github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-27 16:36:54 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

Vulkan not working on Linux (Ubuntu Server 25.10) #8413

New Issue
Open
opened 2025-11-12 14:41:17 -06:00 by GiteaMirror · 2 comments
GiteaMirror commented 2025-11-12 14:41:17 -06:00
Owner
Copy Link

Originally created by @rladinger on GitHub (Oct 17, 2025).

What is the issue?

The GPU detection crashes when starting Ollama. In my opinion, it doesn't even try to access Vulkan. Or does an environment variable still need to be set for Vulkan?

Relevant log output

2025-10-17T05:14:40.285508+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.283Z level=INFO source=routes.go:1511 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:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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_NEW_ENGINE: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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
2025-10-17T05:14:40.301116+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.301Z level=INFO source=images.go:522 msg="total blobs: 72"
2025-10-17T05:14:40.301759+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.301Z level=INFO source=images.go:529 msg="total unused blobs removed: 0"
2025-10-17T05:14:40.303793+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.303Z level=INFO source=routes.go:1564 msg="Listening on [::]:11434 (version 0.12.6)"
2025-10-17T05:14:40.307259+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.306Z level=INFO source=runner.go:80 msg="discovering available GPUs..."
2025-10-17T05:14:42.312826+00:00 ai ollama[3616]: time=2025-10-17T05:14:42.312Z level=INFO source=runner.go:545 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extra_envs="[GGML_CUDA_INIT=1 ROCR_VISIBLE_DEVICES=0]" error="runner crashed"
2025-10-17T05:14:42.312933+00:00 ai ollama[3616]: time=2025-10-17T05:14:42.312Z level=INFO source=types.go:129 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="57.5 GiB" available="52.9 GiB"
2025-10-17T05:14:42.312962+00:00 ai ollama[3616]: time=2025-10-17T05:14:42.312Z level=INFO source=routes.go:1605 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"

vulkaninfo --summary
'DISPLAY' environment variable not set... skipping surface info
error: XDG_RUNTIME_DIR is invalid or not set in the environment.
==========
VULKANINFO
==========

Vulkan Instance Version: 1.4.321


Instance Extensions: count = 24
-------------------------------
VK_EXT_acquire_drm_display             : extension revision 1
VK_EXT_acquire_xlib_display            : extension revision 1
VK_EXT_debug_report                    : extension revision 10
VK_EXT_debug_utils                     : extension revision 2
VK_EXT_direct_mode_display             : extension revision 1
VK_EXT_display_surface_counter         : extension revision 1
VK_EXT_headless_surface                : extension revision 1
VK_EXT_surface_maintenance1            : extension revision 1
VK_EXT_swapchain_colorspace            : extension revision 5
VK_KHR_device_group_creation           : extension revision 1
VK_KHR_display                         : extension revision 23
VK_KHR_external_fence_capabilities     : extension revision 1
VK_KHR_external_memory_capabilities    : extension revision 1
VK_KHR_external_semaphore_capabilities : extension revision 1
VK_KHR_get_display_properties2         : extension revision 1
VK_KHR_get_physical_device_properties2 : extension revision 2
VK_KHR_get_surface_capabilities2       : extension revision 1
VK_KHR_portability_enumeration         : extension revision 1
VK_KHR_surface                         : extension revision 25
VK_KHR_surface_protected_capabilities  : extension revision 1
VK_KHR_wayland_surface                 : extension revision 6
VK_KHR_xcb_surface                     : extension revision 6
VK_KHR_xlib_surface                    : extension revision 6
VK_LUNARG_direct_driver_loading        : extension revision 1

Instance Layers: count = 4
--------------------------
VK_LAYER_INTEL_nullhw       INTEL NULL HW                1.1.73   version 1
VK_LAYER_KHRONOS_validation Khronos Validation Layer     1.4.321  version 1
VK_LAYER_MESA_device_select Linux device selection layer 1.4.303  version 1
VK_LAYER_MESA_overlay       Mesa Overlay layer           1.4.303  version 1

Devices:
========
GPU0:
        apiVersion         = 1.4.318
        driverVersion      = 25.2.3
        vendorID           = 0x1002
        deviceID           = 0x150e
        deviceType         = PHYSICAL_DEVICE_TYPE_INTEGRATED_GPU
        deviceName         = AMD Radeon 890M Graphics (RADV GFX1150)
        driverID           = DRIVER_ID_MESA_RADV
        driverName         = radv
        driverInfo         = Mesa 25.2.3-1ubuntu1
        conformanceVersion = 1.4.0.0
        deviceUUID         = 00000000-c600-0000-0000-000000000000
        driverUUID         = 414d442d-4d45-5341-2d44-525600000000
GPU1:
        apiVersion         = 1.4.318
        driverVersion      = 25.2.3
        vendorID           = 0x10005
        deviceID           = 0x0000
        deviceType         = PHYSICAL_DEVICE_TYPE_CPU
        deviceName         = llvmpipe (LLVM 20.1.8, 256 bits)
        driverID           = DRIVER_ID_MESA_LLVMPIPE
        driverName         = llvmpipe
        driverInfo         = Mesa 25.2.3-1ubuntu1 (LLVM 20.1.8)
        conformanceVersion = 1.3.1.1
        deviceUUID         = 6d657361-3235-2e32-2e33-2d3175627500
        driverUUID         = 6c6c766d-7069-7065-5555-494400000000

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.12.6

Originally created by @rladinger on GitHub (Oct 17, 2025). ### What is the issue? The GPU detection crashes when starting Ollama. In my opinion, it doesn't even try to access Vulkan. Or does an environment variable still need to be set for Vulkan? ### Relevant log output ```shell 2025-10-17T05:14:40.285508+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.283Z level=INFO source=routes.go:1511 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:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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_NEW_ENGINE: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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" 2025-10-17T05:14:40.301116+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.301Z level=INFO source=images.go:522 msg="total blobs: 72" 2025-10-17T05:14:40.301759+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.301Z level=INFO source=images.go:529 msg="total unused blobs removed: 0" 2025-10-17T05:14:40.303793+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.303Z level=INFO source=routes.go:1564 msg="Listening on [::]:11434 (version 0.12.6)" 2025-10-17T05:14:40.307259+00:00 ai ollama[3616]: time=2025-10-17T05:14:40.306Z level=INFO source=runner.go:80 msg="discovering available GPUs..." 2025-10-17T05:14:42.312826+00:00 ai ollama[3616]: time=2025-10-17T05:14:42.312Z level=INFO source=runner.go:545 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extra_envs="[GGML_CUDA_INIT=1 ROCR_VISIBLE_DEVICES=0]" error="runner crashed" 2025-10-17T05:14:42.312933+00:00 ai ollama[3616]: time=2025-10-17T05:14:42.312Z level=INFO source=types.go:129 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="57.5 GiB" available="52.9 GiB" 2025-10-17T05:14:42.312962+00:00 ai ollama[3616]: time=2025-10-17T05:14:42.312Z level=INFO source=routes.go:1605 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" vulkaninfo --summary 'DISPLAY' environment variable not set... skipping surface info error: XDG_RUNTIME_DIR is invalid or not set in the environment. ========== VULKANINFO ========== Vulkan Instance Version: 1.4.321 Instance Extensions: count = 24 ------------------------------- VK_EXT_acquire_drm_display : extension revision 1 VK_EXT_acquire_xlib_display : extension revision 1 VK_EXT_debug_report : extension revision 10 VK_EXT_debug_utils : extension revision 2 VK_EXT_direct_mode_display : extension revision 1 VK_EXT_display_surface_counter : extension revision 1 VK_EXT_headless_surface : extension revision 1 VK_EXT_surface_maintenance1 : extension revision 1 VK_EXT_swapchain_colorspace : extension revision 5 VK_KHR_device_group_creation : extension revision 1 VK_KHR_display : extension revision 23 VK_KHR_external_fence_capabilities : extension revision 1 VK_KHR_external_memory_capabilities : extension revision 1 VK_KHR_external_semaphore_capabilities : extension revision 1 VK_KHR_get_display_properties2 : extension revision 1 VK_KHR_get_physical_device_properties2 : extension revision 2 VK_KHR_get_surface_capabilities2 : extension revision 1 VK_KHR_portability_enumeration : extension revision 1 VK_KHR_surface : extension revision 25 VK_KHR_surface_protected_capabilities : extension revision 1 VK_KHR_wayland_surface : extension revision 6 VK_KHR_xcb_surface : extension revision 6 VK_KHR_xlib_surface : extension revision 6 VK_LUNARG_direct_driver_loading : extension revision 1 Instance Layers: count = 4 -------------------------- VK_LAYER_INTEL_nullhw INTEL NULL HW 1.1.73 version 1 VK_LAYER_KHRONOS_validation Khronos Validation Layer 1.4.321 version 1 VK_LAYER_MESA_device_select Linux device selection layer 1.4.303 version 1 VK_LAYER_MESA_overlay Mesa Overlay layer 1.4.303 version 1 Devices: ======== GPU0: apiVersion = 1.4.318 driverVersion = 25.2.3 vendorID = 0x1002 deviceID = 0x150e deviceType = PHYSICAL_DEVICE_TYPE_INTEGRATED_GPU deviceName = AMD Radeon 890M Graphics (RADV GFX1150) driverID = DRIVER_ID_MESA_RADV driverName = radv driverInfo = Mesa 25.2.3-1ubuntu1 conformanceVersion = 1.4.0.0 deviceUUID = 00000000-c600-0000-0000-000000000000 driverUUID = 414d442d-4d45-5341-2d44-525600000000 GPU1: apiVersion = 1.4.318 driverVersion = 25.2.3 vendorID = 0x10005 deviceID = 0x0000 deviceType = PHYSICAL_DEVICE_TYPE_CPU deviceName = llvmpipe (LLVM 20.1.8, 256 bits) driverID = DRIVER_ID_MESA_LLVMPIPE driverName = llvmpipe driverInfo = Mesa 25.2.3-1ubuntu1 (LLVM 20.1.8) conformanceVersion = 1.3.1.1 deviceUUID = 6d657361-3235-2e32-2e33-2d3175627500 driverUUID = 6c6c766d-7069-7065-5555-494400000000 ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.12.6
GiteaMirror added the bug label 2025-11-12 14:41:17 -06:00
GiteaMirror commented 2025-11-12 14:41:18 -06:00
Author
Owner
Copy Link

@seboss666 commented on GitHub (Oct 18, 2025):

It's stated in the pull request about experimental support that it's not enabled by default. You need to compile ollama explicitly yourself to try it. I'm also having segfault on gpu detection for now (780M here), I hope it will be better handled in the near future, not fond of having to constantly manually compile too many things for AMD related stuff, when Nvidia ecosystem is so much easier to deal with.

@seboss666 commented on GitHub (Oct 18, 2025): It's stated [in the pull request](https://github.com/ollama/ollama/pull/5059) about experimental support that it's not enabled by default. You need to compile ollama explicitly yourself to try it. I'm also having segfault on gpu detection for now (780M here), I hope it will be better handled in the near future, not fond of having to constantly manually compile too many things for AMD related stuff, when Nvidia ecosystem is so much easier to deal with.
GiteaMirror commented 2025-11-12 14:41:18 -06:00
Author
Owner
Copy Link

@rladinger commented on GitHub (Oct 18, 2025):

I hope so too. I don't think NVIDIA is receiving preferential treatment, as AMD also has an increasing number of users. I am always happy to test either the new ROCm environment or VULKAN Ollama to see which ones support my GPUs or even NPUs.

@rladinger commented on GitHub (Oct 18, 2025): I hope so too. I don't think NVIDIA is receiving preferential treatment, as AMD also has an increasing number of users. I am always happy to test either the new ROCm environment or VULKAN Ollama to see which ones support my GPUs or even NPUs.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
client2
cloud
compatibility
context-length
create
docker
documentation
embeddings
engine
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
install
integration
intel
js
linux
macos
memory
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
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-ollama#8413
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?