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 #9847] reload model error #6448

New Issue
Closed
opened 2026-04-12 18:00:24 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 18:00:24 -05:00
Owner
Copy Link

Originally created by @lajiyou9 on GitHub (Mar 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9847

What is the issue?

When I run the deepseek-r1:32b model and pass different context lengths through the model parameter, the model reloads and throws an error.
Q1：why reload?
Q2: why error? host pid is error! SET_TASK_PID FAILED.

Relevant log output

[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17274503168 total=25386352640 limit=25757220864 usage=7617930240
[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17689739264 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17689739264 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17092050944 total=25386352640 limit=25757220864 usage=7796343808
[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17689739264 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17243045888 total=25386352640 limit=25757220864 usage=7644955648
[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17689739264 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=17274503168 total=25386352640 limit=25757220864 usage=7617930240
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
time=2025-03-17T17:46:08.236+08:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.676611462 model=/root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648
[HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
time=2025-03-17T17:46:09.916+08:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=7.357191556 model=/root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb
[HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240
[HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808
[HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648
[HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
time=2025-03-17T17:46:11.704+08:00 level=INFO source=sched.go:730 msg="new model will fit in available VRAM, loading" model=/root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb library=cuda parallel=4 required="31.7 GiB"
[HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240
[HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808
[HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648
[HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
time=2025-03-17T17:46:13.214+08:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=10.654653934 model=/root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb
[HAMI-core Msg(1:140176256923392:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240
[HAMI-core Msg(1:140176256923392:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140176256923392:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140176256923392:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808
[HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
[HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648
[HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088
time=2025-03-17T17:46:14.792+08:00 level=INFO source=server.go:100 msg="system memory" total="503.3 GiB" free="474.4 GiB" free_swap="0 B"
time=2025-03-17T17:46:14.794+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=65 layers.offload=65 layers.split=10,10,9,9,9,9,9 memory.available="[17.3 GiB 17.3 GiB 17.3 GiB 17.3 GiB 16.9 GiB 16.9 GiB 16.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="31.7 GiB" memory.required.partial="31.7 GiB" memory.required.kv="2.0 GiB" memory.required.allocations="[4.7 GiB 5.0 GiB 4.4 GiB 4.4 GiB 4.4 GiB 4.4 GiB 4.4 GiB]" memory.weights.total="19.5 GiB" memory.weights.repeating="18.9 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="916.1 MiB" memory.graph.partial="916.1 MiB"
time=2025-03-17T17:46:14.794+08:00 level=INFO source=server.go:381 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb --ctx-size 8192 --batch-size 512 --n-gpu-layers 65 --threads 56 --parallel 4 --tensor-split 10,10,9,9,9,9,9 --port 45405"
time=2025-03-17T17:46:14.795+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-03-17T17:46:14.795+08:00 level=INFO source=server.go:558 msg="waiting for llama runner to start responding"
time=2025-03-17T17:46:14.796+08:00 level=INFO source=server.go:592 msg="waiting for server to become available" status="llm server error"
time=2025-03-17T17:46:14.847+08:00 level=INFO source=runner.go:936 msg="starting go runner"
time=2025-03-17T17:46:14.848+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=56
time=2025-03-17T17:46:14.848+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:45405"
[HAMI-core Msg(432:140668983752448:libvgpu.c:836)]: Initializing.....
[HAMI-core Warn(432:140668983752448:multiprocess_memory_limit.c:589)]: Kick dead proc 78
time=2025-03-17T17:46:15.048+08:00 level=INFO source=server.go:592 msg="waiting for server to become available" status="llm server loading model"
[HAMI-core ERROR (pid:432 thread=140668983752448 utils.c:146)]: host pid is error!
[HAMI-core Msg(432:140668983752448:libvgpu.c:855)]: Initialized
[HAMI-core Warn(432:140668983752448:libvgpu.c:857)]: SET_TASK_PID FAILED.
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 7 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes
  Device 1: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes
  Device 2: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes
  Device 3: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes
  Device 4: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes
  Device 5: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes
  Device 6: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes
load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v12/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so

OS

Docker

GPU

Nvidia

CPU

Intel

Ollama version

No response

Originally created by @lajiyou9 on GitHub (Mar 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9847 ### What is the issue? When I run the deepseek-r1:32b model and pass different context lengths through the model parameter, the model reloads and throws an error. Q1：why reload? Q2: why error? host pid is error! SET_TASK_PID FAILED. ### Relevant log output ```shell [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17274503168 total=25386352640 limit=25757220864 usage=7617930240 [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17689739264 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17689739264 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17092050944 total=25386352640 limit=25757220864 usage=7796343808 [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17689739264 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17243045888 total=25386352640 limit=25757220864 usage=7644955648 [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=17689739264 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=17274503168 total=25386352640 limit=25757220864 usage=7617930240 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 time=2025-03-17T17:46:08.236+08:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.676611462 model=/root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648 [HAMI-core Msg(1:140179091461888:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 time=2025-03-17T17:46:09.916+08:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=7.357191556 model=/root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb [HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240 [HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808 [HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648 [HAMI-core Msg(1:140178420778752:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 time=2025-03-17T17:46:11.704+08:00 level=INFO source=sched.go:730 msg="new model will fit in available VRAM, loading" model=/root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb library=cuda parallel=4 required="31.7 GiB" [HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240 [HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808 [HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648 [HAMI-core Msg(1:140178127021824:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 time=2025-03-17T17:46:13.214+08:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=10.654653934 model=/root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb [HAMI-core Msg(1:140176256923392:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7617930240 [HAMI-core Msg(1:140176256923392:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140176256923392:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140176256923392:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7796343808 [HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 [HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7644955648 [HAMI-core Msg(1:140176852510464:memory.c:511)]: orig free=25016664064 total=25386352640 limit=25757220864 usage=7198553088 time=2025-03-17T17:46:14.792+08:00 level=INFO source=server.go:100 msg="system memory" total="503.3 GiB" free="474.4 GiB" free_swap="0 B" time=2025-03-17T17:46:14.794+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=65 layers.offload=65 layers.split=10,10,9,9,9,9,9 memory.available="[17.3 GiB 17.3 GiB 17.3 GiB 17.3 GiB 16.9 GiB 16.9 GiB 16.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="31.7 GiB" memory.required.partial="31.7 GiB" memory.required.kv="2.0 GiB" memory.required.allocations="[4.7 GiB 5.0 GiB 4.4 GiB 4.4 GiB 4.4 GiB 4.4 GiB 4.4 GiB]" memory.weights.total="19.5 GiB" memory.weights.repeating="18.9 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="916.1 MiB" memory.graph.partial="916.1 MiB" time=2025-03-17T17:46:14.794+08:00 level=INFO source=server.go:381 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-c62ccde5630c20c8a9cf601861d31977d07450cad6dfdf1c661aab307107bddb --ctx-size 8192 --batch-size 512 --n-gpu-layers 65 --threads 56 --parallel 4 --tensor-split 10,10,9,9,9,9,9 --port 45405" time=2025-03-17T17:46:14.795+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-03-17T17:46:14.795+08:00 level=INFO source=server.go:558 msg="waiting for llama runner to start responding" time=2025-03-17T17:46:14.796+08:00 level=INFO source=server.go:592 msg="waiting for server to become available" status="llm server error" time=2025-03-17T17:46:14.847+08:00 level=INFO source=runner.go:936 msg="starting go runner" time=2025-03-17T17:46:14.848+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=56 time=2025-03-17T17:46:14.848+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:45405" [HAMI-core Msg(432:140668983752448:libvgpu.c:836)]: Initializing..... [HAMI-core Warn(432:140668983752448:multiprocess_memory_limit.c:589)]: Kick dead proc 78 time=2025-03-17T17:46:15.048+08:00 level=INFO source=server.go:592 msg="waiting for server to become available" status="llm server loading model" [HAMI-core ERROR (pid:432 thread=140668983752448 utils.c:146)]: host pid is error! [HAMI-core Msg(432:140668983752448:libvgpu.c:855)]: Initialized [HAMI-core Warn(432:140668983752448:libvgpu.c:857)]: SET_TASK_PID FAILED. ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 7 CUDA devices: Device 0: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes Device 1: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes Device 2: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes Device 3: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes Device 4: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes Device 5: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes Device 6: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v12/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so ``` ### OS Docker ### GPU Nvidia ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 18:00:24 -05:00
GiteaMirror commented 2026-04-12 18:00:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 18, 2025):

Q1：why reload?

A change in context size means a change in the processing environment so the model is reloaded.

Q2: why error? host pid is error! SET_TASK_PID FAILED.

HAMI-core is not part of ollama.

<!-- gh-comment-id:2731443857 --> @rick-github commented on GitHub (Mar 18, 2025): > Q1：why reload? A change in context size means a change in the processing environment so the model is reloaded. > Q2: why error? host pid is error! SET_TASK_PID FAILED. HAMI-core is not part of ollama.
GiteaMirror commented 2026-04-12 18:00:26 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 18, 2025):

I'm going to go ahead and close this as answered (thank you @rick-github !)

<!-- gh-comment-id:2734635661 --> @pdevine commented on GitHub (Mar 18, 2025): I'm going to go ahead and close this as answered (thank you @rick-github !)
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#6448
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?