github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6588] Intel ARC PRO not working on Windows install. #4146

New Issue
Closed
opened 2026-04-12 15:03:29 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 15:03:29 -05:00
Owner
Copy Link

Originally created by @Solaris17 on GitHub (Sep 2, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6588

What is the issue?

I am having problems getting Ollama to run GPU accelerated. Even with the github pull req that pulls llama.cpp. I also installed openVINO. I am using an ARC Pro A40 and the system also has an iGPU. When attempting to run the software though the following is given in the logs.

This is a windows install.
https://pastebin.com/Zyn0DSNw

2024/09/01 20:51:22 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Solaris17\\.ollama\\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_RUNNERS_DIR:C:\\Users\\Solaris17\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-09-01T20:51:22.669-05:00 level=INFO source=images.go:753 msg="total blobs: 0" time=2024-09-01T20:51:22.669-05:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0" time=2024-09-01T20:51:22.670-05:00 level=INFO source=routes.go:1172 msg="Listening on 127.0.0.1:11434 (version 0.3.9)" time=2024-09-01T20:51:22.686-05:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v12 rocm_v6.1 cpu cpu_avx cpu_avx2 cuda_v11]" time=2024-09-01T20:51:22.686-05:00 level=INFO source=gpu.go:200 msg="looking for compatible GPUs" time=2024-09-01T20:51:22.842-05:00 level=INFO source=gpu.go:347 msg="no compatible GPUs were discovered"

OS

Windows

GPU

Intel

CPU

Intel

Ollama version

0.3.9

Originally created by @Solaris17 on GitHub (Sep 2, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6588 ### What is the issue? I am having problems getting Ollama to run GPU accelerated. [Even with the github pull req that pulls llama.cpp](https://github.com/ollama/ollama/pull/3278). I also installed openVINO. I am using an ARC Pro A40 and the system also has an iGPU. When attempting to run the software though the following is given in the logs. This is a windows install. https://pastebin.com/Zyn0DSNw `2024/09/01 20:51:22 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Solaris17\\.ollama\\models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_RUNNERS_DIR:C:\\Users\\Solaris17\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-09-01T20:51:22.669-05:00 level=INFO source=images.go:753 msg="total blobs: 0" time=2024-09-01T20:51:22.669-05:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0" time=2024-09-01T20:51:22.670-05:00 level=INFO source=routes.go:1172 msg="Listening on 127.0.0.1:11434 (version 0.3.9)" time=2024-09-01T20:51:22.686-05:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v12 rocm_v6.1 cpu cpu_avx cpu_avx2 cuda_v11]" time=2024-09-01T20:51:22.686-05:00 level=INFO source=gpu.go:200 msg="looking for compatible GPUs" time=2024-09-01T20:51:22.842-05:00 level=INFO source=gpu.go:347 msg="no compatible GPUs were discovered"` ### OS Windows ### GPU Intel ### CPU Intel ### Ollama version 0.3.9
GiteaMirror added the bug label 2026-04-12 15:03:29 -05:00
GiteaMirror commented 2026-04-12 15:03:31 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 3, 2024):

Intel ARC GPU support is tracked via #1590 (partial support is checked into the tree if you build from source, but it isn't in our official builds yet)

<!-- gh-comment-id:2327450945 --> @dhiltgen commented on GitHub (Sep 3, 2024): Intel ARC GPU support is tracked via #1590 (partial support is checked into the tree if you build from source, but it isn't in our official builds yet)
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#4146
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?