:19:51 | 201 |  1.465328174s |       127.0.0.1 | POST     "/api/blobs/sha256:5aa6e5cbe642377fd441fb4e60e83cca96b2bcd9820e245b9ea06d94653f17f2"
[GIN] 2025/08/22 - 14:19:55 | 201 |  5.775598735s |       127.0.0.1 | POST     "/api/blobs/sha256:88512721805f73b6e813946b9fc056170ffde78ef1738a6f9a283170d6be10f9"
[GIN] 2025/08/22 - 14:19:56 | 201 |  6.454938488s |       127.0.0.1 | POST     "/api/blobs/sha256:d63855fa35c986f08a50bd48a500668d1e896917f0966a45e9a5168d715dab6f"
[GIN] 2025/08/22 - 14:19:56 | 201 |  6.538105052s |       127.0.0.1 | POST     "/api/blobs/sha256:0962ca6631df3dbf813431f098c5baa203b1b870b0ff158796740719208065c2"
Killed
(base) root:~#

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.11.2

Originally created by @Paul-Grant2000 on GitHub (Aug 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12026 ### What is the issue? Hello everyone, I encountered a strange issue while using Ollama on a Linux server. When I used the command 'ollama create model' to add a Safetensors format model that I had fine-tuned myself to Ollama, the Ollama service was unexpectedly killed during the console output "converting model." This fine-tuned model could be added normally on the Windows version of Ollama. Strangely, when I used the same command to add a downloaded GGUF format model, it was added successfully. I am unsure where the problem lies and would appreciate any insights from experts who might know about this issue. ### Relevant log output ```shell (base) root:~/merge_output/Qwen_coder_7B_2100# ollama create qwencoder gathering model components copying file sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa 100% copying file sha256:88512721805f73b6e813946b9fc056170ffde78ef1738a6f9a283170d6be10f9 100% copying file sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa 100% copying file sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b 100% copying file sha256:5aa6e5cbe642377fd441fb4e60e83cca96b2bcd9820e245b9ea06d94653f17f2 100% copying file sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b 100% copying file sha256:0962ca6631df3dbf813431f098c5baa203b1b870b0ff158796740719208065c2 100% copying file sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 100% copying file sha256:20db9a065d1a2e4ed9e1158bf6bcbeb37b7fb5b739db536f62a649b54a7be16e 100% copying file sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 100% copying file sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb 100% copying file sha256:fcdef8bc02ee7f055a80503a0b57074013fc697c7cc6ca6d38457cd6f05e0a58 100% copying file sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710 100% copying file sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd 100% copying file sha256:d63855fa35c986f08a50bd48a500668d1e896917f0966a45e9a5168d715dab6f 100% copying file sha256:fcdef8bc02ee7f055a80503a0b57074013fc697c7cc6ca6d38457cd6f05e0a58 100% copying file sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd 100% copying file sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb 100% copying file sha256:20db9a065d1a2e4ed9e1158bf6bcbeb37b7fb5b739db536f62a649b54a7be16e 100% copying file sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710 100% converting model (base) root:~/merge_output/Qwen_coder_7B_2100# (base) root:~# ollama serve time=2025-08-22T14:18:20.884+08:00 level=INFO source=routes.go:1318 msg="server config" env="map[CUDA_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://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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NEW_ESTIMATES: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_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-08-22T14:18:20.885+08:00 level=INFO source=images.go:477 msg="total blobs: 14" time=2025-08-22T14:18:20.886+08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 12" time=2025-08-22T14:18:20.886+08:00 level=INFO source=routes.go:1371 msg="Listening on 127.0.0.1:11434 (version 0.11.6)" time=2025-08-22T14:18:20.886+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-08-22T14:18:21.096+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d4046a26-9f69-36f8-3fa5-3fabd5c52864 library=cuda variant=v12 compute=8.0 driver=12.2 name="NVIDIA A800-SXM4-80GB" total="79.3 GiB" available="78.9 GiB" [GIN] 2025/08/22 - 14:19:44 | 200 | 39.641µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/22 - 14:19:50 | 201 | 1.430265ms | 127.0.0.1 | POST "/api/blobs/sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd" [GIN] 2025/08/22 - 14:19:50 | 201 | 420.744µs | 127.0.0.1 | POST "/api/blobs/sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b" [GIN] 2025/08/22 - 14:19:50 | 201 | 1.504626ms | 127.0.0.1 | POST "/api/blobs/sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b" [GIN] 2025/08/22 - 14:19:50 | 201 | 930.731µs | 127.0.0.1 | POST "/api/blobs/sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd" [GIN] 2025/08/22 - 14:19:50 | 200 | 826.309µs | 127.0.0.1 | POST "/api/blobs/sha256:20db9a065d1a2e4ed9e1158bf6bcbeb37b7fb5b739db536f62a649b54a7be16e" [GIN] 2025/08/22 - 14:19:50 | 201 | 661.029µs | 127.0.0.1 | POST "/api/blobs/sha256:20db9a065d1a2e4ed9e1158bf6bcbeb37b7fb5b739db536f62a649b54a7be16e" [GIN] 2025/08/22 - 14:19:50 | 201 | 1.73941ms | 127.0.0.1 | POST "/api/blobs/sha256:fcdef8bc02ee7f055a80503a0b57074013fc697c7cc6ca6d38457cd6f05e0a58" [GIN] 2025/08/22 - 14:19:50 | 201 | 1.729821ms | 127.0.0.1 | POST "/api/blobs/sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710" [GIN] 2025/08/22 - 14:19:50 | 201 | 1.664407ms | 127.0.0.1 | POST "/api/blobs/sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710" [GIN] 2025/08/22 - 14:19:50 | 201 | 914.385µs | 127.0.0.1 | POST "/api/blobs/sha256:fcdef8bc02ee7f055a80503a0b57074013fc697c7cc6ca6d38457cd6f05e0a58" [GIN] 2025/08/22 - 14:19:50 | 201 | 2.26517ms | 127.0.0.1 | POST "/api/blobs/sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb" [GIN] 2025/08/22 - 14:19:50 | 201 | 2.146527ms | 127.0.0.1 | POST "/api/blobs/sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb" [GIN] 2025/08/22 - 14:19:50 | 201 | 17.842599ms | 127.0.0.1 | POST "/api/blobs/sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa" [GIN] 2025/08/22 - 14:19:50 | 201 | 5.070885ms | 127.0.0.1 | POST "/api/blobs/sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910" [GIN] 2025/08/22 - 14:19:50 | 201 | 4.795032ms | 127.0.0.1 | POST "/api/blobs/sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910" [GIN] 2025/08/22 - 14:19:50 | 201 | 17.843664ms | 127.0.0.1 | POST "/api/blobs/sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa" [GIN] 2025/08/22 - 14:19:51 | 201 | 1.465328174s | 127.0.0.1 | POST "/api/blobs/sha256:5aa6e5cbe642377fd441fb4e60e83cca96b2bcd9820e245b9ea06d94653f17f2" [GIN] 2025/08/22 - 14:19:55 | 201 | 5.775598735s | 127.0.0.1 | POST "/api/blobs/sha256:88512721805f73b6e813946b9fc056170ffde78ef1738a6f9a283170d6be10f9" [GIN] 2025/08/22 - 14:19:56 | 201 | 6.454938488s | 127.0.0.1 | POST "/api/blobs/sha256:d63855fa35c986f08a50bd48a500668d1e896917f0966a45e9a5168d715dab6f" [GIN] 2025/08/22 - 14:19:56 | 201 | 6.538105052s | 127.0.0.1 | POST "/api/blobs/sha256:0962ca6631df3dbf813431f098c5baa203b1b870b0ff158796740719208065c2" Killed (base) root:~# ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.11.2
GiteaMirror added the bug label 2026-04-22 16:43:11 -05:00
GiteaMirror commented 2026-04-22 16:43:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 3, 2025):

This is likely the server being killed due to an OOM issue while spinning up multiple go co-routines to process the tensors. You can set GOMAXPROCS=1 in the server environment to force the server to only launch one co-routine. It may take a little but longer to run but it should prevent the kernel from killing the server due to memory requirements.

<!-- gh-comment-id:3248737616 --> @rick-github commented on GitHub (Sep 3, 2025): This is likely the server being killed due to an OOM issue while spinning up multiple go co-routines to process the tensors. You can set `GOMAXPROCS=1` in the server environment to force the server to only launch one co-routine. It may take a little but longer to run but it should prevent the kernel from killing the server due to memory requirements.
GiteaMirror commented 2026-04-22 16:43:14 -05:00
Author
Owner
Copy Link

@hcaicai commented on GitHub (Sep 20, 2025):

This is likely the server being killed due to an OOM issue while spinning up multiple go co-routines to process the tensors. You can set GOMAXPROCS=1 in the server environment to force the server to only launch one co-routine. It may take a little but longer to run but it should prevent the kernel from killing the server due to memory requirements.

After setting GOMAXPROCS=1, the model conversion still fails. How can this issue be resolved?

(base) user1@Server:/model/Qwen2.5-7B-lora$ GOMAXPROCS=1 ollama create qwen2.5-7b-lora -f Modefile
gathering model components
copying file sha256:d10d4ad57348e7bf9b899b6d9b3b9cf8209776b47803e754541ca275e03f2dd3 100%
copying file sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 100%
copying file sha256:887c09423c3a29bda09175e95c056e6ec1fd36c265cdd589a7db12c80eac085e 100%
copying file sha256:c592a0ce7d8c1553d27cedab02cb200d610faecabd38038363c71ff98f3d4f53 100%
copying file sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b 100%
copying file sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710 100%
copying file sha256:56f7a098fe2da207676326ab02a0564a544aefd0ba309208f033cc3b72c501a0 100%
copying file sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd 100%
copying file sha256:d6fc3e28ea0bebb696b08b5ce047b640c1420493bd3baaf167ae1a2e29eb1b76 100%
copying file sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2 100%
copying file sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb 100%
copying file sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa 100%
converting model
(base) user1@Server:/model/Qwen2.5-7B-lora$

<!-- gh-comment-id:3314477760 --> @hcaicai commented on GitHub (Sep 20, 2025): > This is likely the server being killed due to an OOM issue while spinning up multiple go co-routines to process the tensors. You can set `GOMAXPROCS=1` in the server environment to force the server to only launch one co-routine. It may take a little but longer to run but it should prevent the kernel from killing the server due to memory requirements. After setting GOMAXPROCS=1, the model conversion still fails. How can this issue be resolved? (base) user1@Server:/model/Qwen2.5-7B-lora$ GOMAXPROCS=1 ollama create qwen2.5-7b-lora -f Modefile gathering model components copying file sha256:d10d4ad57348e7bf9b899b6d9b3b9cf8209776b47803e754541ca275e03f2dd3 100% copying file sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 100% copying file sha256:887c09423c3a29bda09175e95c056e6ec1fd36c265cdd589a7db12c80eac085e 100% copying file sha256:c592a0ce7d8c1553d27cedab02cb200d610faecabd38038363c71ff98f3d4f53 100% copying file sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b 100% copying file sha256:14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710 100% copying file sha256:56f7a098fe2da207676326ab02a0564a544aefd0ba309208f033cc3b72c501a0 100% copying file sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd 100% copying file sha256:d6fc3e28ea0bebb696b08b5ce047b640c1420493bd3baaf167ae1a2e29eb1b76 100% copying file sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2 100% copying file sha256:998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb 100% copying file sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa 100% converting model (base) user1@Server:/model/Qwen2.5-7B-lora$
GiteaMirror commented 2026-04-22 16:43:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 20, 2025):

Set GOMAXPROCS=1 in the server environment.

<!-- gh-comment-id:3314832401 --> @rick-github commented on GitHub (Sep 20, 2025): Set GOMAXPROCS=1 in the **server** environment.
GiteaMirror commented 2026-04-22 16:43:15 -05:00
Author
Owner
Copy Link

@mjyang04 commented on GitHub (Nov 5, 2025):

Still have the same problem

(base) ymj@cics:~/resource$ export GOMAXPROCS=1
(base) ymj@cics:~/resource$ ollama create DeepSeek-R1-70B -f /home/ymj/dev/DeepSeek-R1-70B/Modelfile
gathering model components
copying file sha256:3b91e78c60e2708c9354d46fe4fc20520d0a12713e13d5ffab60118305c96620 100%
copying file sha256:b1d4326d0d4187830fcea956d8ccfafbf6871fa7baed1b759c1ed843cafe92c0 100%
copying file sha256:62a83ba7af95d532065e46322ae2c17ee020c3c8e92b7285420c09ca0d6f68f0 100%
copying file sha256:8189753d14d5f9b3c31466d1f5a185bb7ffc7fc346cbc06a5453e48e07c2b97b 100%
copying file sha256:928bea3ae97c3962b3eb3f51a66f674be4cd5858caae541becd3e175f3305403 100%
copying file sha256:1db6d4f8387897b0f40e505310a1542f6d0308370526fa86c42cdc99451d2200 100%
copying file sha256:572ed974eb237aacf3de9ddfeaa373c62d39038a96ffd7f2beec6ea8f8a7b16e 100%
copying file sha256:cd5194726d1e8f7361a8c8425fc11d33ade5e69de1fd7615eb23fae5601af68b 100%
copying file sha256:8ac8c85fb242563c2260baec0909debd69d718af6a0b3d90e6cab62b4d341cd5 100%
copying file sha256:4f57a2538539d61f9f22785d3c48f089227829948ee66572808dd13d5b08d63e 100%
copying file sha256:3f948c2df3e4f3e678e1b4c75b345ce646c4843a23e7c9089462cf3995d2af45 100%
copying file sha256:31a5eb90d0773f1514ae7b240ed62961412e48f9eb160fdac6226221b87fe61f 100%
copying file sha256:d01c2823a0393ded7f97556995b69965dad78665664853f1c8a2be901e643a44 100%
copying file sha256:e5a581377b62f0a918bf515d05f2514281eec031ea2748e7ce8123b910403bba 100%
copying file sha256:077f51bc9eb56b50868cb95c7cf0d6d0f0a524b824ba3af8b248c78a46593e97 100%
copying file sha256:e826381017b2d8a9d8704be34ee0e0ceeb0a3a9abca27beaa4555d370d5a4f10 100%
copying file sha256:0f2ce0194b017ae009448602d7fd4ac24d7f25059c0a87d42fc496000f7bdacc 100%
copying file sha256:95ef9768e4741543dbfaf0c274f101855883ff338b235c99eca2b6a4f4abee12 100%
copying file sha256:f888421726665e8a84b738eed42a64875aed79de8be7daade851ac8bf4c0cef9 100%
copying file sha256:b9c9eb63a8e03059914880f918cd28a880dec8b6e15e4461e1ff677e3743dbb8 100%
copying file sha256:aa4b0afa70d26873dabc927e59b7dbc24a0e8eda323d4fdba17927d316d3516c 100%
copying file sha256:3c43532c1b128f0135edc587ace540dfa53759916836960db06b73ab718e5eca 100%
copying file sha256:605b29e86ec80aaa3a38bb3aab4bc859e4df26928fe49bbca00f127f55897e8d 100%
converting model
<!-- gh-comment-id:3489175783 --> @mjyang04 commented on GitHub (Nov 5, 2025): Still have the same problem ``` (base) ymj@cics:~/resource$ export GOMAXPROCS=1 (base) ymj@cics:~/resource$ ollama create DeepSeek-R1-70B -f /home/ymj/dev/DeepSeek-R1-70B/Modelfile gathering model components copying file sha256:3b91e78c60e2708c9354d46fe4fc20520d0a12713e13d5ffab60118305c96620 100% copying file sha256:b1d4326d0d4187830fcea956d8ccfafbf6871fa7baed1b759c1ed843cafe92c0 100% copying file sha256:62a83ba7af95d532065e46322ae2c17ee020c3c8e92b7285420c09ca0d6f68f0 100% copying file sha256:8189753d14d5f9b3c31466d1f5a185bb7ffc7fc346cbc06a5453e48e07c2b97b 100% copying file sha256:928bea3ae97c3962b3eb3f51a66f674be4cd5858caae541becd3e175f3305403 100% copying file sha256:1db6d4f8387897b0f40e505310a1542f6d0308370526fa86c42cdc99451d2200 100% copying file sha256:572ed974eb237aacf3de9ddfeaa373c62d39038a96ffd7f2beec6ea8f8a7b16e 100% copying file sha256:cd5194726d1e8f7361a8c8425fc11d33ade5e69de1fd7615eb23fae5601af68b 100% copying file sha256:8ac8c85fb242563c2260baec0909debd69d718af6a0b3d90e6cab62b4d341cd5 100% copying file sha256:4f57a2538539d61f9f22785d3c48f089227829948ee66572808dd13d5b08d63e 100% copying file sha256:3f948c2df3e4f3e678e1b4c75b345ce646c4843a23e7c9089462cf3995d2af45 100% copying file sha256:31a5eb90d0773f1514ae7b240ed62961412e48f9eb160fdac6226221b87fe61f 100% copying file sha256:d01c2823a0393ded7f97556995b69965dad78665664853f1c8a2be901e643a44 100% copying file sha256:e5a581377b62f0a918bf515d05f2514281eec031ea2748e7ce8123b910403bba 100% copying file sha256:077f51bc9eb56b50868cb95c7cf0d6d0f0a524b824ba3af8b248c78a46593e97 100% copying file sha256:e826381017b2d8a9d8704be34ee0e0ceeb0a3a9abca27beaa4555d370d5a4f10 100% copying file sha256:0f2ce0194b017ae009448602d7fd4ac24d7f25059c0a87d42fc496000f7bdacc 100% copying file sha256:95ef9768e4741543dbfaf0c274f101855883ff338b235c99eca2b6a4f4abee12 100% copying file sha256:f888421726665e8a84b738eed42a64875aed79de8be7daade851ac8bf4c0cef9 100% copying file sha256:b9c9eb63a8e03059914880f918cd28a880dec8b6e15e4461e1ff677e3743dbb8 100% copying file sha256:aa4b0afa70d26873dabc927e59b7dbc24a0e8eda323d4fdba17927d316d3516c 100% copying file sha256:3c43532c1b128f0135edc587ace540dfa53759916836960db06b73ab718e5eca 100% copying file sha256:605b29e86ec80aaa3a38bb3aab4bc859e4df26928fe49bbca00f127f55897e8d 100% converting model ```
GiteaMirror commented 2026-04-22 16:43:16 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 5, 2025):

Set GOMAXPROCS=1 in the server environment.

<!-- gh-comment-id:3490314775 --> @rick-github commented on GitHub (Nov 5, 2025): Set `GOMAXPROCS=1` in the [***server environment***](https://github.com/ollama/ollama/blob/main/docs/faq.mdx#setting-environment-variables-on-linux).
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#33745
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?