github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14997] i cant use ollama on rx6600m #35398

New Issue
Closed
opened 2026-04-22 19:53:48 -05:00 by GiteaMirror · 16 comments
GiteaMirror commented 2026-04-22 19:53:48 -05:00
Owner
Copy Link

Originally created by @eineemail13059-source on GitHub (Mar 21, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14997

What is the issue?

Hi Ollama team,

please please please³ consider adding official support for the AMD Radeon RX 6600M.

I would really like to use Ollama with GPU acceleration on this card, especially on Linux. Official support would make Ollama much more useful for RX 6600M users.

Thank you for your work and for considering this GPU.

Relevant log output

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

No response

Originally created by @eineemail13059-source on GitHub (Mar 21, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14997 ### What is the issue? Hi Ollama team, please please please³ consider adding official support for the AMD Radeon RX 6600M. I would really like to use Ollama with GPU acceleration on this card, especially on Linux. Official support would make Ollama much more useful for RX 6600M users. Thank you for your work and for considering this GPU. ### Relevant log output ```shell ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 19:53:48 -05:00
GiteaMirror commented 2026-04-22 19:53:50 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 21, 2026):

Set HSA_OVERRIDE_GFX_VERSION=10.3.0 in the environment of the ollama server.

<!-- gh-comment-id:4103907409 --> @rick-github commented on GitHub (Mar 21, 2026): Set `HSA_OVERRIDE_GFX_VERSION=10.3.0` in the environment of the ollama server.
GiteaMirror commented 2026-04-22 19:53:51 -05:00
Author
Owner
Copy Link

@ganakee commented on GitHub (Mar 26, 2026):

I have a similar issue with the AMD6650. I have HSA_OVERRIDE_GFX_VERSION=10.3.0 set.
This started with v.18.0. Can fallback to 17.7.

Journalctrl reports:
Failure during GPU discovery OLLAMA_LIBRARY_PATH=/usr/lib/ollama/rocm

<!-- gh-comment-id:4136092321 --> @ganakee commented on GitHub (Mar 26, 2026): I have a similar issue with the AMD6650. I have HSA_OVERRIDE_GFX_VERSION=10.3.0 set. This started with v.18.0. Can fallback to 17.7. Journalctrl reports: Failure during GPU discovery OLLAMA_LIBRARY_PATH=/usr/lib/ollama/rocm
GiteaMirror commented 2026-04-22 19:53:51 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 26, 2026):

Server logs will aid in debugging.

<!-- gh-comment-id:4136133935 --> @rick-github commented on GitHub (Mar 26, 2026): [Server logs](https://docs.ollama.com/troubleshooting) will aid in debugging.
GiteaMirror commented 2026-04-22 19:53:51 -05:00
Author
Owner
Copy Link

@ganakee commented on GitHub (Mar 27, 2026):

I downloaded 0.16.4-rc0. The issue occurs with all 0.18.0+ versions, for me. (worked fine e.g., 0.17.7).

RTX6650 AMD GPU (see below)
ROCM 7.0.2 (this is the only 7 that will work, to the best of my knowledge, with my Linux distro and AMD Card).

JOURNCTRL

sudo journalctl -u ollama.service -n 100

Mar 27 12:22:55 OMEN systemd[1]: Stopping ollama.service - Ollama Service...
Mar 27 12:22:55 OMEN systemd[1]: ollama.service: Deactivated successfully.
Mar 27 12:22:55 OMEN systemd[1]: Stopped ollama.service - Ollama Service.
Mar 27 12:22:55 OMEN systemd[1]: ollama.service: Consumed 1.020s CPU time, 310M memory peak.
Mar 27 12:23:01 OMEN systemd[1]: Started ollama.service - Ollama Service.
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.892-04:00 level=INFO source=routes.go:1740 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVI>
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.892-04:00 level=INFO source=routes.go:1742 msg="Ollama cloud disabled: false"
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.894-04:00 level=INFO source=images.go:477 msg="total blobs: 33"
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=INFO source=routes.go:1798 msg="Listening on [::]:11434 (version 0.18.4-rc0)"
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=WARN source=runner.go:485 msg="user overrode visible devices" HSA_OVERRIDE_GFX_VERSION=10.3.0
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again"
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN>
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.896-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port>
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.924-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port>
Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.953-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port>
Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.062-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port>
Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.062-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port>
Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.263-04:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama>
Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.284-04:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama>
Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.284-04:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description>
Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.284-04:00 level=INFO source=routes.go:1848 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
Mar 27 12:23:08 OMEN ollama[12363]: [GIN] 2026/03/27 - 12:23:08 | 200 |      49.032µs |       127.0.0.1 | GET      "/api/version"

rocminfo

rocminfo
ROCk module is loaded
=====================    
HSA System Attributes    
=====================    
Runtime Version:         1.18
Runtime Ext Version:     1.11
System Timestamp Freq.:  1000.000000MHz
Sig. Max Wait Duration:  18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model:           LARGE                              
System Endianness:       LITTLE                             
Mwaitx:                  DISABLED
XNACK enabled:           NO
DMAbuf Support:          YES
VMM Support:             YES

==========               
HSA Agents               
==========               
*******                  
Agent 1                  
*******                  
  Name:                    AMD Ryzen 7 6800H with Radeon Graphics
  Uuid:                    CPU-XX                             
  Marketing Name:          AMD Ryzen 7 6800H with Radeon Graphics
  Vendor Name:             CPU                                
  Feature:                 None specified                     
  Profile:                 FULL_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        0(0x0)                             
  Queue Min Size:          0(0x0)                             
  Queue Max Size:          0(0x0)                             
  Queue Type:              MULTI                              
  Node:                    0                                  
  Device Type:             CPU                                
  Cache Info:              
    L1:                      32768(0x8000) KB                   
  Chip ID:                 0(0x0)                             
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   4787                               
  BDFID:                   0                                  
  Internal Node ID:        0                                  
  Compute Unit:            16                                 
  SIMDs per CU:            0                                  
  Shader Engines:          0                                  
  Shader Arrs. per Eng.:   0                                  
  WatchPts on Addr. Ranges:1                                  
  Memory Properties:       
  Features:                None
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: FINE GRAINED        
      Size:                    31514836(0x1e0e0d4) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    31514836(0x1e0e0d4) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 3                   
      Segment:                 GLOBAL; FLAGS: KERNARG, FINE GRAINED
      Size:                    31514836(0x1e0e0d4) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 4                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    31514836(0x1e0e0d4) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
  ISA Info:                
*******                  
Agent 2                  
*******                  
  Name:                    gfx1030                            
  Uuid:                    GPU-XX                             
  Marketing Name:          AMD Radeon RX 6650M                
  Vendor Name:             AMD                                
  Feature:                 KERNEL_DISPATCH                    
  Profile:                 BASE_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        128(0x80)                          
  Queue Min Size:          64(0x40)                           
  Queue Max Size:          131072(0x20000)                    
  Queue Type:              MULTI                              
  Node:                    1                                  
  Device Type:             GPU                                
  Cache Info:              
    L1:                      16(0x10) KB                        
    L2:                      2048(0x800) KB                     
    L3:                      32768(0x8000) KB                   
  Chip ID:                 29679(0x73ef)                      
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          128(0x80)                          
  Max Clock Freq. (MHz):   2625                               
  BDFID:                   768                                
  Internal Node ID:        1                                  
  Compute Unit:            28                                 
  SIMDs per CU:            2                                  
  Shader Engines:          2                                  
  Shader Arrs. per Eng.:   2                                  
  WatchPts on Addr. Ranges:4                                  
  Coherent Host Access:    FALSE                              
  Memory Properties:       
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      TRUE                               
  Wavefront Size:          32(0x20)                           
  Workgroup Max Size:      1024(0x400)                        
  Workgroup Max Size per Dimension:
    x                        1024(0x400)                        
    y                        1024(0x400)                        
    z                        1024(0x400)                        
  Max Waves Per CU:        32(0x20)                           
  Max Work-item Per CU:    1024(0x400)                        
  Grid Max Size:           4294967295(0xffffffff)             
  Grid Max Size per Dimension:
    x                        2147483647(0x7fffffff)             
    y                        65535(0xffff)                      
    z                        65535(0xffff)                      
  Max fbarriers/Workgrp:   32                                 
  Packet Processor uCode:: 131                                
  SDMA engine uCode::      76                                 
  IOMMU Support::          None                               
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    8372224(0x7fc000) KB               
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    8372224(0x7fc000) KB               
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 3                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Recommended Granule:0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1030         
      Machine Models:          HSA_MACHINE_MODEL_LARGE            
      Profiles:                HSA_PROFILE_BASE                   
      Default Rounding Mode:   NEAR                               
      Default Rounding Mode:   NEAR                               
      Fast f16:                TRUE                               
      Workgroup Max Size:      1024(0x400)                        
      Workgroup Max Size per Dimension:
        x                        1024(0x400)                        
        y                        1024(0x400)                        
        z                        1024(0x400)                        
      Grid Max Size:           4294967295(0xffffffff)             
      Grid Max Size per Dimension:
        x                        2147483647(0x7fffffff)             
        y                        65535(0xffff)                      
        z                        65535(0xffff)                      
      FBarrier Max Size:       32                                 
    ISA 2                    
      Name:                    amdgcn-amd-amdhsa--gfx10-3-generic 
      Machine Models:          HSA_MACHINE_MODEL_LARGE            
      Profiles:                HSA_PROFILE_BASE                   
      Default Rounding Mode:   NEAR                               
      Default Rounding Mode:   NEAR                               
      Fast f16:                TRUE                               
      Workgroup Max Size:      1024(0x400)                        
      Workgroup Max Size per Dimension:
        x                        1024(0x400)                        
        y                        1024(0x400)                        
        z                        1024(0x400)                        
      Grid Max Size:           4294967295(0xffffffff)             
      Grid Max Size per Dimension:
        x                        2147483647(0x7fffffff)             
        y                        65535(0xffff)                      
        z                        65535(0xffff)                      
      FBarrier Max Size:       32                                 
*******                  
Agent 3                  
*******                  
  Name:                    gfx1030                            
  Uuid:                    GPU-XX                             
  Marketing Name:          AMD Radeon Graphics                
  Vendor Name:             AMD                                
  Feature:                 KERNEL_DISPATCH                    
  Profile:                 BASE_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        128(0x80)                          
  Queue Min Size:          64(0x40)                           
  Queue Max Size:          131072(0x20000)                    
  Queue Type:              MULTI                              
  Node:                    2                                  
  Device Type:             GPU                                
  Cache Info:              
    L1:                      16(0x10) KB                        
    L2:                      2048(0x800) KB                     
  Chip ID:                 5761(0x1681)                       
  ASIC Revision:           2(0x2)                             
  Cacheline Size:          128(0x80)                          
  Max Clock Freq. (MHz):   2200                               
  BDFID:                   2304                               
  Internal Node ID:        2                                  
  Compute Unit:            12                                 
  SIMDs per CU:            2                                  
  Shader Engines:          1                                  
  Shader Arrs. per Eng.:   2                                  
  WatchPts on Addr. Ranges:4                                  
  Coherent Host Access:    FALSE                              
  Memory Properties:       APU
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      TRUE                               
  Wavefront Size:          32(0x20)                           
  Workgroup Max Size:      1024(0x400)                        
  Workgroup Max Size per Dimension:
    x                        1024(0x400)                        
    y                        1024(0x400)                        
    z                        1024(0x400)                        
  Max Waves Per CU:        32(0x20)                           
  Max Work-item Per CU:    1024(0x400)                        
  Grid Max Size:           4294967295(0xffffffff)             
  Grid Max Size per Dimension:
    x                        2147483647(0x7fffffff)             
    y                        65535(0xffff)                      
    z                        65535(0xffff)                      
  Max fbarriers/Workgrp:   32                                 
  Packet Processor uCode:: 131                                
  SDMA engine uCode::      47                                 
  IOMMU Support::          None                               
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    15757416(0xf07068) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    15757416(0xf07068) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 3                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Recommended Granule:0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1030         
      Machine Models:          HSA_MACHINE_MODEL_LARGE            
      Profiles:                HSA_PROFILE_BASE                   
      Default Rounding Mode:   NEAR                               
      Default Rounding Mode:   NEAR                               
      Fast f16:                TRUE                               
      Workgroup Max Size:      1024(0x400)                        
      Workgroup Max Size per Dimension:
        x                        1024(0x400)                        
        y                        1024(0x400)                        
        z                        1024(0x400)                        
      Grid Max Size:           4294967295(0xffffffff)             
      Grid Max Size per Dimension:
        x                        2147483647(0x7fffffff)             
        y                        65535(0xffff)                      
        z                        65535(0xffff)                      
      FBarrier Max Size:       32                                 
    ISA 2                    
      Name:                    amdgcn-amd-amdhsa--gfx10-3-generic 
      Machine Models:          HSA_MACHINE_MODEL_LARGE            
      Profiles:                HSA_PROFILE_BASE                   
      Default Rounding Mode:   NEAR                               
      Default Rounding Mode:   NEAR                               
      Fast f16:                TRUE                               
      Workgroup Max Size:      1024(0x400)                        
      Workgroup Max Size per Dimension:
        x                        1024(0x400)                        
        y                        1024(0x400)                        
        z                        1024(0x400)                        
      Grid Max Size:           4294967295(0xffffffff)             
      Grid Max Size per Dimension:
        x                        2147483647(0x7fffffff)             
        y                        65535(0xffff)                      
        z                        65535(0xffff)                      
      FBarrier Max Size:       32                                 
*** Done ***

SystemD Config

/etc/systemd/system$ cat ./ollama.service 
[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=/usr/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=$PATH"
Environment="OLLAMA_HOST=0.0.0.0"
#Environment="CUDA_VISIBLE_DEVICES=1"
# REMOVED 2025-11-13 Environment="ROCR_VISIBLE_DEVICES=2,3,1,0"
#Environment="ROCR_VISIBLE_DEVICES=1,0"
Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"
#Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"
# REMOVED 2025-11-13 Environment="OLLAMA_DEBUG=2"
#Environment="OLLAMA_DEBUG=1" #ORIGINAL

[Install]
WantedBy=multi-user.target

#[Service]
#Environment="OLLAMA_HOST=0.0.0.0:11434"
<!-- gh-comment-id:4143803376 --> @ganakee commented on GitHub (Mar 27, 2026): I downloaded 0.16.4-rc0. The issue occurs with all 0.18.0+ versions, for me. (worked fine e.g., 0.17.7). RTX6650 AMD GPU (see below) ROCM 7.0.2 (this is the only 7 that will work, to the best of my knowledge, with my Linux distro and AMD Card). ## JOURNCTRL `sudo journalctl -u ollama.service -n 100` ``` Mar 27 12:22:55 OMEN systemd[1]: Stopping ollama.service - Ollama Service... Mar 27 12:22:55 OMEN systemd[1]: ollama.service: Deactivated successfully. Mar 27 12:22:55 OMEN systemd[1]: Stopped ollama.service - Ollama Service. Mar 27 12:22:55 OMEN systemd[1]: ollama.service: Consumed 1.020s CPU time, 310M memory peak. Mar 27 12:23:01 OMEN systemd[1]: Started ollama.service - Ollama Service. Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.892-04:00 level=INFO source=routes.go:1740 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVI> Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.892-04:00 level=INFO source=routes.go:1742 msg="Ollama cloud disabled: false" Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.894-04:00 level=INFO source=images.go:477 msg="total blobs: 33" Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0" Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=INFO source=routes.go:1798 msg="Listening on [::]:11434 (version 0.18.4-rc0)" Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=WARN source=runner.go:485 msg="user overrode visible devices" HSA_OVERRIDE_GFX_VERSION=10.3.0 Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again" Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.895-04:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN> Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.896-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port> Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.924-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port> Mar 27 12:23:01 OMEN ollama[12363]: time=2026-03-27T12:23:01.953-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port> Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.062-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port> Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.062-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port> Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.263-04:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama> Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.284-04:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama> Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.284-04:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description> Mar 27 12:23:02 OMEN ollama[12363]: time=2026-03-27T12:23:02.284-04:00 level=INFO source=routes.go:1848 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096 Mar 27 12:23:08 OMEN ollama[12363]: [GIN] 2026/03/27 - 12:23:08 | 200 | 49.032µs | 127.0.0.1 | GET "/api/version" ``` ## rocminfo ``` rocminfo ROCk module is loaded ===================== HSA System Attributes ===================== Runtime Version: 1.18 Runtime Ext Version: 1.11 System Timestamp Freq.: 1000.000000MHz Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count) Machine Model: LARGE System Endianness: LITTLE Mwaitx: DISABLED XNACK enabled: NO DMAbuf Support: YES VMM Support: YES ========== HSA Agents ========== ******* Agent 1 ******* Name: AMD Ryzen 7 6800H with Radeon Graphics Uuid: CPU-XX Marketing Name: AMD Ryzen 7 6800H with Radeon Graphics Vendor Name: CPU Feature: None specified Profile: FULL_PROFILE Float Round Mode: NEAR Max Queue Number: 0(0x0) Queue Min Size: 0(0x0) Queue Max Size: 0(0x0) Queue Type: MULTI Node: 0 Device Type: CPU Cache Info: L1: 32768(0x8000) KB Chip ID: 0(0x0) ASIC Revision: 0(0x0) Cacheline Size: 64(0x40) Max Clock Freq. (MHz): 4787 BDFID: 0 Internal Node ID: 0 Compute Unit: 16 SIMDs per CU: 0 Shader Engines: 0 Shader Arrs. per Eng.: 0 WatchPts on Addr. Ranges:1 Memory Properties: Features: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: FINE GRAINED Size: 31514836(0x1e0e0d4) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 2 Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 31514836(0x1e0e0d4) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 3 Segment: GLOBAL; FLAGS: KERNARG, FINE GRAINED Size: 31514836(0x1e0e0d4) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 4 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 31514836(0x1e0e0d4) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE ISA Info: ******* Agent 2 ******* Name: gfx1030 Uuid: GPU-XX Marketing Name: AMD Radeon RX 6650M Vendor Name: AMD Feature: KERNEL_DISPATCH Profile: BASE_PROFILE Float Round Mode: NEAR Max Queue Number: 128(0x80) Queue Min Size: 64(0x40) Queue Max Size: 131072(0x20000) Queue Type: MULTI Node: 1 Device Type: GPU Cache Info: L1: 16(0x10) KB L2: 2048(0x800) KB L3: 32768(0x8000) KB Chip ID: 29679(0x73ef) ASIC Revision: 0(0x0) Cacheline Size: 128(0x80) Max Clock Freq. (MHz): 2625 BDFID: 768 Internal Node ID: 1 Compute Unit: 28 SIMDs per CU: 2 Shader Engines: 2 Shader Arrs. per Eng.: 2 WatchPts on Addr. Ranges:4 Coherent Host Access: FALSE Memory Properties: Features: KERNEL_DISPATCH Fast F16 Operation: TRUE Wavefront Size: 32(0x20) Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Max Waves Per CU: 32(0x20) Max Work-item Per CU: 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) Max fbarriers/Workgrp: 32 Packet Processor uCode:: 131 SDMA engine uCode:: 76 IOMMU Support:: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 8372224(0x7fc000) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:2048KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 2 Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 8372224(0x7fc000) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:2048KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 3 Segment: GROUP Size: 64(0x40) KB Allocatable: FALSE Alloc Granule: 0KB Alloc Recommended Granule:0KB Alloc Alignment: 0KB Accessible by all: FALSE ISA Info: ISA 1 Name: amdgcn-amd-amdhsa--gfx1030 Machine Models: HSA_MACHINE_MODEL_LARGE Profiles: HSA_PROFILE_BASE Default Rounding Mode: NEAR Default Rounding Mode: NEAR Fast f16: TRUE Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) FBarrier Max Size: 32 ISA 2 Name: amdgcn-amd-amdhsa--gfx10-3-generic Machine Models: HSA_MACHINE_MODEL_LARGE Profiles: HSA_PROFILE_BASE Default Rounding Mode: NEAR Default Rounding Mode: NEAR Fast f16: TRUE Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) FBarrier Max Size: 32 ******* Agent 3 ******* Name: gfx1030 Uuid: GPU-XX Marketing Name: AMD Radeon Graphics Vendor Name: AMD Feature: KERNEL_DISPATCH Profile: BASE_PROFILE Float Round Mode: NEAR Max Queue Number: 128(0x80) Queue Min Size: 64(0x40) Queue Max Size: 131072(0x20000) Queue Type: MULTI Node: 2 Device Type: GPU Cache Info: L1: 16(0x10) KB L2: 2048(0x800) KB Chip ID: 5761(0x1681) ASIC Revision: 2(0x2) Cacheline Size: 128(0x80) Max Clock Freq. (MHz): 2200 BDFID: 2304 Internal Node ID: 2 Compute Unit: 12 SIMDs per CU: 2 Shader Engines: 1 Shader Arrs. per Eng.: 2 WatchPts on Addr. Ranges:4 Coherent Host Access: FALSE Memory Properties: APU Features: KERNEL_DISPATCH Fast F16 Operation: TRUE Wavefront Size: 32(0x20) Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Max Waves Per CU: 32(0x20) Max Work-item Per CU: 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) Max fbarriers/Workgrp: 32 Packet Processor uCode:: 131 SDMA engine uCode:: 47 IOMMU Support:: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 15757416(0xf07068) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:2048KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 2 Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 15757416(0xf07068) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:2048KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 3 Segment: GROUP Size: 64(0x40) KB Allocatable: FALSE Alloc Granule: 0KB Alloc Recommended Granule:0KB Alloc Alignment: 0KB Accessible by all: FALSE ISA Info: ISA 1 Name: amdgcn-amd-amdhsa--gfx1030 Machine Models: HSA_MACHINE_MODEL_LARGE Profiles: HSA_PROFILE_BASE Default Rounding Mode: NEAR Default Rounding Mode: NEAR Fast f16: TRUE Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) FBarrier Max Size: 32 ISA 2 Name: amdgcn-amd-amdhsa--gfx10-3-generic Machine Models: HSA_MACHINE_MODEL_LARGE Profiles: HSA_PROFILE_BASE Default Rounding Mode: NEAR Default Rounding Mode: NEAR Fast f16: TRUE Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) FBarrier Max Size: 32 *** Done *** ``` ## SystemD Config ``` /etc/systemd/system$ cat ./ollama.service [Unit] Description=Ollama Service After=network-online.target [Service] ExecStart=/usr/bin/ollama serve User=ollama Group=ollama Restart=always RestartSec=3 Environment="PATH=$PATH" Environment="OLLAMA_HOST=0.0.0.0" #Environment="CUDA_VISIBLE_DEVICES=1" # REMOVED 2025-11-13 Environment="ROCR_VISIBLE_DEVICES=2,3,1,0" #Environment="ROCR_VISIBLE_DEVICES=1,0" Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0" #Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0" # REMOVED 2025-11-13 Environment="OLLAMA_DEBUG=2" #Environment="OLLAMA_DEBUG=1" #ORIGINAL [Install] WantedBy=multi-user.target #[Service] #Environment="OLLAMA_HOST=0.0.0.0:11434" ```
GiteaMirror commented 2026-04-22 19:53:52 -05:00
Author
Owner
Copy Link

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

Set OLLAMA_DEBUG=2 in the server environment, restart the server, and post the output of

journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)"
<!-- gh-comment-id:4143834728 --> @rick-github commented on GitHub (Mar 27, 2026): Set `OLLAMA_DEBUG=2` in the server environment, restart the server, and post the output of ``` journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" ```
GiteaMirror commented 2026-04-22 19:53:52 -05:00
Author
Owner
Copy Link

@ganakee commented on GitHub (Mar 27, 2026):

Thanks @rick-github

journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)"
Mar 27 13:00:37 OMEN systemd[1]: Stopping ollama.service - Ollama Service...
Mar 27 13:00:37 OMEN systemd[1]: ollama.service: Deactivated successfully.
Mar 27 13:00:37 OMEN systemd[1]: Stopped ollama.service - Ollama Service.
Mar 27 13:00:37 OMEN systemd[1]: ollama.service: Consumed 714ms CPU time, 88.4M memory peak.
Mar 27 13:00:37 OMEN systemd[1]: Started ollama.service - Ollama Service.
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.853-04:00 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:10.3.0 HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:DEBUG-4 OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:/usr/share/ollama/.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:]"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.853-04:00 level=INFO source=routes.go:1742 msg="Ollama cloud disabled: false"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.854-04:00 level=INFO source=images.go:477 msg="total blobs: 33"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=INFO source=routes.go:1798 msg="Listening on [::]:11434 (version 0.18.4-rc0)"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=DEBUG source=sched.go:145 msg="starting llm scheduler"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=WARN source=runner.go:485 msg="user overrode visible devices" HSA_OVERRIDE_GFX_VERSION=10.3.0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/cuda_v12]" extraEnvs=map[]
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.856-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 34235"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.856-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v12 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v12
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.869-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.870-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:34235"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama
Mar 27 13:00:37 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/cuda_v12
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default=""
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=6.478425ms
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=531ns
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v12]" devices=[]
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=28.623126ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v12]" extra_envs=map[]
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extraEnvs=map[]
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 39755"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.898-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.899-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:39755"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama
Mar 27 13:00:37 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/cuda_v13
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default=""
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=6.292968ms
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=440ns
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" devices=[]
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=27.510818ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extra_envs=map[]
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/rocm]" extraEnvs=map[]
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.912-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36387"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.912-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.925-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.925-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:36387"
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.935-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.935-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.935-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.935-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected
Mar 27 13:00:40 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.214-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/rocm
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: found 2 ROCm devices:
Mar 27 13:00:40 OMEN ollama[19869]:   Device 0: AMD Radeon RX 6650M, gfx1030 (0x1030), VMM: no, Wave Size: 32, ID: 0
Mar 27 13:00:40 OMEN ollama[19869]:   Device 1: AMD Radeon 680M, gfx1030 (0x1030), VMM: no, Wave Size: 32, ID: 1
Mar 27 13:00:40 OMEN ollama[19869]: load_backend: loaded ROCm backend from /usr/lib/ollama/rocm/libggml-hip.so
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 ROCm.1.NO_VMM=1 ROCm.1.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default=""
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=2.284129072s
Mar 27 13:00:40 OMEN ollama[19869]: ggml_hip_get_device_memory searching for device 0000:03:00.0
Mar 27 13:00:40 OMEN ollama[19869]: ggml_backend_cuda_device_get_memory device 0000:03:00.0 utilizing AMD specific memory reporting free: 8556400640 total: 8573157376
Mar 27 13:00:40 OMEN ollama[19869]: ggml_hip_get_device_memory searching for device 0000:09:00.0
Mar 27 13:00:40 OMEN ollama[19869]: ggml_backend_cuda_device_get_memory device 0000:09:00.0 utilizing AMD specific memory reporting free: 15851724800 total: 16672464896
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=900.55µs
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" devices="[{DeviceID:{ID:0 Library:ROCm} Name:ROCm0 Description:AMD Radeon RX 6650M FilterID: Integrated:false PCIID:0000:03:00.0 TotalMemory:8573157376 FreeMemory:8556400640 ComputeMajor:16 ComputeMinor:48 DriverMajor:70226 DriverMinor:1 LibraryPath:[/usr/lib/ollama /usr/lib/ollama/rocm]} {DeviceID:{ID:1 Library:ROCm} Name:ROCm1 Description:AMD Radeon 680M FilterID: Integrated:true PCIID:0000:09:00.0 TotalMemory:16672464896 FreeMemory:15851724800 ComputeMajor:16 ComputeMinor:48 DriverMajor:70226 DriverMinor:1 LibraryPath:[/usr/lib/ollama /usr/lib/ollama/rocm]}]"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=2.30775423s OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs=map[]
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=2
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=/usr/lib/ollama/rocm description="AMD Radeon RX 6650M" compute=gfx1030 id=0 pci_id=0000:03:00.0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=/usr/lib/ollama/rocm description="AMD Radeon 680M" compute=gfx1030 id=1 pci_id=0000:09:00.0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/rocm]" extraEnvs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:1]"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/rocm]" extraEnvs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42573"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.220-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm GGML_CUDA_INIT=1 ROCR_VISIBLE_DEVICES=1
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.220-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 46015"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.220-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm ROCR_VISIBLE_DEVICES=0 GGML_CUDA_INIT=1
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.233-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.233-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:42573"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.234-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.234-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:46015"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.242-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.242-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.242-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected
Mar 27 13:00:40 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.323-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/rocm
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: found 1 ROCm devices:
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: initializing rocBLAS on device 0
Mar 27 13:00:40 OMEN ollama[19869]: rocBLAS error: Could not initialize Tensile host: No devices found
Mar 27 13:00:40 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.334-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/rocm
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: found 1 ROCm devices:
Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: initializing rocBLAS on device 0
Mar 27 13:00:40 OMEN ollama[19869]: rocBLAS error: Could not initialize Tensile host: No devices found
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.431-04:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]" error="runner crashed"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.431-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" devices=[]
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.431-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=211.558077ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.431-04:00 level=DEBUG source=runner.go:153 msg="filtering device which didn't fully initialize" id=0 libdir=/usr/lib/ollama/rocm pci_id=0000:03:00.0 library=ROCm
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:1]" error="runner crashed"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" devices=[]
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=221.427075ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:1]"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=DEBUG source=runner.go:153 msg="filtering device which didn't fully initialize" id=1 libdir=/usr/lib/ollama/rocm pci_id=0000:09:00.0 library=ROCm
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[]
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=TRACE source=runner.go:183 msg="removing unsupported or overlapping GPU combination" libDir=/usr/lib/ollama/rocm description="AMD Radeon RX 6650M" compute=gfx1030 pci_id=0000:03:00.0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=TRACE source=runner.go:183 msg="removing unsupported or overlapping GPU combination" libDir=/usr/lib/ollama/rocm description="AMD Radeon 680M" compute=gfx1030 pci_id=0000:09:00.0
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=2.585911217s
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 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="30.1 GiB" available="25.4 GiB"
Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=INFO source=routes.go:1848 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
shannon@OMEN:/etc/systemd/system$
<!-- gh-comment-id:4144008632 --> @ganakee commented on GitHub (Mar 27, 2026): Thanks @rick-github ``` journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" Mar 27 13:00:37 OMEN systemd[1]: Stopping ollama.service - Ollama Service... Mar 27 13:00:37 OMEN systemd[1]: ollama.service: Deactivated successfully. Mar 27 13:00:37 OMEN systemd[1]: Stopped ollama.service - Ollama Service. Mar 27 13:00:37 OMEN systemd[1]: ollama.service: Consumed 714ms CPU time, 88.4M memory peak. Mar 27 13:00:37 OMEN systemd[1]: Started ollama.service - Ollama Service. Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.853-04:00 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:10.3.0 HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:DEBUG-4 OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:/usr/share/ollama/.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:]" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.853-04:00 level=INFO source=routes.go:1742 msg="Ollama cloud disabled: false" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.854-04:00 level=INFO source=images.go:477 msg="total blobs: 33" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=INFO source=routes.go:1798 msg="Listening on [::]:11434 (version 0.18.4-rc0)" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=DEBUG source=sched.go:145 msg="starting llm scheduler" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=WARN source=runner.go:485 msg="user overrode visible devices" HSA_OVERRIDE_GFX_VERSION=10.3.0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.855-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/cuda_v12]" extraEnvs=map[] Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.856-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 34235" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.856-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v12 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v12 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.869-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.870-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:34235" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.877-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama Mar 27 13:00:37 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/cuda_v12 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.883-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default="" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=6.478425ms Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=531ns Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v12]" devices=[] Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=28.623126ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v12]" extra_envs=map[] Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extraEnvs=map[] Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 39755" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.884-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.898-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.899-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:39755" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.905-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama Mar 27 13:00:37 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/cuda_v13 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default="" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=6.292968ms Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=440ns Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" devices=[] Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=27.510818ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extra_envs=map[] Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.911-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/rocm]" extraEnvs=map[] Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.912-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36387" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.912-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.925-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.925-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:36387" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.934-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.935-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.935-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.935-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 27 13:00:37 OMEN ollama[19869]: time=2026-03-27T13:00:37.935-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected Mar 27 13:00:40 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.214-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/rocm Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: found 2 ROCm devices: Mar 27 13:00:40 OMEN ollama[19869]: Device 0: AMD Radeon RX 6650M, gfx1030 (0x1030), VMM: no, Wave Size: 32, ID: 0 Mar 27 13:00:40 OMEN ollama[19869]: Device 1: AMD Radeon 680M, gfx1030 (0x1030), VMM: no, Wave Size: 32, ID: 1 Mar 27 13:00:40 OMEN ollama[19869]: load_backend: loaded ROCm backend from /usr/lib/ollama/rocm/libggml-hip.so Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 ROCm.1.NO_VMM=1 ROCm.1.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default="" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.218-04:00 level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=2.284129072s Mar 27 13:00:40 OMEN ollama[19869]: ggml_hip_get_device_memory searching for device 0000:03:00.0 Mar 27 13:00:40 OMEN ollama[19869]: ggml_backend_cuda_device_get_memory device 0000:03:00.0 utilizing AMD specific memory reporting free: 8556400640 total: 8573157376 Mar 27 13:00:40 OMEN ollama[19869]: ggml_hip_get_device_memory searching for device 0000:09:00.0 Mar 27 13:00:40 OMEN ollama[19869]: ggml_backend_cuda_device_get_memory device 0000:09:00.0 utilizing AMD specific memory reporting free: 15851724800 total: 16672464896 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=900.55µs Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" devices="[{DeviceID:{ID:0 Library:ROCm} Name:ROCm0 Description:AMD Radeon RX 6650M FilterID: Integrated:false PCIID:0000:03:00.0 TotalMemory:8573157376 FreeMemory:8556400640 ComputeMajor:16 ComputeMinor:48 DriverMajor:70226 DriverMinor:1 LibraryPath:[/usr/lib/ollama /usr/lib/ollama/rocm]} {DeviceID:{ID:1 Library:ROCm} Name:ROCm1 Description:AMD Radeon 680M FilterID: Integrated:true PCIID:0000:09:00.0 TotalMemory:16672464896 FreeMemory:15851724800 ComputeMajor:16 ComputeMinor:48 DriverMajor:70226 DriverMinor:1 LibraryPath:[/usr/lib/ollama /usr/lib/ollama/rocm]}]" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=2.30775423s OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs=map[] Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=2 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=/usr/lib/ollama/rocm description="AMD Radeon RX 6650M" compute=gfx1030 id=0 pci_id=0000:03:00.0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=DEBUG source=runner.go:146 msg="verifying if device is supported" library=/usr/lib/ollama/rocm description="AMD Radeon 680M" compute=gfx1030 id=1 pci_id=0000:09:00.0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/rocm]" extraEnvs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:1]" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/lib/ollama /usr/lib/ollama/rocm]" extraEnvs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.219-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42573" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.220-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm GGML_CUDA_INIT=1 ROCR_VISIBLE_DEVICES=1 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.220-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 46015" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.220-04:00 level=DEBUG source=server.go:433 msg=subprocess PATH=$PATH OLLAMA_HOST=0.0.0.0 HSA_OVERRIDE_GFX_VERSION=10.3.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/rocm ROCR_VISIBLE_DEVICES=0 GGML_CUDA_INIT=1 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.233-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.233-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:42573" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.234-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.234-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:46015" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.241-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.242-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.242-04:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.242-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected Mar 27 13:00:40 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.323-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/rocm Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: found 1 ROCm devices: Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: initializing rocBLAS on device 0 Mar 27 13:00:40 OMEN ollama[19869]: rocBLAS error: Could not initialize Tensile host: No devices found Mar 27 13:00:40 OMEN ollama[19869]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.334-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/rocm Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: found 1 ROCm devices: Mar 27 13:00:40 OMEN ollama[19869]: ggml_cuda_init: initializing rocBLAS on device 0 Mar 27 13:00:40 OMEN ollama[19869]: rocBLAS error: Could not initialize Tensile host: No devices found Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.431-04:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]" error="runner crashed" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.431-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" devices=[] Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.431-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=211.558077ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.431-04:00 level=DEBUG source=runner.go:153 msg="filtering device which didn't fully initialize" id=0 libdir=/usr/lib/ollama/rocm pci_id=0000:03:00.0 library=ROCm Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:1]" error="runner crashed" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" devices=[] Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=221.427075ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:1]" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=DEBUG source=runner.go:153 msg="filtering device which didn't fully initialize" id=1 libdir=/usr/lib/ollama/rocm pci_id=0000:09:00.0 library=ROCm Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[] Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=TRACE source=runner.go:183 msg="removing unsupported or overlapping GPU combination" libDir=/usr/lib/ollama/rocm description="AMD Radeon RX 6650M" compute=gfx1030 pci_id=0000:03:00.0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=TRACE source=runner.go:183 msg="removing unsupported or overlapping GPU combination" libDir=/usr/lib/ollama/rocm description="AMD Radeon 680M" compute=gfx1030 pci_id=0000:09:00.0 Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=2.585911217s Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 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="30.1 GiB" available="25.4 GiB" Mar 27 13:00:40 OMEN ollama[19869]: time=2026-03-27T13:00:40.441-04:00 level=INFO source=routes.go:1848 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096 shannon@OMEN:/etc/systemd/system$ ```
GiteaMirror commented 2026-04-22 19:53:53 -05:00
Author
Owner
Copy Link

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

What's the output of the following two commands:

ls /usr/local/lib/ollama/rocm
find /usr/local/lib/ollama/rocm/ | grep gfx | sed -e 's/.*\(gfx[0-9][0-9]*\).*/\1/'|sort|uniq
<!-- gh-comment-id:4144059879 --> @rick-github commented on GitHub (Mar 27, 2026): What's the output of the following two commands: ``` ls /usr/local/lib/ollama/rocm find /usr/local/lib/ollama/rocm/ | grep gfx | sed -e 's/.*\(gfx[0-9][0-9]*\).*/\1/'|sort|uniq ```
GiteaMirror commented 2026-04-22 19:53:54 -05:00
Author
Owner
Copy Link

@ganakee commented on GitHub (Mar 27, 2026):

ls /usr/local/lib/ollama/rocm
ls: cannot access '/usr/local/lib/ollama/rocm': No such file or directory

find /usr/local/lib/ollama/rocm/ | grep gfx | sed -e 's/.*\(gfx[0-9][0-9]*\).*/\1/'|sort|uniq
find: ‘/usr/local/lib/ollama/rocm/’: No such file or directory
<!-- gh-comment-id:4144099267 --> @ganakee commented on GitHub (Mar 27, 2026): ``` ls /usr/local/lib/ollama/rocm ls: cannot access '/usr/local/lib/ollama/rocm': No such file or directory ``` ``` find /usr/local/lib/ollama/rocm/ | grep gfx | sed -e 's/.*\(gfx[0-9][0-9]*\).*/\1/'|sort|uniq find: ‘/usr/local/lib/ollama/rocm/’: No such file or directory ```
GiteaMirror commented 2026-04-22 19:53:55 -05:00
Author
Owner
Copy Link

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

Sorry, looks like your install is not standard ollama. What variant of linux, Arch?

What's the result of:

ls /usr/lib/ollama/rocm
find /usr/lib/ollama/rocm/ | grep gfx | sed -e 's/.*\(gfx[0-9][0-9]*\).*/\1/'|sort|uniq
<!-- gh-comment-id:4144135590 --> @rick-github commented on GitHub (Mar 27, 2026): Sorry, looks like your install is not standard ollama. What variant of linux, Arch? What's the result of: ``` ls /usr/lib/ollama/rocm find /usr/lib/ollama/rocm/ | grep gfx | sed -e 's/.*\(gfx[0-9][0-9]*\).*/\1/'|sort|uniq ```
GiteaMirror commented 2026-04-22 19:53:55 -05:00
Author
Owner
Copy Link

@ganakee commented on GitHub (Mar 27, 2026):

Ubuntu 25.10

/usr/lib/ollama/rocm
libamd_comgr.so.2          libdrm.so.2               libggml-hip.so              libhipblaslt.so.1.2.70200       librocblas.so.5                   librocsolver.so.0.3.60303
libamd_comgr.so.2.8.60303  libdrm.so.2.123.0         libhipblas.so.2             libhsa-runtime64.so.1           librocblas.so.5.2.70200           librocsolver.so.0.7.70200
libamd_comgr.so.3          libdrm.so.2.4.0           libhipblas.so.2.3.60303     libhsa-runtime64.so.1.14.60303  librocprofiler-register.so.0      libroctx64.so.4
libamd_comgr.so.3.0.0      libdrm_amdgpu.so.1        libhipblas.so.3             libhsa-runtime64.so.1.18.70200  librocprofiler-register.so.0.4.0  libroctx64.so.4.1.70200
libamdhip64.so.6           libdrm_amdgpu.so.1.0.0    libhipblas.so.3.2.70200     libnuma.so.1                    librocprofiler-register.so.0.6.0  rocblas
libamdhip64.so.6.3.60303   libdrm_amdgpu.so.1.123.0  libhipblaslt.so.0           libnuma.so.1.0.0                librocroller.so.1
libamdhip64.so.7           libelf-0.190.so           libhipblaslt.so.0.10.60303  librocblas.so.4                 librocroller.so.1.0.0
libamdhip64.so.7.2.70200   libelf.so.1               libhipblaslt.so.1           librocblas.so.4.3.60303         librocsolver.so.0

find /usr/lib/ollama/rocm/ | grep gfx | sed -e 's/.*\(gfx[0-9][0-9]*\).*/\1/'|sort|uniq
gfx1010
gfx1012
gfx1030
gfx1100
gfx1101
gfx1102
gfx1150
gfx1151
gfx1200
gfx1201
gfx90
gfx900
gfx906
gfx908
gfx942
gfx950
<!-- gh-comment-id:4144206508 --> @ganakee commented on GitHub (Mar 27, 2026): Ubuntu 25.10 ``` /usr/lib/ollama/rocm libamd_comgr.so.2 libdrm.so.2 libggml-hip.so libhipblaslt.so.1.2.70200 librocblas.so.5 librocsolver.so.0.3.60303 libamd_comgr.so.2.8.60303 libdrm.so.2.123.0 libhipblas.so.2 libhsa-runtime64.so.1 librocblas.so.5.2.70200 librocsolver.so.0.7.70200 libamd_comgr.so.3 libdrm.so.2.4.0 libhipblas.so.2.3.60303 libhsa-runtime64.so.1.14.60303 librocprofiler-register.so.0 libroctx64.so.4 libamd_comgr.so.3.0.0 libdrm_amdgpu.so.1 libhipblas.so.3 libhsa-runtime64.so.1.18.70200 librocprofiler-register.so.0.4.0 libroctx64.so.4.1.70200 libamdhip64.so.6 libdrm_amdgpu.so.1.0.0 libhipblas.so.3.2.70200 libnuma.so.1 librocprofiler-register.so.0.6.0 rocblas libamdhip64.so.6.3.60303 libdrm_amdgpu.so.1.123.0 libhipblaslt.so.0 libnuma.so.1.0.0 librocroller.so.1 libamdhip64.so.7 libelf-0.190.so libhipblaslt.so.0.10.60303 librocblas.so.4 librocroller.so.1.0.0 libamdhip64.so.7.2.70200 libelf.so.1 libhipblaslt.so.1 librocblas.so.4.3.60303 librocsolver.so.0 ``` ``` find /usr/lib/ollama/rocm/ | grep gfx | sed -e 's/.*\(gfx[0-9][0-9]*\).*/\1/'|sort|uniq gfx1010 gfx1012 gfx1030 gfx1100 gfx1101 gfx1102 gfx1150 gfx1151 gfx1200 gfx1201 gfx90 gfx900 gfx906 gfx908 gfx942 gfx950 ```
GiteaMirror commented 2026-04-22 19:53:56 -05:00
Author
Owner
Copy Link

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

Ubuntu 25.10

How did you install ollama?

<!-- gh-comment-id:4144213292 --> @rick-github commented on GitHub (Mar 27, 2026): > Ubuntu 25.10 How did you install ollama?
GiteaMirror commented 2026-04-22 19:53:56 -05:00
Author
Owner
Copy Link

@ganakee commented on GitHub (Mar 27, 2026):

This is a puzzle. I use a simple BASH script.
The material part fetches the latest tar files and then install with
for file in "$FILE1" "$FILE2"; do #Remove * ???????
echo "Extracting $file..."
# sudo tar -C /usr -xzf "$file"
sudo tar -C /usr --zstd -xf "$file"

I am starting, based on your notes, to see that the path may have changed with the 0.18.0+.

Should I install to /usr/local rather than /usr?

I manually tried to do that, install both the ollama and rocm extra to /usr/local

I restart the ollama.service on systemd.
I get ollama --version
ollama version is 0.18.4-rc0
Warning: client version is 0.18.3

<!-- gh-comment-id:4144232620 --> @ganakee commented on GitHub (Mar 27, 2026): This is a puzzle. I use a simple BASH script. The material part fetches the latest tar files and then install with for file in "$FILE1" "$FILE2"; do #Remove * ??????? echo "Extracting $file..." # sudo tar -C /usr -xzf "$file" sudo tar -C /usr --zstd -xf "$file" I am starting, based on your notes, to see that the path may have changed with the 0.18.0+. Should I install to /usr/local rather than /usr? I manually tried to do that, install both the ollama and rocm extra to /usr/local I restart the ollama.service on systemd. I get ollama --version ollama version is 0.18.4-rc0 Warning: client version is 0.18.3
GiteaMirror commented 2026-04-22 19:53:57 -05:00
Author
Owner
Copy Link

@ganakee commented on GitHub (Mar 27, 2026):

@rick-github

THANKS!

I think you resolved the issue.

The script was installing to /usr.

I manually un-tarred the ollama baase for AMD and rocm into /usr/local/

I then edited my /etc/systemd/syste/ollama.service to initiate via /usr/local/bin/ollama serve.

sudo systemctl daemon-reload
sudo systemcctl restart ollama.service

now I get
ollama ps
NAME ID SIZE PROCESSOR CONTEXT UNTIL
gemma3n:latest 15cb39fd9394 10 GB 100% GPU 32768 4 minutes from now

<!-- gh-comment-id:4144282422 --> @ganakee commented on GitHub (Mar 27, 2026): @rick-github THANKS! I think you resolved the issue. The script was installing to /usr. I manually un-tarred the ollama baase for AMD and rocm into /usr/local/ I then edited my /etc/systemd/syste/ollama.service to initiate via /usr/local/bin/ollama serve. sudo systemctl daemon-reload sudo systemcctl restart ollama.service now I get ollama ps NAME ID SIZE PROCESSOR CONTEXT UNTIL gemma3n:latest 15cb39fd9394 10 GB 100% GPU 32768 4 minutes from now
GiteaMirror commented 2026-04-22 19:53:57 -05:00
Author
Owner
Copy Link

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

I suggest using the official install method: curl -fsSL https://ollama.com/install.sh | sh

Before doing that, remove the old install:

sudo rm /usr/bin/ollama
sudo rm -rf /usr/lib/ollama

After the install, run sudo systemctl edit ollama and insert the following after the line that says "### Anything between here and the comment below will become the contents of the drop-in file":

[Service]
Environment="OLLAMA_HOST=0.0.0.0"
#Environment="CUDA_VISIBLE_DEVICES=1"
# REMOVED 2025-11-13 Environment="ROCR_VISIBLE_DEVICES=2,3,1,0"
#Environment="ROCR_VISIBLE_DEVICES=1,0"
Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"
#Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"
# REMOVED 2025-11-13 Environment="OLLAMA_DEBUG=2"
#Environment="OLLAMA_DEBUG=1" #ORIGINAL
Environment="OLLAMA_DEBUG=2"

Then restart the service: sudo systemctl restart ollama and run

journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)"
<!-- gh-comment-id:4144283417 --> @rick-github commented on GitHub (Mar 27, 2026): I suggest using the official install method: `curl -fsSL https://ollama.com/install.sh | sh` Before doing that, remove the old install: ``` sudo rm /usr/bin/ollama sudo rm -rf /usr/lib/ollama ``` After the install, run `sudo systemctl edit ollama` and insert the following after the line that says "### Anything between here and the comment below will become the contents of the drop-in file": ``` [Service] Environment="OLLAMA_HOST=0.0.0.0" #Environment="CUDA_VISIBLE_DEVICES=1" # REMOVED 2025-11-13 Environment="ROCR_VISIBLE_DEVICES=2,3,1,0" #Environment="ROCR_VISIBLE_DEVICES=1,0" Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0" #Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0" # REMOVED 2025-11-13 Environment="OLLAMA_DEBUG=2" #Environment="OLLAMA_DEBUG=1" #ORIGINAL Environment="OLLAMA_DEBUG=2" ``` Then restart the service: `sudo systemctl restart ollama` and run ``` journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" ```
GiteaMirror commented 2026-04-22 19:53:58 -05:00
Author
Owner
Copy Link

@ganakee commented on GitHub (Mar 27, 2026):

I will plan to use the official method.

(I have been doing this since c.2024. For so long, the AMD support was achaallenge thus my script solution. I think I can now switch to official! )
THANKS.
@rick-github

<!-- gh-comment-id:4144319841 --> @ganakee commented on GitHub (Mar 27, 2026): I will plan to use the official method. (I have been doing this since c.2024. For so long, the AMD support was achaallenge thus my script solution. I think I can now switch to official! ) THANKS. @rick-github
GiteaMirror commented 2026-04-22 19:53:58 -05:00
Author
Owner
Copy Link

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

Oops, re-open for OP.

<!-- gh-comment-id:4144375008 --> @rick-github commented on GitHub (Mar 27, 2026): Oops, re-open for OP.
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#35398
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?