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

[GH-ISSUE #9599] Ollama checks for amdgpu driver in WSL #32022

New Issue
Closed
opened 2026-04-22 12:53:56 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 12:53:56 -05:00
Owner
Copy Link

Originally created by @cromefire on GitHub (Mar 8, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9599

What is the issue?

In WSL2, ollama checks for the amdgpu module to be present, even though AMD instructs that no amdgpu driver shall be installed for WSL2 (only the userland bits). This results in ollama aborting the check for AMD GPUs. Other checks seem like they might fail as well (the card0 in the drm device is there for example, but the kfd stuff is missing). And there currently doesn't seem to be a way to force the skipping of those checks as far as I can see. And the kfd one also seems vital right now.

The offending check is here: 4100ed7bdd/discover/amd_linux.go (L419)

The same is happening for the installer as well BTW. As the card isn't shown by lspci or lshw, it's not being detected and an AMD compatible install is skipped. Here rocminfo should probably be used:

rocminfo output under WSL2 
WSL environment detected.
=====================
HSA System Attributes
=====================
Runtime Version:         1.1
Runtime Ext Version:     1.6
System Timestamp Freq.:  1000.000000MHz
Sig. Max Wait Duration:  18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model:           LARGE
System Endianness:       LITTLE
Mwaitx:                  DISABLED
DMAbuf Support:          YES

==========
HSA Agents
==========
*******
Agent 1
*******
  Name:                    AMD Ryzen 9 5950X 16-Core Processor
  Uuid:                    CPU-XX
  Marketing Name:          AMD Ryzen 9 5950X 16-Core Processor
  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)
  Cacheline Size:          64(0x40)
  Internal Node ID:        0
  Compute Unit:            32
  SIMDs per CU:            0
  Shader Engines:          0
  Shader Arrs. per Eng.:   0
  Memory Properties:
  Features:                None
  Pool Info:
    Pool 1
      Segment:                 GLOBAL; FLAGS: FINE GRAINED
      Size:                    41072432(0x272b730) 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:                    41072432(0x272b730) 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:                    41072432(0x272b730) 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:                    41072432(0x272b730) KB
      Allocatable:             TRUE
      Alloc Granule:           4KB
      Alloc Recommended Granule:4KB
      Alloc Alignment:         4KB
      Accessible by all:       TRUE
  ISA Info:
*******
Agent 2
*******
  Name:                    gfx1100
  Marketing Name:          AMD Radeon RX 7900 XTX
  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:                      32(0x20) KB
    L2:                      6144(0x1800) KB
    L3:                      98304(0x18000) KB
  Chip ID:                 29772(0x744c)
  Cacheline Size:          64(0x40)
  Max Clock Freq. (MHz):   2304
  Internal Node ID:        1
  Compute Unit:            96
  SIMDs per CU:            2
  Shader Engines:          6
  Shader Arrs. per Eng.:   2
  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                        4294967295(0xffffffff)
    y                        4294967295(0xffffffff)
    z                        4294967295(0xffffffff)
  Max fbarriers/Workgrp:   32
  Packet Processor uCode:: 372
  SDMA engine uCode::      24
  IOMMU Support::          None
  Pool Info:
    Pool 1
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED
      Size:                    25078440(0x17eaaa8) 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:                    25078440(0x17eaaa8) 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--gfx1100
      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                        4294967295(0xffffffff)
        y                        4294967295(0xffffffff)
        z                        4294967295(0xffffffff)
      FBarrier Max Size:       32
*** Done ***

Relevant log output

time=2025-03-08T17:35:42.102+01:00 level=DEBUG source=amd_linux.go:419 msg="amdgpu driver not detected /sys/module/amdgpu"
time=2025-03-08T17:35:42.102+01:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-03-08T17:35:42.102+01:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="39.2 GiB" available="38.1 GiB"

OS

WSL2 ubuntu 24.04

GPU

AMD

CPU

AMD

Ollama version

0.5.13

Originally created by @cromefire on GitHub (Mar 8, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9599 ### What is the issue? In WSL2, ollama checks for the `amdgpu` module to be present, even though AMD instructs that [no `amdgpu` driver shall be installed for WSL2](https://rocm.docs.amd.com/projects/radeon/en/latest/docs/install/wsl/install-radeon.html#wsl-usecase) (only the userland bits). This results in ollama aborting the check for AMD GPUs. Other checks seem like they might fail as well (the card0 in the drm device is there for example, but the kfd stuff is missing). And there currently doesn't seem to be a way to force the skipping of those checks as far as I can see. And the kfd one also seems vital right now. The offending check is here: https://github.com/ollama/ollama/blob/4100ed7bdd417ae6d25bf64467fb9df33f3f6525/discover/amd_linux.go#L419 The same is happening for the installer as well BTW. As the card isn't shown by `lspci` or `lshw`, it's not being detected and an AMD compatible install is skipped. Here `rocminfo` should probably be used: <details> <summary>rocminfo output under WSL2</summary> ``` WSL environment detected. ===================== HSA System Attributes ===================== Runtime Version: 1.1 Runtime Ext Version: 1.6 System Timestamp Freq.: 1000.000000MHz Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count) Machine Model: LARGE System Endianness: LITTLE Mwaitx: DISABLED DMAbuf Support: YES ========== HSA Agents ========== ******* Agent 1 ******* Name: AMD Ryzen 9 5950X 16-Core Processor Uuid: CPU-XX Marketing Name: AMD Ryzen 9 5950X 16-Core Processor 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) Cacheline Size: 64(0x40) Internal Node ID: 0 Compute Unit: 32 SIMDs per CU: 0 Shader Engines: 0 Shader Arrs. per Eng.: 0 Memory Properties: Features: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: FINE GRAINED Size: 41072432(0x272b730) 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: 41072432(0x272b730) 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: 41072432(0x272b730) 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: 41072432(0x272b730) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE ISA Info: ******* Agent 2 ******* Name: gfx1100 Marketing Name: AMD Radeon RX 7900 XTX 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: 32(0x20) KB L2: 6144(0x1800) KB L3: 98304(0x18000) KB Chip ID: 29772(0x744c) Cacheline Size: 64(0x40) Max Clock Freq. (MHz): 2304 Internal Node ID: 1 Compute Unit: 96 SIMDs per CU: 2 Shader Engines: 6 Shader Arrs. per Eng.: 2 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 4294967295(0xffffffff) y 4294967295(0xffffffff) z 4294967295(0xffffffff) Max fbarriers/Workgrp: 32 Packet Processor uCode:: 372 SDMA engine uCode:: 24 IOMMU Support:: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 25078440(0x17eaaa8) 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: 25078440(0x17eaaa8) 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--gfx1100 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 4294967295(0xffffffff) y 4294967295(0xffffffff) z 4294967295(0xffffffff) FBarrier Max Size: 32 *** Done *** ``` </details> ### Relevant log output ```shell time=2025-03-08T17:35:42.102+01:00 level=DEBUG source=amd_linux.go:419 msg="amdgpu driver not detected /sys/module/amdgpu" time=2025-03-08T17:35:42.102+01:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-03-08T17:35:42.102+01:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="39.2 GiB" available="38.1 GiB" ``` ### OS WSL2 ubuntu 24.04 ### GPU AMD ### CPU AMD ### Ollama version 0.5.13
GiteaMirror added the bug label 2026-04-22 12:53:56 -05:00
GiteaMirror commented 2026-04-22 12:53:57 -05:00
Author
Owner
Copy Link

@yongkaikai commented on GitHub (Apr 14, 2025):

@cromefire Hope this finds you well, I catch the same problem as you.
Did you solve this problem?

<!-- gh-comment-id:2801944473 --> @yongkaikai commented on GitHub (Apr 14, 2025): @cromefire Hope this finds you well, I catch the same problem as you. Did you solve this problem?
GiteaMirror commented 2026-04-22 12:53:57 -05:00
Author
Owner
Copy Link

@cromefire commented on GitHub (Apr 14, 2025):

Nope

<!-- gh-comment-id:2801949818 --> @cromefire commented on GitHub (Apr 14, 2025): Nope
GiteaMirror commented 2026-04-22 12:53:58 -05:00
Author
Owner
Copy Link

@xyuanwenjie commented on GitHub (Apr 26, 2025):

@cromefire Hope this finds you well, I catch the same problem as you. Did you solve this problem?

+1

<!-- gh-comment-id:2832279709 --> @xyuanwenjie commented on GitHub (Apr 26, 2025): > [@cromefire](https://github.com/cromefire) Hope this finds you well, I catch the same problem as you. Did you solve this problem? +1
GiteaMirror commented 2026-04-22 12:53:58 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 5, 2025):

AMD GPU support inside WSL2 is tracked via #5275

<!-- gh-comment-id:3039876752 --> @dhiltgen commented on GitHub (Jul 5, 2025): AMD GPU support inside WSL2 is tracked via #5275
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#32022
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?